Natural Language-based Egocentric Task Verification (NLETV) aims to verify the alignment between action sequences in egocentric videos and their corresponding textual descriptions. However, existing NLETV approaches are still facing two critical challenges: (1) These methods are designed for simulating environments, ignoring the domain gap between synthetic and realistic data. (2) The matching processes are regarded as a simple binary classification problem, which undermines model reliability due to evaluation bias and uncalibrated decision settings. To address these challenges, we propose a novel method termed Prototypical Evidential Learning (PEL), which can be adapted to existing NLETV approaches and boost the model generalization and mitigate prediction bias. Our method leverages prototypes to guide cross-domain alignment and evidence collection. Specifically, PEL consists of two key components: (1) Prototypical Domain Adaptation module enabling cross-domain feature alignment and intra-domain prototype preservation between synthetic and realistic domains; (2) Matching Evidence Collector module, which quantifies prediction uncertainty on the prototypical representations through evidential deep learning. It enforces the model to collect the vision-text consistency and discrepancy evidence, thus addressing the issues of biased decisions in binary classification. Extensive experiments on two public datasets demonstrate that our PEL method outperforms existing state-of-the-art NLETV methods and shows remarkable generalizability.

The Point-of-Interest (POI) recommender systems utilize users’ historical check-in sequences to predict future visits and are widely used in location-based social service platforms. However, users’ check-in behaviors often exhibit strong spatial constraints and temporal dependencies, as users typically visit only a limited set of POIs. This leads to a long-tail distribution and severe data sparsity, which obscures the contribution of individual decision factors such as specific POI characteristics, temporal preferences, and geographic proximity, and limits model generalization due to insufficient fine-grained supervision. To address these issues, we propose a multi-factor generative adversarial framework, GANPOI, that integrates a multi-head discriminator within a generative adversarial network architecture to mitigate data sparsity and improve recommendation accuracy. Specifically, the proposed model consists of two primary components: (1) the generator module models user trajectories using a Transformer-based architecture and employs adversarial training to capture self-supervised signals from check-in contexts; and (2) a multi-head discriminator module composed of several sub-discriminators, each performing task-specific discrimination from different semantic perspectives. This structure enhances the model’s ability to capture fine-grained contextual factors influencing user decisions. Extensive experiments on three real-world datasets demonstrate that GANPOI consistently outperforms existing state-of-the-art POI recommendation methods. To facilitate reproducibility, we have released both the code and the POI recommendation datasets we used. The source codes and datasets are available at https://anonymous.4open.science/r/GANPOI-YYR .

Multi-modal hashing aims to succinctly encode heterogeneous modalities into binary hash codes, facilitating efficient multimedia retrieval characterized by low storage demands and high retrieval speed. Despite the commendable achievements of existing methods, they still face three crucial challenges: 1) Inadequate bridging of the heterogeneous modality gap through coarse, global feature-level alignment and fusion. 2) The erosion of bit independence and consequent limitations on the semantic representation capacity of hash codes during feature-level hash code learning. 3) The insufficiency of binary label-based pairwise semantic preservation strategies in capturing intricate fine-grained semantic correlations within multi-modal data. To address these challenges, this paper introduces the Dynamic Bit-wise Semantic Transformer Hashing (DBSTH) framework. Remarkably, it treats each hash bit as a unique semantic concept, facilitating concept-level alignment of heterogeneous modalities. This safeguards bit independence and augments representation capabilities. Specifically, we devise a dynamic unit fusion strategy for the adaptive combination of local multi-modal information units, facilitating the acquisition of bit-wise semantic concepts. Subsequently, we incorporate a transformer encoder to refine these concepts by uncovering latent correlations among distinct concepts. Finally, we perform the multi-modal alignment and fusion on the fine-grained concept-level, independently encoding each concept to its corresponding hash bit. To provide enhanced guidance for concept learning, a label prototype learning mechanism is introduced, which learns prototype embeddings for all categories through the consideration of co-occurrence priors. This mechanism effectively captures fine-grained explicit semantic correlations and generates supervising hash codes. Additionally, to improve the robustness of the hashing model in handling noisy multi-modal data, a masked concept learning strategy is introduced, facilitating the acquisition of resilient semantic concepts. Extensive experiments conducted on three widely tested multi-modal retrieval datasets demonstrate the superiority of our method in conventional, noisy, and open-set retrieval scenarios.

Eliminating semantic discrepancy between different modalities is the ultimate goal of image text retrieval. However, most of the existing methods only focus on retrieval of the ground-truth instance while ignoring those semantically similar instances yet unlabeled as positives, which causes the phenomenon of one-to-many correspondence. The mainstream solutions of this research are mainly based on uncertainty learning and the exploration of one-to-many correspondence is still insufficient albeit their significant progress. Therefore, this work develops a novel Distribution-to-Points (termed D2P) matching mechanism for image-text retrieval to capture the one-to-many correspondence between multiple samples and a given query via hypergraph modeling. Specifically, a given query is first mapped as a probabilistic embedding to learn its true semantic distribution based on Mahalanobis distance. Then each candidate instance in a mini-batch is regarded as a hypergraph node with its mean semantics while a Gaussian query is modeled as a hyperedge to capture the semantic correlations beyond the pair between candidate points and the query. Moreover, an energy-based semantic modeling framework is developed to pull all similar candidates (not only the ground truth) close to their query while pushing those dissimilar ones far away. In the end, distribution-to-points matching is learned based on the similarity measurement over the Mahalanobis distance, which considers semantic variance to perform many-to-one correspondence well. Experimental results on several widely used datasets and under various evaluation metrics confirm our superiority and effectiveness in improving the retrieval ability of the baseline including ground-truth matching and semantic multiplicity for image text retrieval.

Continual cross-modal hashing is critical for efficient retrieval across heterogeneous modalities in dynamic environments. Yet, existing approaches primarily focus on mitigating catastrophic forgetting, while overlooking two key challenges: 1) the hash collision arising from the excessive utilization of the Hamming space across tasks, and 2) the absence of consistency modeling for cross-modal dynamic associations. To address these challenges, we introduce Prompt-driven Bit Extension Hashing (PBEH), a novel framework that dynamically extends hash codes to prevent hash collisions and capture evolving modality-aligned semantics in continuously expanding multi-modal data. Specifically, PBEH first adaptively initializes a set of modality-shared prompts for each task, which are jointly optimized with the hashing functions to enhance model plasticity and retain task-specific knowledge, enabling continual cross-modal semantic alignment. In parallel, a dynamic Hamming space extension mechanism allocates dedicated capacity per task, alleviating bottlenecks and inter-task collisions. During retrieval, queries are encoded via the extended hash functions and matched to stored codes using a truncated strategy for compatibility. To ensure efficiency and semantic stability, only the prompts and hashing functions are updated while the pre-trained backbone remains frozen. Extensive experiments demonstrate that PBEH achieves superior and stable performance in continual cross-modal retrieval with substantially reduced computational overhead. The source codes and datasets are available at https://github.com/Liuwwhh/PBEH.

Image-text matching as a fundamental cross-modal understanding task presents unique challenges in weakly-aligned scenarios. Such data typically feature highly abstract textual captions with sparse entity references, creating a significant semantic gap with visual content. Current mainstream methods, primarily designed for strongly aligned data pairs, employ dynamic modeling or multi-dimensional similarity computation to achieve feature space mapping. However, they struggle with information asymmetry and modal heterogeneity in weakly aligned cases. To address this, we propose a Visual Perception Knowledge Enhancement (VPKE) framework. Unlike existing methods based on strong alignment assumptions, this framework mines latent image semantics through vision-language models and generates auxiliary captions, overcoming the information bottleneck of traditional text modalities. Its core innovation lies in an adaptive knowledge distillation mechanism that combines retrieval-augmented generation (RAG) with key entity extraction. This mechanism effectively filters noise when introducing external knowledge while optimizing cross-modal feature integration. The framework employs multi-level similarity evaluation to dynamically adjust fusion weights among original text, key entities, and auxiliary captions, enabling adaptive integration of diverse semantic features and significantly improving model flexibility. Additionally, multi-scale feature extraction further enhances cross-modal representation capabilities. Experimental results show that the proposed method performs excellently in image-text retrieval tasks on the MSCOCO and Flickr30K datasets, validating its effectiveness.

Deep cross-modal hashing models generally inherit the vulnerabilities of deep neural networks, making them susceptible to adversarial attacks and thus posing a serious security risk during real-world deployment. Current adversarial attack or defense strategies often establish a weak correlation between the hashing codes and the targeted semantic representations, and there is still a lack of related works that simultaneously consider the attack and defense for deep cross-modal hashing. To alleviate these concerns, we propose a Fuzzy-Prototype-guided Adversarial Attack and Defense (FPAD) framework to enhance the adversarial robustness of deep cross-modal hashing models. First, an adaptive fuzzy-prototype learning network (FpNet) is efficiently presented to extract a set of fuzzy-prototypes, aiming to encode the underlying semantic structure of the heterogeneous modalities in both feature and Hamming spaces. Then, these derived prototypical hash codes are heuristically employed to supervise the generation of high-quality adversarial examples, while a fuzzy-prototype rectification scheme is simultaneously designed to preserve the latent semantic consistency between the adversarial and benign examples. By mixing the adversarial samples with the original training samples as the augmented inputs, an efficient fuzzy-prototype-guided adversarial learning framework is proposed to execute the collaborative adversarial training and generate robust cross-modal hash codes with high adversarial defense capabilities, therefore resisting various attacks and benefiting various challenging cross-modal hashing tasks. Extensive experiments evaluated on benchmark datasets show that the proposed FPAD framework not only produces high-quality adversarial samples to enhance the adversarial training process, but also shows its high adversarial defense capability to benefit various cross-modal hashing tasks. The code is available at: https://github.com/yzq131/FPAD.

The Vision-language navigation task requires agents to efficiently interpret visual cues in the environment and accurately follow long-range instructions, posing significant challenges to their scene memory and spatial reasoning capabilities. Existing methods typically construct memory systems directly from raw visual observations. However, task-irrelevant cues commonly present in the environment can continuously introduce localization errors during navigation, severely limiting the agent’s performance in complex scenes. Meanwhile, due to the lack of transferable general knowledge priors, existing agents exhibit notable limitations in spatial perception, which undermines the reliability of their decision-making in unseen environments. To address these issues, this paper proposes the dynamic object filtering with Spatial Perception Enhancement for Vision-Language Navigation (SPENav), which aggregates open-vocabulary perception with multi-level information modeling. At the local level, the Hierarchical Semantic Prior Extractor and Room-Information-Guided Filtering construct task-oriented semantic priors to capture critical objects and suppress irrelevant features. At the global level, the Spatial-Instructional Guided Dual Attention module leverages spatial information and instruction guidance to enable the agent to develop selective memory that is goal- and task-oriented. On the unseen test split of R2R, SPENav achieves a 76% Success Rate (SR) and a 65% Success weighted by Path Length (SPL). These results demonstrate the effectiveness of task-oriented feature selection and multi-level semantic modeling in enhancing cross-modal understanding and adaptive navigation performance.

In egocentric videos, collecting and annotating supervised data is more complicated and time-consuming than in exocentric videos, limiting research in this area. As a remedy, Unsupervised Domain Adaptation (UDA) enhances model performance on unlabeled target domains by bridging the distribution gap between source and target domains. However, UDA for egocentric action recognition is under-explored, facing unique challenges such as simultaneous learning of verb and noun representations, focusing on human-object interactions, and managing excessive verb-noun combinations. To tackle these issues, we propose a novel Unsupervised Domain Adaptation for Egocentric Action Recognition (UDA-EAR) approach that adaptively models egocentric actions and facilitates cross-domain knowledge transfer, improving recognition performance in unlabeled target domains. Specifically, our UDA-EAR employs adaptive spatio-temporal and spatio-channel attention in a dual-branch pipeline to focus on motion intervals and interaction regions, respectively, allowing specialized learning of discriminative representations while avoiding negative combination dependencies from domain gaps. Additionally, an adversarial domain alignment mechanism aligns the data distributions between source and target domains, effectively transferring fine-grained verb-noun knowledge of egocentric videos. Extensive experiments demonstrate that our UDA-EAR outperforms state-of-the-art baselines on widely used egocentric datasets, significantly improving egocentric action recognition accuracy. Our source codes and datasets are available at https://github.com/zou-y23/UDA-EAR.

Federated domain generalization (FedDG) aims to improve the global model’s generalization ability in unseen domains by addressing data heterogeneity under privacy-preserving constraints. A common strategy in existing FedDG studies involves sharing domain-specific knowledge among clients, such as spectrum information, class prototypes, and data styles. However, this knowledge is extracted directly from local client samples, and sharing such sensitive information poses a potential risk of data leakage, which might not fully meet the FedDG requirements. In this paper, we introduce prompt learning to adapt pretrained vision-language models (VLMs) in the FedDG scenario, and leverage locally learned prompts as a more secure bridge to facilitate knowledge transfer among clients. Specifically, we propose a novel FedDG framework through Prompt Learning and AggregatioN (PLAN), which comprises two training stages to collaboratively generate local prompts and global prompts at each federated round. First, each client performs both text and visual prompt learning using their own data, with local prompts indirectly synchronized by regarding the global prompts as a common reference. Second, all domain-specific local prompts are exchanged among clients and selectively aggregated into global prompts using lightweight attention-based aggregators. The global prompts are finally applied to adapt the VLMs to unseen target domains. As our PLAN framework requires training only a limited number of prompts and lightweight aggregators, it offers notable advantages in terms of computational and communication efficiency for FedDG. Extensive experiments demonstrate the superior generalization ability of PLAN across four benchmark datasets. We have released our code at https://github.com/GongShuai8210/PLAN.

Federated Domain Generalization (FedDG) aims to train a globally generalizable model on data from decentralized, heterogeneous clients. While recent work has adapted vision-language models for FedDG using prompt learning, the prevailing "one-prompt-fits-all" paradigm struggles with sample diversity, causing a marked performance decline on personalized samples. The Mixture of Experts (MoE) architecture offers a promising solution for specialization. However, existing MoE-based prompt learning methods suffer from two key limitations: coarse image-level expert assignment and high communication costs from parameterized routers. To address these limitations, we propose TRIP, a Token-level pRompt mIxture with Parameter-free routing framework for FedDG. TRIP treats prompts as multiple experts, and assigns individual tokens within an image to distinct experts, facilitating the capture of fine-grained visual patterns. To ensure communication efficiency, TRIP introduces a parameter-free routing mechanism based on capacity-aware clustering and Optimal Transport (OT). First, tokens are grouped into capacity-aware clusters to ensure balanced workloads. These clusters are then assigned to experts via OT, stabilized by mapping cluster centroids to static, non-learnable keys. The final instance-specific prompt is synthesized by aggregating experts, weighted by the number of tokens assigned to each. Extensive experiments across four benchmarks demonstrate that TRIP achieves optimal generalization results, with communicating as few as 1K parameters. Our code is available at https://github.com/GongShuai8210/TRIP.

Noisy Correspondence (NC), caused by mismatched pairs in multimedia datasets, poses major challenges for cross-modal retrieval, especially under high noise levels. Existing solutions often suffer from substantial performance degradation as noise levels increase. To address this issue, we propose Pseudo-Text guided Robust Learning (PTRL), a novel framework designed to identify noisy pairs and enhance model robustness. Specifically, PTRL leverages pseudo-text as explicit supervision signals and introduces a new data division criterion to accurately distinguish between clean and noisy pairs. Instead of discarding or directly using noisy data, PTRL proposes a pseudo-text replacement strategy to maintain semantic consistency of the training set, thereby facilitating more reliable learning. In addition, pseudo-text-image pairs serve as a form of data augmentation, enriching data diversity and improving model generalization. To further stabilize training and mitigate overfitting, PTRL incorporates a robust InfoNCE loss that is particularly effective in the presence of noise. Extensive experiments demonstrate that PTRL achieves state-of-the-art performance and robustness, with an RSum improvements of +60.1% on Flickr30K and +22.6% on MS-COCO at an 80% noise level, significantly outperforming existing methods. The datasets and source code are available at https://github.com/shidan0122/PTRL.git.

Multi-behavior recommender systems have demonstrated their effectiveness in mitigating issues such as data sparsity by incorporating auxiliary behaviors into the target behavior. However, existing multi-behavior recommendation approaches typically take one of two directions: (1) fusing behavior-specific preference features from various behavior interaction graphs explicitly or implicitly for recommendation; or (2) utilizing behavior-unified preference features from the unified interaction graph for recommendation or to initialize features for subsequent modeling. These methods fail to exploit the integration of behavior-unified global and behavior-specific local preference features, resulting in incomplete preference modeling. To address this issue, in this work, we propose a novel method calledUnifyingGlobal andLocalPreferences (UGLP) for multi-behavior recommendation. In UGLP, we design a behavior feature fusion network that consists of global and local fusion modules for comprehensive and fine-grained user preferences. The global fusion module performs graph convolution on behavior-unified global and behavior-specific local interaction graphs to obtain behavior-unified and behavior-specific features. The behavior-unified and behavior-specific features are then fused into globally fused features via a gating network. The local fusion module then performs cross-behavior fusion on these globally fused features via another gating network. We introduce a contrastive learning module to promote preference alignment and knowledge transfer from auxiliary behaviors to the target behavior. Additionally, we incorporate a GCN refinement module to adjust the fused features to ensure that both global and local user preferences are learned. Experimental results on three real-world datasets verify that our method is able to surpass various state-of-the-art models. For instance, our method outperforms the best baseline by an average of 16.43% and 14.36% in terms of HR@10 and NDCG@10, respectively.

Spatio-temporal time series (STTS) play a crucial role in domains such as traffic forecasting, energy scheduling, and financial analysis. However, accurate and efficient prediction remains challenging due to the complex dynamic dependencies across temporal and spatial dimensions. Existing Graph Neural Networks (GNNs) often struggle to balance effectiveness and efficiency when modeling dynamic spatio-temporal relations. Meanwhile, Large Language Models (LLMs) exhibit strong capabilities in modeling long-range dependencies and generalization under few-shot and zero-shot conditions, yet their ability to capture spatio-temporal structures remains limited. To address this, we propose LAD-SGNN, a unified framework that integrates the advantages of graph-based and language-based modeling. Specifically, LAD-SGNN employs Spectral Graph Convolution on the Stiefel manifold (SGSC) together with Linear Dynamic Graph Optimization (LDGOSM) to efficiently extract dynamic spatio-temporal features with nearly linear complexity. Structured prompts and a spatio-temporal alignment mechanism are then designed to fuse the extracted dynamic spectral information with task semantics, which are fed into a lightweight LLM to achieve unified modeling of spatio-temporal structures and semantic reasoning. In this framework, SGSC efficiently represents dynamic spatial dependencies in the spectral domain, while the prompt-based alignment strategy explicitly injects spatio-temporal information into the LLM, thereby enhancing generalization across datasets. Extensive experiments on multiple real-world spatio-temporal datasets demonstrate that LAD-SGNN significantly improves prediction accuracy in both zero-shot and few-shot scenarios.

Cross-modal hashing models face significant challenges in handling continuous data growth, particularly in balancing the plasticity to learn new knowledge and the stability to retain prior cross-modal knowledge. Existing studies partially address this by maintaining previous mappings or extending hash codes, but struggle to reconcile plasticity and stability while requiring heavy parameter optimization. To tackle this, we propose an efficient Prompt-Infused Continual Cross-Modal Hashing (PIC-CMH) approach designed for hash learning with the continuous growth of multi-modal data and emerging knowledge. Specifically, PIC-CMH introduces a finite set of learnable multi-modal prompts, including global and task-specific expert prompts, which work in synergy with multi-modal representations. All prompts are optimized with the hash functions via backpropagation after Gaussian initialization. Global prompts stay learnable throughout, linking tasks, while expert prompts are updated only within their tasks, facilitating knowledge acquisition and mitigating catastrophic forgetting in continual learning. By freezing the pre-trained models used for multi-modal representations, continual learning is confined to the lightweight multi-modal prompts and hash functions, significantly reducing computational overhead. Extensive experiments demonstrate that PIC-CMH effectively addresses the stability-plasticity trade-off in cross-modal hash learning, delivering high retrieval accuracy with low computational cost and a simple yet efficient architecture. The source codes and datasets are available athttps://github.com/styx29-0/PIC-CMH.

The objective of the Point-of-Interest (POI) recommendation system is to predict potential future visits based on users' check-in histories. However, due to factors such as users' tendency to visit nearby locations, time and space mobility costs, users are more likely to visit a limited number of POIs within a confined geographical area. Consequently, POI recommendation faces a more severe data sparsity issue compared to other recommendation scenarios. Current research has shown that incorporating multimodal content information into POI recommendations can effectively alleviate the data sparsity problem. However, existing methods still have the following limitations: 1) Multimodal noise hinders the effective extraction of multimodal content. 2) Multimodal feature fusion ignores the differential impact of various modalities on user decisions. To address these issues, we propose anInterest-awareMultiModal adaptive fusion framework forPOIrecommendations (IMMPOI). Specifically, we propose an interest-oriented purifier to perform multimodal noise filtering based on user preference, and introduce a disentangled multimodal graph encoder to accurately capture fine-grained behavior features, multimodal features, geographical, and sequential relationships between users and POIs. Then, we develop an interest-aware multimodal fuser that learns comprehensive multimodal representations of users and POIs by adaptively integrating multimodal content features and context features based on a self-supervised strategy. Extensive experiments on four real-world datasets demonstrate that IMMPOI achieves a 6% to 10% performance improvement compared to state-of-the-art methods.

Unsupervised cross-domain image retrieval (UCDIR) aims to obtain images with the same category from other domains yet without labels for all data. The prevailing strategy first enhances the intra-domain representation by clustering, and then realizes cross-domain alignment based on various similarity comparisons. Despite their significant advancements, current methods are hindered by substantial ambiguity resulting from the absence of explicit semantic information, exacerbated by various sources of noise such as background interference and attribute composition. This difficulty can compromise the performance of existing clustering-based methods. Therefore, we propose a straightforward yet effective strategy to Progressively Alleviate Noise (termedPAN) for UCDIR. We initially utilize information entropy to quantify the certainty of prediction, which also serves as an indicator of uncertainty level resulting from noise. We further refine a progressive learning approach that specifically targets data with low confidence to enhance the semantic comprehension. The model can gradually focus on data with appropriate uncertainty for semantic learning and cross-domain alignment via dynamic reweighing, thereby excluding the adverse effects of noisy data in an incremental manner. Extensive experiments on three widely used datasets for UCDIR demonstrate our effectiveness and superiority.

Video Question Answering (VideoQA) requires clarifying the true question intent and understanding dynamic video content to predict the answer. However, most existing methods overlook the temporal semantic exploration of fine-grained clues across frames, and neglect the interrogative properties of question text, leading to suboptimal grounding of video frames. To address these limitations, in this paper, we propose a novel Semantic Coherence Learning (SCL) framework, which explicitly models the fine-grained spatio-temporal coherence of critical visual regions and progressively mines multi-modal semantic clues aligned with the reasoning intent. Specifically, we design a spatio-temporal clue reasoning module to adaptively model the fine-grained coherent transition semantics of critical regions across temporal frames while suppressing irrelevant noisy regions within frames. Additionally, we propose a multi-modal clue reasoning module to progressively mine multi-modal coherent semantics associated with reasoning intent, which iteratively grounds critical frames in videos based on refined question semantics and mines critical phrases in questions based on refined video semantics. Finally, the answer is derived through an answer decoder with intra and inter-sample contrastive strategies. Extensive experimental results on six widely used benchmarks verify our effectiveness and superiority. The experimental source codes are available at https://github.com/XizeWu/SCL.

In large-scale Point-of-Interest (POI) recommendation, the conflict between accuracy and computational efficiency intensifies as POI catalogs grow. Traditional deep models struggle to balance quality with efficiency. To address this challenge, we propose a knowledge-distilled product quantization framework EffiPOI for efficient POI recommendation. EffiPOI jointly optimizes accuracy and efficiency by integrating product quantization with multi-modal knowledge distillation. Specifically, we first construct service-oriented multi-modal POI representations, which comprehensively capture each POI’s spatial coverage, temporal activity patterns, and semantic attributes. Based on these representations, we design a teacher-student distillation paradigm. The teacher model adopts a Mixture-of-Experts architecture to generate discriminative and semantically expressive POI representations, which serve as high-quality supervision signals for guiding the student model through knowledge distillation. The student model leverages product quantization to encode POIs into compact and computation-friendly representations, achieving a favorable tradeoff between representational compactness and predictive accuracy. To alleviate the performance degradation due to quantization, we develop a hybrid knowledge distillation strategy that transfers both response-aware and feature-aware knowledge from the teacher model to the student model. Experimental results on three real-world datasets show that the proposed method achieves 4.6%–12.1% improvements in accuracy and over 10× speedup in inference efficiency, outperforming existing POI recommendation models. Code is available at: https://github.com/pcm1217/EffiPOI .

Deep hashing has proven remarkable effectiveness for large-scale cross-modal retrieval, yet its performance is highly vulnerable to supervisory noise, such as mismatched cross-modal correspondences and incorrect category labels. Such noise is prevalent in real-world scenarios, where correspondence mismatches and label inaccuracies often coexist, posing significant challenges for learning accurate multimodal representations. Existing methods typically address only a single type of noise in isolation and neglect the potential value of noisy data, resulting in limited performance gains. To address these challenges, we propose Noise-Robust Generative Hashing (NRGH), a unified framework designed to accommodate various forms of noise inherent in cross-modal retrieval. Specifically, NRGH introduces a hash-driven noise estimation module that computes the confidence score for each multimodal sample by combining frozen auxiliary hash functions with a Gaussian mixture model. Guided by these confidence scores, NRGH performs data correction through two stages: generative text refinement and multi-label probability calibration. The former leverages a pre-trained vision-language model to generate descriptive captions that refine noisy textual information, while the latter corrects noisy labels using confidence-aware soft labels. Furthermore, a dynamic margin contrastive loss adaptively modulates the data contribution of each sample based on its confidence, enabling sample-level adaptive learning. Extensive experiments on benchmark datasets demonstrate that NRGH significantly exceeds state-of-the-art baselines in various noisy scenarios, delivering superior robustness and accuracy. Our source codes and datasets are available at https://github.com/xiaolaohuuu/NRGH .

Existing semi-supervised learning (SSL) approaches follow the idealized closed-world assumption, neglecting the challenges present in realistic medical scenarios, such as open-set distribution and imbalanced class distribution. Although some methods in natural domains attempt to address the open-set problem, they are insufficient for medical domains, where intertwined challenges like class imbalance and small inter-class lesion discrepancies persist. Thus, this paper presents a novel self-recalibrated semantic training framework, which is tailored for SSL in medical imaging by ingeniously harvesting realistic unlabeled samples. Inspired by the observation that certain open-set samples share some similar disease-related representations with in-distribution samples, we first propose an informative sample selection strategy that identifies high-value samples to serve as augmentations, thereby effectively enriching the semantics of known categories. Furthermore, we adopt a compact semantic clustering strategy to address the semantic confusion raised by the above newly introduced open-set semantics. Moreover, to mitigate the interference of class imbalance in open-set SSL, we introduce a less biased dual-balanced classifier with similarity pseudo-label regularization and category-customized regularization. Extensive experiments on a variety of medical image datasets demonstrate the superior performance of our proposed method over state-of-the-art Closed-set and Open-set SSL methods.

Unsupervised domain adaptation (UDA) has emerged as a promising technique for transferring knowledge from a labeled domain to an unlabeled domain. However, existing UDA methods are severely constrained by data privacy and semantic inconsistencies. To alleviate these limitations, this work challenges the Source-Free Open-Set Domain Adaptation (SF-OSDA), where the pre-trained source model is directly leveraged on the open target domain for adaptation. For this purpose, we introduce the novel Dynamic Target Distribution Estimation (DTDE) method, which effectively performs known classification and unknown separation through self-supervised learning with prototypes. To construct known prototypes, a self-adaptive sampling strategy is employed to consider the category disparity. For unknown prototypes, we utilize a self-splitting and excluding principle to bypass the unknown semantics problem. Specifically, self-splitting is to evaluate the overall clustering distribution of the target domain. By excluding clusters resembling known prototypes, the remaining cluster centroids can serve as unknown prototypes. The superiority of our approach is validated across multiple benchmarks. Remarkably, DTDE outperforms the best competitor by 7.6% on the VisDA dataset.

With the proliferation of multi-modal data, safe and efficient multi-modal hashing retrieval has become a pressing research challenge, particularly due to concerns over data privacy during centralized processing. To address this, we propose Prototype-based Federated Multi-modal Hashing (PFMH), an innovative framework that seamlessly integrates federated learning with multi-modal hashing techniques. PFMH achieves fine-grained fusion of heterogeneous multi-modal data, enhancing retrieval accuracy while ensuring data privacy through prototype-based communication, thereby reducing communication costs and mitigating risks of data leakage. Furthermore, using a prototype completion strategy, PFMH tackles class imbalance and statistical heterogeneity in multi-modal data, improving model generalization and performance across diverse data distributions. Extensive experiments demonstrate the efficiency and effectiveness of PFMH within the federated learning framework, enabling distributed training for secure and precise multi-modal retrieval in real-world scenarios.

Generative diffusion model approaches have achieved remarkable success in multimodal recommendation by generating latent user interest interaction graphs. However, current diffusion methods based on Gaussian noise introduce uncertain interest bias noise. This noise not only disrupts the original user-item interaction bipartite graph structure but also undermines the model's ability to accurately capture user interest preferences. To address these challenges, we propose Unbiased Interest Generation for Multimodal Recommendation (GenRec). Our approach aims to generate valid latent user interests while non-invasively preserving the original interest graph structure. We innovatively introduce the Multi-Modal Interest Generaction Module. During the forward process, we simulate user interest state transitions using ''forward flipping.'' In the reverse stage, we generate binary interaction graphs following a Bernoulli distribution. To further mitigate the random uncertainty during the generation process, we design a Multi-Modal Interest Debiase Module. By constructing a multimodal interest clustering space and using user interest hashing, we correct and enhance the generated interest graphs. Finally, the Multi-modal High-Order Graph Learning Optimization is employed to capture high-order interaction information between users and items. A contrastive learning loss function is used for model optimization. We conduct extensive experiments on different real-world open datasets from the industrial sector. Compared with the state-of-the-art DiffMM, our method significantly improves NDCG@20 by 7.3% on the TikTok dataset and boosts Recall@20 by 4.2% on the Sports dataset. The experimental results validate the effectiveness of GenRec. The code is publicly available at https://github.com/orangeheyue/GenRec-V1.

The rich pretrained knowledge in vision-language models (VLMs) endows them with the ability to discriminate common objects given only category names, but may be challenged by out-of-distribution unlabeled samples. To address this limitation, test-time adaptation (TTA) dynamically adjusts VLMs to target distributions during inference. Current TTA frameworks rely heavily on unsupervised data augmentations to enhance sample informativeness, but remain vulnerable to naive augmented views. This work introduces Patch Augmentation (PatAug), a pixel-level perturbation framework that optimizes the benefits of informative augmentations and mitigates negative transformation impacts. Implemented as trainable pixels, PatAug are prepared given only category names before inference, introducing few additional overheads. The patches encode class-related semantic information. They assist VLMs in emphasizing on the compatible visual information in the images, restoring perturbed image details, while retaining unrecognized information. Such merits inspire the design of an augmentation of augmentation framework, where PatAug is applied to standard augmentation views for reliable TTA inference results. To better fit the target distributions, we adjust patches with a cross-modal similarity alignment loss and learnable patching weights. Experiments on natural and specialized domain shifts confirm the effectiveness of PatAug.

Pre-training vision-language representations on human action videos has emerged as a promising approach to reduce reliance on large-scale expert demonstrations for training embodied agents. However, prior methods often employ time con- trastive learning based on goal-reaching heuristics, progressively aligning language instructions from the initial to the final frame. This overemphasis on future frames can result in erroneous vision-language associations, as actions may terminate early or include irrelevant moments in the end. To address this issue, we propose Action Temporal Coherence Learning (AcTOL) to learn ordered and continuous vision-language representations without rigid goal-based constraint. AcTOL treats a video as a continuous trajectory where it (1) contrasts semantic differences be- tween frames to reflect their natural ordering, and (2) imposes a local Brownian bridge constraint to ensure smooth transitions across intermediate frames. Exten- sive imitation learning experiments on both simulated and real robots show that the pretrained features significantly enhance downstream manipulation tasks with high robustness to different linguistic styles of instructions, offering a viable pathway toward generalized embodied agents. Our project page is at https://actol-pretrain.github.io/.

Unsupervised domain adaptation (UDA) enables models trained on a labeled source domain to handle new unlabeled domains. Recently, pre-trained vision-language models (VLMs) have demonstrated promising zero-shot performance by leveraging semantic information to facilitate target tasks. By aligning vision and text embeddings, VLMs have shown notable success in bridging domain gaps. However, inherent differences naturally exist between modalities, which is known as modality gap. Our findings reveal that direct UDA with the presence of modality gap only transfers modality-invariant knowledge, leading to suboptimal target performance. To address this limitation, we propose a unified modality separation framework that accommodates both modality-specific and modality-invariant components. During training, different modality components are disentangled from VLM features then handled separately in a unified manner. At test time, modality-adaptive ensemble weights are automatically determined to maximize the synergy of different components. To evaluate instance-level modality characteristics, we design a modality discrepancy metric to categorize samples into modality-invariant, modality-specific, and uncertain ones. The modality-invariant samples are exploited to facilitate cross-modal alignment, while uncertain ones are annotated to enhance model capabilities. Building upon prompt tuning techniques, our methods achieve up to 9% performance gain with 9 times of computational efficiencies. Extensive experiments and analysis across various backbones, baselines, datasets and adaptation settings demonstrate the efficacy of our design.

With growing concerns about information security, protecting the privacy of user-sensitive data has become crucial. The rapid development of multi-modal retrieval technologies poses new threats, making sensitive data more vulnerable to leakage and malicious mining. To address this, we introduce a Proactive Adversarial Multi-modal Learning (PAML) approach that transforms sensitive data into adversarial counterparts, evading malicious multi-modal retrieval and ensuring privacy. Our method starts by sending queries to a knowledge-agnostic retrieval system and analyzing the results to understand the retrieval feedback mechanism. Using a U-Net-based diffusion model, we create a semantic perturbation network that subtly alters the implicit semantics of sensitive data. This, combined with multi-modal retrieved results and random noise, shifts the data's semantics towards outliers, preventing retrieval as neighbors to relevant queries. Additionally, a discriminator and pre-trained model enhance the visual realism and outlier generalization of protected data. Extensive experiments show that PAML outperforms potential baselines in data privacy protection. Ablation analysis validates each component's effectiveness, and our approach's variants are applicable to diverse retrieval systems.

The accumulation of adversarial perturbations in the feature space makes it impossible for Deep Neural Networks (DNNs) to know what features are robust and reliable, and thus DNNs can be fooled by relying on a single contaminated feature. Numerous defense strategies attempt to improve their robustness by denoising, deactivating, or recalibrating non-robust features. Despite their effectiveness, we still argue that these methods are under-explored in terms of determining how trustworthy the features are. To address this issue, we propose a novel Evidence-based Multi-Feature Fusion (termed EMFF) for adversarial robustness. Specifically, our EMFF approach introduces evidential deep learning to help DNNs quantify the belief mass and uncertainty of the contaminated features. Subsequently, a novel multi-feature evidential fusion mechanism based on Dempster's rule is proposed to fuse the trusted features of multiple blocks within an architecture, which further helps DNNs avoid the induction of a single manipulated feature and thus improve their robustness. Comprehensive experiments confirm that compared with existing defense techniques, our novel EMFF method has obvious advantages and effectiveness in both scenarios of white-box and black-box attacks, and also prove that by integrating into several adversarial training strategies, we can improve the robustness of across distinct architectures, including traditional CNNs and recent vision Transformers with a few extra parameters and almost the same cost.

Video-text cross-modal retrieval is widely studied to improve retrieval accuracy. However, the security of video-text cross-modal retrieval models receives little attention. If attackers exploit the security vulnerabilities in these models, it poses a significant threat to the retrieval models. Thus, identifying security flaws in video-text cross-modal retrieval models becomes the focus of our research. We are the first to design a video poisoning model to uncover security vulnerabilities in retrieval models. Existing poisoning models have certain limitations when it comes to exploiting vulnerabilities in retrieval models. These include failing to comprehensively embed malicious information into the original video and being unable to maintain visual consistency between the original and poisoned videos. These limitations can result in unsuccessful attacks on retrieval models and an inability to effectively identify security flaws within them. To address these shortcomings, we design an efficient poisoning model that embeds malicious information thoroughly into the original clean data to attack video-text cross-modal retrieval models. We are the first to use a poisoning model to attack retrieval models, thereby uncovering their security vulnerabilities. Second, we introduce a bi-level poisoning module to ensure that malicious information is thoroughly embedded into the original video, thereby enhancing the attack capability of the poisoning model. Finally, we design an adversarial module to improve visual consistency between the original and poisoned videos, thus enhancing the concealment of malicious information within the training data of retrieval models. Our poisoning model can identify security flaws in video-text cross-modal retrieval models, providing insights into improving the security of retrieval models. The effectiveness of our model is validated on the MSR-VTT, LSMDC, and MSVD datasets.

Video, as an information carrier, provides a vast amount of important information to people. Therefore, the method of obtaining video becomes particularly important, which drives the research on text-video cross-modal retrieval technology. However, current text-video cross-modal retrieval models still face several issues. First, these models do not fully utilize the powerful reasoning and generative capabilities of large models to address the issues of missing critical objects and insufficient high-quality video-text paired training data. Second, existing retrieval models do not adequately research the bidirectional cross-modal semantic interaction and reasoning mechanism, which hinders the ability to fully capture and learn the implicit semantic features between different modalities. To address these issues, we propose an innovative bidirectional semantic reasoning and large model data augmentation cross-modal retrieval model (BiSeR-LMA). This model first leverages the strong reasoning and generative capabilities of large models to perform semantic reasoning on the textual descriptions of videos, then generates multiple semantically rich video frames, thereby compensating for the missing critical objects in the original video and improving the quality of video-text paired training data. Second, we design a bidirectional text-video semantic reasoning module, which uses features from one modality as auxiliary information to assist the model in reasoning the implicit semantic information of another modality. This enhances the model’s capability to establish semantic relationships and perform reasoning on implicit semantics, promoting text-video semantic alignment. Finally, we verify the effectiveness of the proposed cross-modal retrieval model on the MSR-VTT, LSMDC, and MSVD datasets. The source codes of our method are available at: https://anonymous.4open.science/r/BiSeR_LMA.

Deep cross-modal hashing has demonstrated strong performance in large-scale retrieval but remains challenging in few-shot scenarios due to limited data and weak cross-modal alignment. We propose Generative Augmentation Hashing (GAH), a new framework that synergizes Visual-Language Models (VLMs) and generation-driven hashing to address these limitations. GAH first introduces a cycle generative augmentation mechanism: VLMs generate descriptive textual captions for images, which, combined with label semantics, guide diffusion models to synthesize semantically aligned images via inconsistency filtering. These images then regenerate coherent textual descriptions through VLMs, forming a self-reinforcing cycle that iteratively expands cross-modal data. To resolve the diversity-alignment trade-off in augmentation, we design cross-modal perturbation enhancement, injecting synchronized perturbations with controlled noise to preserve inter-modal semantic relationships while enhancing robustness. Finally, GAH employs dual-level adversarial hash learning, where adversarial alignment of modality-specific and shared latent spaces optimizes both cross-modal consistency and discriminative hash code generation, effectively bridging heterogeneous gaps. Extensive experiments on benchmark datasets show that GAH outperforms state-of-the-art methods in few-shot cross-modal retrieval, achieving significant improvements in retrieval accuracy. Our source codes and datasets are available at https://github.com/xiaolaohuuu/GAH.

In real-world surveillance scenarios, person re-identification tasks are often seriously affected by occlusion problems, which requires the model to be able to not only extract powerful features, but also effectively recover features when they are occluded. Although existing methods disentangle visible human bodies by clustering semantic information, they often damage discriminative appearance due to the introduction of background noises. To solve this problem, we propose Heterogeneous Generative Tokens and Distance-aware Recovery (HGTDR) network, which aims to effectively extract discriminative appearance and recover the occluded body regions. HGTDR mainly contains two branches: a holistic stream and a part stream. The holistic stream utilizes ViT to capture the global context information and provide stable global features by establishing long-range relationships. In the part stream, we propose a Semantic Patch Generator (SPG), which combines the local attention mechanism to capture rich local semantics and further generate semantic patches. Further, considering the discrimination score and relevance score of semantic patches, we feed them into the proposed Adaptive Heterogeneous Semantic Token Generator (AHSTG) to gradually generate strong-response foreground and weak-response background features. In addition, to complete the features of occluded regions, the Distance-based Feature Recovery (DFR) module is designed. The module calculates the planar Euclidean distance of heterogeneous tokens and adaptively allocates the corresponding weights to dynamically recover the invisible bodies. Finally, we obtain discriminative and robust person descriptors. Extensive experiments on several challenging occluded, partial and holistic Re-ID datasets demonstrate that our proposed HGTDR network achieves superior performance and outperforms various state-of-the-art methods.

Correspondence learning aims to identify correct correspondences from the initial correspondence set and estimate camera pose between a pair of images. At present, Transformer-based methods have make notable progress in the correspondence learning task due to their powerful non-local information modeling capabilities. However, these methods seem to neglect local structures during feature aggregation from all query-key pairs, resulting in computational inefficiency and inaccurate correspondence identification. To address this issue, we propose a novel Context-aware Local and Global interaction Transformer (CLGFormer), a lightweight Transformer-based module with dual-branches that address local and global context perception in attention mechanisms. CLGFormer explores the relationship between neighborhood consistency observed in correspondences and context-aware weights appearing in vanilla attention and introduces an attention-style convolution operator. On top of that, CLGFormer also incorporates a cascaded operation that splits full features into multiple subsets and then feeds to the attention heads, which not only reduces computational costs but also enhances attention diversity. At last, we also introduce a feature recombination operate with high jointness and a lightweight channel attention module. The culmination of our efforts is the Context-aware Local and Global interaction Network (CLG-Net), which accurately estimates camera pose and identifies inliers. Through rigorous experiments, we demonstrate that our CLG-Net network outperforms existing state-of-the-art methods while exhibiting robust generalization capabilities across various scenarios. Code will be available athttps://github.com/guobaoxiao/CLG.

Video question answering (VideoQA) is the challenging task of accurately responding to natural language questions based on a given video. Most previous methods focus on designing complex cross-modal interactions to perform question-oriented video scene mining and semantic reasoning, and utilize straightforward classification and matching strategies with different decoders to forcibly associate the predicted representation with ground-truth answer. However, the limitations of question-oriented reasoning and the overlapping semantic co-occurrences between questions and candidates may cause them to fall into spurious correlation reasoning. In this paper, we propose a Collaborative aware Bidirectional Semantic Reasoning (CBSR) model to alleviate this challenging problem. Specifically, we first propose a collaborative aware adaptive correlation reasoning module to collaboratively mine multi-granularity text-aware critical video scenes and reason about the complex intrinsic correlations between them via bottom-up cross-granularity adaptive aggregation. By progressively performing video reasoning from object-level to frame-level, we can obtain a set of semantically rich critical video representations. Then, we collaboratively decode it together with question and knowledge semantics into an implicit representation through the proposed unified answer semantic collaborated decoding module. Finally, a novel bidirectional semantic reasoning learning strategy is proposed to bridge and strengthen the unique positive semantic correlation between the learned implicit representation and the ground-truth answer, and explicitly alleviate the challenge of overlapping semantic co-occurrence. Benefiting from the same model structure and learning strategy, our method can achieve seamless transfer between Open-Ended and Multi-Choice tasks. Extensive experimental results on seven commonly tested datasets (i.e. MSVD-QA, MSRVTT-QA, NExT-QA, Causal-VidQA, NExT-OOD, ActivityNet-QA and EgoSchema) verify the superior performance of our method and the effectiveness of each reasoning module. We provide our source codes and experimental datasets athttps://github.com/XizeWu/CBSR.

Unsupervised domain adaptation (UDA) aims to adapt models learned from a well-annotated source domain to a target domain, where only unlabeled samples are available. To this end, adversarial training is widely used in conventional UDA methods to reduce the discrepancy between source and target domains. Recently, prompt tuning has emerged as an efficient way to adapt large pre-trained vision-language models like CLIP to a variety of downstream tasks. In this paper, we present a novel method named Adversarial DuAl Prompt Tuning (ADAPT) for UDA, which employs text prompts and visual prompts to guide CLIP simultaneously. Rather than simply performing a joint optimization of text prompts and visual prompts, we integrate text prompt tuning and visual prompt tuning into a collaborative framework where they engage in an adversarial game: text prompt tuning focuses on distinguishing between source and target images, whereas visual prompt tuning seeks to align source and target domains. Unlike most existing adversarial training-based UDA approaches, ADAPT does not require explicit domain discriminators for domain alignment. Instead, the objective is effectively achieved at both global and category levels through modeling the joint probability distribution of images on domains and categories. Extensive experiments on four benchmark datasets demonstrate the effectiveness of our ADAPT method for UDA. We have released our code at https://github.com/Liuziyi1999/ADAPT.

Cross-Modal Hashing (CMH) has become a powerful technique for large-scale cross-modal retrieval, offering benefits like fast computation and efficient storage. However, most CMH models struggle to adapt to streaming multimodal data in real-time once deployed. Although recent online CMH studies have made progress in this area, they often overlook two key challenges: 1) learning effectively from streaming partial-modal multimodal data, and 2) avoiding the high costs associated with frequent hash function re-training and large-scale updates to database hash codes. To address these issues, we propose Fast Partial-modal Online Cross-Modal Hashing (FPO-CMH), the first approach to tackle online cross-modal hash learning with partial-modal data. This marks a significant shift from previous methods that rely on fully-available multimodal data. Specifically, our approach introduces a multimodal dual-tier anchor bank, initialized using offline training data, which allows offline-trained CMH models to adapt seamlessly to partial-modal data while progressively updating the anchor bank. By leveraging gradient accumulation and asynchronous optimization, FPO-CMH facilitates efficient online cross-modal hash learning. Additionally, an initial-anchor rehearsal strategy is employed to prevent model catastrophic forgetting during online optimization, ensuring the code invariance of database hash codes and eliminating the need for frequent hash function re-training. Extensive experiments validate the superiority of FPO-CMH, especially in handling streaming partial-modal multimodal data, a more realistic scenario. The source codes and datasets are available at https://github.com/DandelionWow/FPO-CMH.

Despite recent advances, scene text recognition remains a challenging problem due to the significant variability, irregularity and distortion in text appearance and localization. Attention-based methods have become the mainstream due to their superior vocabulary learning and observation ability. Nonetheless, they are susceptible to attention drift which can lead to word recognition errors. Most works focus on correcting attention drift in decoding but completely ignore the error accumulated during the encoding process. In this paper, we propose a novel scheme, called the Attention Guidance by Cross-Domain Supervision Signals for Scene Text Recognition (ACDS-STR), which can mitigate the attention drift at the feature encoding stage. At the heart of the proposed scheme is the cross-domain attention guidance and feature encoding fusion module (CAFM) that uses the core areas of characters to recursively guide attention to learn in the encoding process. With precise attention information sourced from CAFM, we propose a non-attention-based adaptive transformation decoder (ATD) to guarantee decoding performance and improve decoding speed. In the training stage, we fuse manual guidance and subjective learning to learn the core areas of characters, which notably augments the recognition performance of the model. Experiments are conducted on public benchmarks and show the state-of-the-art performance. The source will be available at https://github.com/xuefanfu/ACDS-STR.

Cross-domain Recommendation (CR) has been extensively studied in recent years to alleviate the data sparsity issue in recommender systems by utilizing different domain information. In this work, we focus on the more general Non-overlapping Cross-domain Sequential Recommendation (NCSR) scenario. Non-overlapping Cross-domain Sequential Recommendation (NCSR) is challenging because there are no overlapped entities (e.g., users and items) between domains, and there is only users’ implicit feedback and no content information. Previous Cross-domain Recommendation (CR) methods cannot solve NCSR well, since (1) they either need extra content to align domains or need explicit domain alignment constraints to reduce the domain discrepancy from domain-invariant features, (2) they pay more attention to users’ explicit feedback (i.e., users’ rating data) and cannot well capture their sequential interaction patterns, (3) they usually do a single-target cross-domain recommendation task and seldom investigate the dual-target ones. Considering the above challenges, we propose Prompt Learning-based Cross-domain Recommender (PLCR), an automated prompting-based recommendation framework for the NCSR task. Specifically, to address the challenge (1), Prompt Learning-based Cross-domain Recommender (PLCR) resorts to learning domain-invariant and domain-specific representations via its prompt learning component, where the domain alignment constraint is discarded. For challenges (2) and (3), PLCR introduces a pre-trained sequence encoder to learn users’ sequential interaction patterns, and conducts a dual-learning target with a separation constraint to enhance recommendations in both domains. Our empirical study on two sub-collections of Amazon demonstrates the advance of PLCR compared with some related SOTA methods.

Conventional domain adaptation (DA) for person re-identification (ReID) aims to bridge the domain gap but often requires direct use of fully labeled source and target domains, raising significant data privacy concerns due to the inclusion of personal identity information (PII) in raw data. Source-free domain adaptation (SFDA) for person ReID effectively preserves PII within the authorized source model. Nevertheless, these methods are vulnerable to data privacy (e.g., portrait rights) of the target domain during retrieval, where attackers can exploit pedestrian images for malicious generation, leading to damage to an individual’s reputation. Beyond these limitations, we propose a novel framework called SecureDA to address privacy-preserving SFDA for person ReID, which can generate a privacy key to defend against potential attacks on PII. Technically, we introduce domain-specific adversarial attacks into DA, where the protected query and gallery images are encrypted to ensure secure image retrieval. Furthermore, we employ two simultaneous processes: 1) The global–local adversarial pathway (GLAP) leverages encrypted and original images as adversarial pairs, thereby fostering the development of robust ReID models; 2) The global–local collaborative pathway (GLCP) is mastered through positive pairs collected from the same domain, effectively mitigating the pernicious catastrophic forgetting phenomenon. Extensive experiments show that SecureDA achieves state-of-the-art performance on multiple DA benchmarks and even outperforms the conventional DA and SFDA methods, which inherently compromise data privacy.

Unsupervised Cross-Modal Hashing (UCMH) models the intrinsic semantic correlations across different modalities to generate binary hash codes, facilitating efficient cross-modal retrieval. This technology offers notable advantages, such as independence from labeled data and superior generalization capabilities compared to supervised methods. However, most UCMH methods are designed for closed-set retrieval scenarios and have difficulty generalizing to open multi-modal data, which is common in real-world retrieval settings. This limitation hampers their performance in open retrieval tasks, particularly when these tasks involve novel categories. To address the above issue, we propose an Open-set Cross-Modal Hashing (OCMH) method, which enhances the generalization capability of trained UCMH models in an efficient plug-in manner for open cross-modal retrieval. Our method enables the model to learn from novel categories in open-set scenarios by increasing the pre-defined hash code length, while simultaneously preventing the catastrophic forgetting of trained knowledge from the closed-set domain using basic hash codes. Additionally, we introduce a historical-category detection module and an asymmetric optimization strategy to support the joint learning of basic and increased hash codes by replaying detected samples related to historical categories. By plugging our proposed method into several representative UCMH methods on three widely used datasets, experimental results show that the enhanced UCMH methods achieve superior retrieval performance in both open-set and closed-set scenarios. The source code is available at:https://github.com/WangBowen7/OCMH/.

Multi-modal hashing achieves low storage costs and high retrieval speeds by using compact hash codes to represent complex and heterogeneous multi-modal data, effectively addressing the inefficiency and resource intensiveness challenges faced by the traditional multi-modal retrieval methods. However, balancing intraclass compactness and interclass separability remains a struggle in existing works due to coarse-grained feature limitations, simplified fusion strategies that overlook semantic complementarity, and neglect of the structural information within the multi-modal data. To address these limitations comprehensively, we propose a Proto-centric Multi-modal Hashing with Pronounced Category Differences (PMH-PCD) model. Specifically, PMH-PCD first learns modality-specific prototypes by deeply exploring within-modality class information, ensuring effective fusion of each modality's unique characteristics. Furthermore, it learns multi-modal integrated class prototypes that seamlessly incorporate semantic information across modalities to effectively capture and represent the intricate relationships and complementary semantic content embedded within the multi-modal data. Additionally, to generate more discriminative and representative binary hash codes, PMH-PCD integrates multifaceted semantic information, encompassing both low-level pairwise relations and high-level structural patterns, holistically capturing intricate data details and leveraging underlying structures. The experimental results demonstrate that, compared with existing advanced methods, PMH-PCD achieves superior and consistent performances in multi-modal retrieval tasks. To promote further research and reproducibility, we have publicly released the source code of PMH-PCD at https://github.com/vindahi/PMH-PCD.

Non-overlapping Cross-domain Sequential Recommendation (NCSR) is the task that focuses on domain knowledge transfer without overlapping entities. Compared with traditional Cross-domain Sequential Recommendation (CSR), NCSR poses several challenges: (1) NCSR methods often rely on explicit item IDs, overlooking semantic information among entities. (2) Existing CSR mainly relies on domain alignment for knowledge transfer, risking semantic loss during alignment. (3) Most previous studies do not consider the many-to-one characteristic, which is challenging because of the utilization of multiple source domains. Given the above challenges, we introduce the prompt learning technique for Many-to-one Non-overlapping Cross-domain Sequential Recommendation (MNCSR) and propose a Text-enhanced Co-attention Prompt Learning Paradigm (TCPLP). Specifically, we capture semantic meanings by representing items through text rather than IDs, leveraging natural language universality to facilitate cross-domain knowledge transfer. Unlike prior works that need to conduct domain alignment, we directly learn transferable domain information, where two types of prompts, i.e., domain-shared and domain-specific prompts, are devised, with a co-attention-based network for prompt encoding. Then, we develop a two-stage learning strategy, i.e., pre-train and prompt-tuning paradigm, for domain knowledge pre-learning and transferring, respectively. We conduct extensive experiments on three datasets and the experimental results demonstrate the superiority of our TCPLP. Our source codes have been publicly released ( https://github.com/songchenlong/TCPLP ).

Providing sequential recommendations along with easily comprehensible natural language explanations can significantly enhance users’ trust in the recommender systems. However, this approach presents two key challenges: (1) The different objectives of the two tasks make it challenging to achieve joint optimization and mutual enhancement. (2) The simultaneous generation of accurate sequential recommendations and high-quality natural language explanations presents serious challenges to the model’s time and space efficiency. To address these challenges, we propose a general and efficient multi-task self-prompt framework for explainable sequential recommendation (ARTS), which improves collaboration performance and time and space efficiency of multi-task modules based on the generated personalized semantic prompts. Specifically, we propose a self-prompt generator that transfers the user’s global behavior features into the continuous prompt, achieving efficient information sharing among multi-task modules. Additionally, we design a personalized prompt-based short sequence inputs strategy under the pre-training and prompt-tuning paradigm, which achieves mutual enhancement among the multi-task modules and significantly improves the model’s time and space efficiency. Extensive experiments have verified that the proposed ARTS outperforms the state-of-the-art methods in both sequential recommendation and explanation generation tasks. The generality, efficiency and effectiveness of each module of the framework have also been validated through various experiments 1 .

In the evolving landscape of recommender systems, the challenge of effectively conducting privacy-preserving Cross-domain Recommendation, especially under strict non-overlapping constraints, has emerged as a key focus. Despite extensive research has made significant progress, several limitations still exist: (1) Previous semantic-based methods fail to deeply exploit rich textual information, since they quantize the text into codes, losing its original rich semantics. (2) The current solution solely relies on the text-modality, while the synergistic effects with the ID-modality are ignored. (3) Existing studies do not consider the impact of irrelevant semantic features, leading to inaccurate semantic representation. To address these challenges, we introduce federated semantic learning and devise FFMSR as our solution. For Limitation 1, we locally learn items’ semantic encodings from their original texts by a multi-layer semantic encoder and then cluster them on the server to facilitate the transfer of semantic knowledge between domains. To tackle Limitation 2, we integrate both ID and Text modalities on the clients, and utilize them to learn different aspects of items. To handle Limitation 3, a Fast Fourier Transform-based filter and a gating mechanism are developed to alleviate the impact of irrelevant semantic information in the local model. We conduct extensive experiments on two real-world datasets, and the results demonstrate the superiority of our FFMSR method over other SOTA methods. Our source codes are publicly available at https://github.com/Sapphire-star/FFMSR .

The expressiveness of historical reviews in capturing user preferences has garnered significant attention in recommender systems. However, this technology still has certain limitations. Firstly, irrelevant reviews can introduce noise that may adversely affect the performance of the model. Secondly, existing approaches often assume a flat structure for review features, thus failing to capture the intricate and hierarchical nature of user–item interactions. Thirdly, it is challenging for review-based recommendation models to effectively assess the usefulness of reviews due to sparse supervision signals. To address these challenges, we propose a novel Hierarchical Gating and Discriminative model for rating prediction. Specifically, we introduce a local gating module that utilizes personalized end-to-end differential thresholds to select reviews in a relatively “hard” manner, thereby minimizing the impact of noisy reviews while facilitating model training. Additionally, we incorporate a global gating module to assess the overall usefulness of review signals by estimating the uncertainties inherent in historical reviews. Moreover, we propose a hierarchical discriminative network to develop self-supervision signals at both global and local levels to guide the learning of the hierarchical gating network. Extensive experiments on public datasets have demonstrated the effectiveness of the proposed model, and further investigations provide deep insight into its superiority.

Unsupervised domain adaptive hashing is a highly promising research direction within the field of retrieval. It aims to transfer valuable insights from the source domain to the target domain while maintaining high storage and retrieval efficiency. Despite its potential, this field remains relatively unexplored. Previous methods usually lead to unsatisfactory retrieval performance, as they frequently directly apply slightly modified domain adaptation algorithms to hash learning framework, or pursue domain alignment within the Hamming space characterized by limited semantic information. In this paper, we propose a simple yet effective approach named Comparative Prototype Hashing (CPH) for unsupervised domain adaptive image retrieval. We establish a domain-shared unit hypersphere space through prototype contrastive learning and then obtain the Hamming hypersphere space via mapping from the shared hypersphere. This strategy achieves a cohesive synergy between learning uniformly distributed and category conflict-averse feature representations, eliminating domain discrepancies, and facilitating hash code learning. Moreover, by leveraging dual-domain information to supervise the entire hashing model training process, we can generate hash codes that retain inter-sample similarity relationships within both domains. Experimental results validate that our CPH significantly outperforms the state-of-the-art counterparts across multiple cross-domain and single-domain retrieval tasks. Notably, on Office-Home and Office-31 datasets, CPH achieves an average performance improvement of 19.29% and 13.85% on cross-domain retrieval tasks compared to the second-best results, respectively. The source codes of our method are available at: https://github.com/christinecui/CPH.

Efficiently utilizing rich knowledge in pretrained models has become a critical topic in the era of large models. This work focuses on adaptively utilize knowledge from multiple source-pretrained models to an unlabeled target domain without accessing the source data. Despite being a practically useful setting, existing methods require extensive parameter tuning over each source model, which is computationally expensive when facing abundant source domains or larger source models. To address this challenge, we propose a novel approach which is free of the parameter tuning over source backbones. Our technical contribution lies in the Bi-level ATtention ENsemble (Bi-ATEN) module, which learns both intra-domain weights and inter-domain ensemble weights to achieve a fine balance between instance specificity and domain consistency. By slightly tuning source bottlenecks, we achieve comparable or even superior performance on a challenging benchmark DomainNet with less than 3% trained parameters and 8 times of throughput compared with SOTA method. Furthermore, with minor modifications, the proposed module can be easily equipped to existing methods and gain more than 4% performance boost. Code is available at https://github.com/TL-UESTC/Bi-ATEN.

Conventional Unsupervised Domain Adaptation (UDA) strives to minimize distribution discrepancy between do-mains, which neglects to harness rich semantics from data and struggles to handle complex domain shifts. A promising technique is to leverage the knowledge of large-scale pretrained vision-language models for more guided adaptation. Despite some endeavors, current methods often learn textual prompts to embed domain semantics for source and target domains separately and perform classification within each domain, limiting cross-domain knowledge transfer. Moreover, prompting only the language branch lacks flex-ibility to adapt both modalities dynamically. To bridge this gap, we propose Domain-Agnostic Mutual Prompting (DAMP) to exploit domain-invariant semantics by mutually aligning visual and textual embeddings. Specifically, the image contextual information is utilized to prompt the language branch in a domain-agnostic and instance-conditioned way. Meanwhile, visual prompts are im-posed based on the domain-agnostic textual prompt to elicit domain-invariant visual embeddings. These two branches of prompts are learned mutually with a cross-attention module and regularized with a semantic-consistency loss and an instance-discrimination contrastive loss. Experiments on three UDA benchmarks demonstrate the superiority of DAMP over state-of-the-art approaches1.

An intuitive strategy for generating more transferable adversarial examples is to absorb the advantages of different surrogates in an ensemble. However, existing ensemble adversarial attacks simply average the outputs of various models while ignoring their different contributions. To quantify the importance of various surrogates, we propose a novel Shapley Ensemble Adversarial Attack (dubbed SEAA) – an effective algorithm that allocates weights based on Shapley values of the surrogates. Specifically, the synthesis of adversarial examples in an ensemble adversarial attack is firstly regarded as a cooperative game process of multiple surrogates from the perspective of contribution. As the Shapley value is known as an effective decision metric in cooperative game theory, it is thus intuitively introduced into this work to accurately evaluate the contribution of a surrogate by reweighing its importance at each iteration, thus avoiding local optimality and steering the generation of adversarial examples. Comprehensive experimental results demonstrate our effectiveness.

The limited data availability and the low signal-to-noise ratio of fMRI signals lead to the challenging task of fMRI-to-image retrieval. State-of-the-art MindEye remarkably improves fMRI-to-image retrieval performance by leveraging a large model, i.e., a 996M MLP Backbone per subject, to align fMRI embeddings to the final hidden layer of CLIP's Vision Transformer (ViT). However, significant individual variations exist among subjects, even under identical experimental setups, mandating the training of large subject-specific models. The substantial parameters pose significant challenges in deploying fMRI decoding on practical devices. To this end, we propose Lite-Mind, a lightweight, efficient, and robust brain representation learning paradigm based on Discrete Fourier Transform (DFT), which efficiently aligns fMRI voxels to fine-grained information of CLIP. We elaborately design a DFT backbone with Spectrum Compression and Frequency Projector modules to learn informative and robust voxel embeddings. Our experiments demonstrate that Lite-Mind achieves an impressive 94.6% fMRI-to-image retrieval accuracy on the NSD dataset for Subject 1, with 98.7% fewer parameters than MindEye. Lite-Mind is also proven to be able to be migrated to smaller fMRI datasets and establishes a new state-of-the-art for zero-shot classification on the GOD dataset.

Mainstream multimodal recommender systems are designed to learn user interest by analyzing user-item interaction graphs. However, what they learn about user interest needs to be completed because historical interactions only record items that best match user interest (i.e., the first-order interest), while suboptimal items are absent. To fully exploit user interest, we propose a Second-Order Interest Learning (SOIL) framework to retrieve second-order interest from unrecorded suboptimal items. In this framework, we build a user-item interaction graph augmented by second-order interest, an interest-aware item-item graph for the visual modality, and a similar graph for the textual modality. In our work, all three graphs are constructed from user-item interaction records and multimodal feature similarity. Similarly to other graph-based approaches, we apply graph convolutional networks to each of the three graphs to learn representations of users and items. To improve the exploitation of both first-order and second-order interest, we optimize the model by implementing contrastive learning modules for user and item representations at both the user-item and item-item levels. The proposed framework is evaluated on three real-world public datasets in online shopping scenarios. Experimental results verify that our method is able to significantly improve prediction performance. For instance, our method outperforms the previous state-of-the-art method MGCN by an average of 8.1% in terms of Recall@10. Code: https://github.com/TL-UESTC/SOIL.

In online advertising, the sample selection bias problem is a major cause of inaccurate conversion rate estimates. Current mainstream solutions only perform causality-based optimization in the click space since the conversion labels in the non-click space are absent. However, optimization for unclicked samples is equally essential because the non-click space contains more samples and user characteristics than the click space. To exploit the unclicked samples, we propose a Direct Dual Propensity Optimization (DDPO) framework to optimize the model directly in impression space with both clicked and unclicked samples. In this framework, we specifically design a click propensity network and a conversion propensity network. The click propensity network is dedicated to ensuring that optimization in the click space is unbiased. The conversion propensity network is designed to generate pseudo-conversion labels for unclicked samples, thus overcoming the challenge of absent labels in non-click space. With these two propensity networks, we are able to perform causality-based optimization in both click space and non-click space. In addition, to strengthen the causal relationship, we design two causal transfer modules for the conversion rate prediction model with the attention mechanism. The proposed framework is evaluated on five real-world public datasets and one private Tencent advertising dataset. Experimental results verify that our method is able to improve the prediction performance significantly. For instance, our method outperforms the previous state-of-the-art method by 7.0% in terms of the Area Under the Curve on the Ali-CCP dataset.

The Point-of-Interest (POI) recommendation system, designed to recommend potential future visits of users based on their check-in sequences, faces the challenge of data scarcity. This challenge primarily stems from the data sparsity issue, namely users interact with only a small number of POIs. Most existing studies attempt to solve this problem by focusing on POI check-in sequences, without considering the substantial multi-modal content information (e.g. textual and image data) commonly associated with POIs. In this paper, we propose a novel multi-modal content-aware framework for POI recommendation (MMPOI). Our approach addresses the issue of data sparsity by incorporating multi-modal content information about POIs from a new perspective. Specifically, MMPOI leverages pre-trained models for inter-modal conversion and employs a unified pre-trained model to extract modal-specific features from each modality, effectively bridging the semantic gap between different modalities. We propose to build a Multi-Modal Trajectory Flow Graph (MTFG) which combines the multi-modal semantic structure with check-in sequences. Moreover, we design an adaptive multi-task Transformer that models users' multi-modal movement patterns and integrates them for the next POI recommendation tasks. Extensive experiments on four real-world datasets demonstrate that MMPOI outperforms state-of-the-art POI recommendation methods. To facilitate reproducibility, we have released both the code and the multi-modal POI recommendation datasets we collect https://github.com/zzmylq/MMPOI

Recent studies tend to employ Contrastive Learning (CL) methods to facilitate model training by extracting self-supervised signals to mitigate data sparsity . However, existing CL-based recommendation methods have not fully exploited the rich semantic information present in multi-modal data. To address these limitations, we propose a new CL-based recommendation framework named Multi-level Cross-modal Contrastive Learning (MCCL), which aims to construct multi-level contrastive learning to fully exploit the intra- and inter-modal semantic information in a self-supervised manner. Specifically, we innovatively consider user interaction and semantic review as two distinct semantic modalities, and devise two modal-specific contrastive learning strategies to enhance intra-modal learning. Furthermore, we leverage the semantic consistency between modalities to construct a multi-level cross-modal contrastive learning framework. Finally, a multi-task learning method is employed for collaborative optimization across multiple tasks. We verify the efficacy of MCCL via comprehensive experiments on three real-world datasets. MCCL achieves a significant performance improvement over the state-of-the-art baseline models .

Cloth-changing person reidentification (ReID) is a newly emerging research topic aimed at addressing the issues of large feature variations due to cloth-changing and pedestrian view/pose changes. Although significant progress has been achieved by introducing extra information (e.g., human contour sketching information, human body keypoints, and 3D human information), cloth-changing person ReID remains challenging because pedestrian appearance representations can change at any time. Moreover, human semantic information and pedestrian identity information are not fully explored. To solve these issues, we propose a novel identity-guided collaborative learning scheme (IGCL) for cloth-changing person ReID, where the human semantic is effectively utilized and the identity is unchangeable to guide collaborative learning. First, we design a novel clothing attention degradation stream to reasonably reduce the interference caused by clothing information where clothing attention and mid-level collaborative learning are employed. Second, we propose a human semantic attention and body jigsaw stream to highlight the human semantic information and simulate different poses of the same identity. In this way, the extraction features not only focus on human semantic information that is unrelated to the background but are also suitable for pedestrian pose variations. Moreover, a pedestrian identity enhancement stream is proposed to enhance the identity importance and extract more favorable identity robust features. Most importantly, all these streams are jointly explored in an end-to-end unified framework, and the identity is utilized to guide the optimization. Extensive experiments on six public clothing person ReID datasets (LaST, LTCC, PRCC, NKUP, Celeb-reID-light, and VC-Clothes) demonstrate the superiority of the IGCL method. It outperforms existing methods on multiple datasets, and the extracted features have stronger representation and discrimination ability and are weakly correlated with clothing.

Over the past decade, domain adaptation has become a widely studied branch of transfer learning which aims to improve performance on target domains by leveraging knowledge from the source domain. Conventional domain adaptation methods often assume access to both source and target domain data simultaneously, which may not be feasible in real-world scenarios due to privacy and confidentiality concerns. As a result, the research of Source-Free Domain Adaptation (SFDA) has drawn growing attention in recent years, which only utilizes the source-trained model and unlabeled target data to adapt to the target domain. Despite the rapid explosion of SFDA work, there has been no timely and comprehensive survey in the field. To fill this gap, we provide a comprehensive survey of recent advances in SFDA and organize them into a unified categorization scheme based on the framework of transfer learning. Instead of presenting each approach independently, we modularize several components of each method to more clearly illustrate their relationships and mechanisms in light of the composite properties of each method. Furthermore, we compare the results of more than 30 representative SFDA methods on three popular classification benchmarks, namely Office-31, Office-home, and VisDA, to explore the effectiveness of various technical routes and the combination effects among them. Additionally, we briefly introduce the applications of SFDA and related fields. Drawing on our analysis of the challenges confronting SFDA, we offer some insights into future research directions and potential settings.

With the exponential surge in diverse multimodal data, traditional unimodal retrieval methods struggle to meet the needs of users seeking access to data across various modalities. To address this, cross-modal retrieval has emerged, enabling interaction across modalities, facilitating semantic matching, and leveraging complementarity and consistency between heterogeneous data. Although prior literature has reviewed the field of cross-modal retrieval, it suffers from numerous deficiencies in terms of timeliness, taxonomy, and comprehensiveness. This article conducts a comprehensive review of cross-modal retrieval’s evolution, spanning from shallow statistical analysis techniques to vision-language pretraining (VLP) models. Commencing with a comprehensive taxonomy grounded in machine learning paradigms, mechanisms, and models, this article delves deeply into the principles and architectures underpinning existing cross-modal retrieval methods. Furthermore, it offers an overview of widely used benchmarks, metrics, and performances. Lastly, this article probes the prospects and challenges that confront contemporary cross-modal retrieval, while engaging in a discourse on potential directions for further progress in the field. To facilitate the ongoing research on cross-modal retrieval, we develop a user-friendly toolbox and an open-source repository athttps://cross-modal-retrieval.github.io.

Unsupervised hashing has the desirable advantages of label independence, high storage, and retrieval efficiency, which is suitable for scalable image retrieval. Most existing methods focus on enhancing the image hashing model training process at the offline stage. However, little attention has been paid to the query content analysis by them at the online retrieval stage. They still suffer from important query semantic shortages, and thus limit the online retrieval performance, which is the ultimate objective of the image retrieval system. In this paper, we propose an Online Query Expansion Hashing (OQEH) for efficient image retrieval, by adaptively enhancing the discriminative capability of query hash codes in an expansion manner at the online retrieval stage. Specifically, we first design a self-expansion network to learn semantically invariant feature representations from images and their visual augmentations. Then, we conduct neighborhood-expansion to search similar samples for each image from a query expansion set with the semantically invariant features and design a Transformer architecture to adaptively transfer the semantics of neighbor samples to their corresponding images. With the support of semantically invariant features, query expansion set, and adaptive semantic transfer, the representation capability of query hash codes can be enhanced at the online retrieval stage. Experimental results demonstrate that the proposed OQEH method achieves superior retrieval accuracy and comparable retrieval efficiency compared with the state-of-the-art methods. Particularly, on MS COCO dataset, OQEH can obtain about 6% performance improvement compared with the state-of-the-art results. The source codes of our method are available at:https://github.com/christinecui/OQEH.

Unsupervised domain adaptation aims to transfer the knowledge learned from a labeled source domain to an unlabeled target domain with different data distributions. However, in practice, source samples are not always available due to privacy protection and storage resource limitations. To address this concern, Source-Free Domain Adaptation (SFDA) has recently attracted growing research attention, as it only needs a pre-trained source model without direct access to source data. In this paper, we propose a novel Adversarial SOurce GEneration (ASOGE) method for SFDA, which introduces an additional generative module to produce synthetic labeled source samples and uses them to facilitate cross-domain adaptation. Unlike early studies that train the generator independently and perform the adaptation only after the generator is finished, ASOGE integrates the generation and adaptation stages within a collaborative framework by making them play an adversarial game. In the generation stage, the labeled source samples are not produced blindly; instead, they are hard-to-align samples that provide knowledge more worth learning for the adaptation stage. To achieve a fine-grained domain alignment, a class-aware discrepancy between source and target domains is measured via contrastive learning. Extensive experiments on benchmark datasets demonstrate the effectiveness of ASOGE compared to the state-of-the-art methods.

The objective of the occluded person re-identification (ReID) task is to capture the same person from different camera angles when the pedestrian’s body is partially occluded. In this task, there are two main challenges: 1) pedestrians are often occluded by other persons or objects, and 2) pedestrians change poses. Moreover, these two issues often simultaneously occur. Although many occluded person ReID algorithms have been proposed, many existing methods can often only solve one of these issues well, and the other issue is often ignored. In this work, a novel semantic perception and CNN-transformer hybrid network (abbreviated as SPH) is proposed for occluded person ReID, which consists of a CNN-based human semantic perception stream and a transformer-based pose perception stream. In the former, a human semantic auxiliary module and a human semantic perception module are designed to obtain human semantic information where multi-granularity region features of the human body are extracted to solve the issues of occlusion. In the latter, we propose a token-based pose integration module to obtain the corresponding patch for each pose key-point and the relative position information to solve the change in pedestrian pose. Moreover, these two streams are jointly optimized in a unified framework. In addition, to further solve the issue of occlusion, the human completion strategy is proposed for the query sample where the gallery samples are used to complete the missing parts of the query. Extensive experimental results on three public occluded person ReID datasets, Occluded-DukeMTMC, P-DukeMTMC-reID, and Occluded-REID, demonstrate that the proposed method can outperform all SOTA occluded person ReID methods in terms of the mAP and Rank-1. Compared with PAT (CVPR21) on the Occluded-DukeMTMC and Occluded-REID datasets, the improvements in mAP/Rank-1 reached 10.1%/7.4%, and 10%/1%, respectively. Moreover, when TransReID (ICCV21) was used, SPH achieved improvements of 4.5% (mAP) and 5.5% (Rank-1) on the Occluded-DukeMTMC dataset.

To meet users’ demands for video retrieval, text-video cross-modal retrieval technology continues to evolve. Methods based on pre-trained models and transfer learning are widely employed in designing cross-modal retrieval models, significantly enhancing the accuracy of video retrieval. However, these methods exhibit shortcomings when it comes to studying the relationships between video frames, preventing the model from fully establishing the hidden semantic relationships within video features. To further deduce the implicit semantic relationships among video frames, we propose a cross-modal retrieval model based on graph convolutional networks (GCN) and visual semantic inference (GVSI). The GCN is utilized to establish relationships between video frame features, facilitating the mining of hidden semantic information across video frames. In order to use text semantic features to help the model to infer temporal and implicit semantic information between video frames, we introduce a semantic mining and temporal space (SM&TS) inference module. Additionally, we design semantic alignment modules (SA_M) to align explicit and implicit object features present in both video and text. Finally, we analyze and validate the effectiveness of the model using MSR-VTT, MSVD, and LSMDC datasets.

Unsupervised cross-modal hashing presents significant advantages in heterogeneous modality retrieval, offering label scalability, high retrieval efficiency, and low storage costs. However, the lack of explicit semantic supervision in this process results in a noticeable semantic deficit, impacting retrieval performance. In this paper, we address this challenge with a dual-pronged approach: Cross-Domain Transfer Hashing (CDTH), a lightweight weakly-supervised cross-modal hashing model. Our method leverages a semantically rich auxiliary domain to augment the target unsupervised cross-modal hash learning process. Simultaneously, we design a lightweight target cross-modal hashing network to reduce semantic requirements, lessening the burden of parameter optimization. Within the auxiliary domain, we perform direct semantic transfer with hashing network parameter transfer and indirect correlation semantic transfer by constructing an auxiliary semantic correlation graph with the identified cross-domain semantic consistent samples. In the target domain, we generate pseudo-labels using CLIP and establish a target weak semantic correlation graph. These two graphs collaborate to bolster the target cross-modal hashing training process. Extensive experiments on three publicly available datasets affirm the superiority of our approach in both retrieval accuracy and training efficiency. The source code for our method is accessible at: https://github.com/WangBowen7/CDTH.

Learning with noisy labels has become more and more popular because of the expensive costs of collecting high-quality labels. To avoid the decrease in model performance caused by incorrect annotations, some existing methods try to select reliable samples based on the local structure of nearest neighbors in the feature space. However, the information from local neighbors is unreliable when encountering extremely noisy cases, and selecting samples only using the feature space may result in clear noise accumulation. To this end, we propose a Dual-Space Collaborative Learning (DSCL) framework to boost classification accuracy by jointly using the complementarity information from both semantic and feature spaces. Specifically, a collaborative selection module is designed by constructing a set of global prototypes and high-confidence semantic predictions, which enhances the robustness of the sample selection process. Moreover, a collaborative regularization module is constructed by the bidirectional adjustment between the semantic and feature spaces, which effectively alleviates the noise accumulation issue caused by sample selection bias in a single space. By simultaneously utilizing the two modules, our method improves the accuracy of sample selection and mitigates the degradation caused by noisy labels. Extensive experimental results indicate the superior performance of DSCL compared with various baselines.

The majority of existing works explore Unsupervised Domain Adaptation (UDA) with an ideal assumption that samples in both domains are available and complete. In real-world applications, however, this assumption does not always hold. For instance, data-privacy is becoming a growing concern, the source domain samples may be not publicly available for training, leading to a typical Source-Free Domain Adaptation (SFDA) problem. Traditional UDA methods would fail to handle SFDA since there are two challenges in the way: the data incompleteness issue and the domain gaps issue. In this paper, we propose a visually SFDA method named Adversarial Style Matching (ASM) to address both issues. Specifically, we first train a style generator to generate source-style samples given the target images to solve the data incompleteness issue. We use the auxiliary information stored in the pre-trained source model to ensure that the generated samples are statistically aligned with the source samples, and use the pseudo labels to keep semantic consistency. Then, we feed the target domain samples and the corresponding source-style samples into a feature generator network to reduce the domain gaps with a self-supervised loss. An adversarial scheme is employed to further expand the distributional coverage of the generated source-style samples. The experimental results verify that our method can achieve comparative performance even compared with the traditional UDA methods with source samples for training.

Despite remarkable successes in unimodal learning tasks, backdoor attacks against cross-modal learning are still underexplored due to the limited generalization and inferior stealthiness when involving multiple modalities. Notably, since works in this area mainly inherit ideas from unimodal visual attacks, they struggle with dealing with diverse cross-modal attack circumstances and manipulating imperceptible trigger samples, which hinders their practicability in real-world applications. In this paper, we introduce a novel bilateral backdoor to fill in the missing pieces of the puzzle in the cross-modal backdoor and propose a generalized invisible backdoor framework against cross-modal learning (BadCM). Specifically, a cross-modal mining scheme is developed to capture the modality-invariant components as target poisoning areas, where well-designed trigger patterns injected into these regions can be efficiently recognized by the victim models. This strategy is adapted to different image-text cross-modal models, making our framework available to various attack scenarios. Furthermore, for generating poisoned samples of high stealthiness, we conceive modality-specific generators for visual and linguistic modalities that facilitate hiding explicit trigger patterns in modality-invariant regions. To the best of our knowledge, BadCM is the first invisible backdoor method deliberately designed for diverse cross-modal attacks within one unified framework. Comprehensive experimental evaluations on two typical applications, i.e., cross-modal retrieval and VQA, demonstrate the effectiveness and generalization of our method under multiple kinds of attack scenarios. Moreover, we show that BadCM can robustly evade existing backdoor defenses. Our code is available at https://github.com/xandery-geek/BadCM.

Hashing-based recommender systems that represent users and items as binary hash codes are recently proposed to significantly improve time and space efficiency. However, the highly developed social media presents two major challenges to hashing-based recommendation algorithms. Firstly, the boundary between information producers and consumers becomes blurred, resulting in the rapid emergence of massive online content. Meanwhile, users' limited information consumption capacity inevitably causes further interaction sparsity. The inherent high sparsity of data leads to insufficient hash learning. Secondly, a considerable amount of online content becomes fast-moving consumer goods, such as short videos and news commentary, causing frequent changes in user interests and item popularity. To address the above problems, we propose a Temporal Social Graph Network Hashing (TSGNH) method for efficient recommendation, which generates binary hash codes of users and items through dynamic-adaptive aggregation on a constructed temporal social graph network. Specifically, we build a temporal social graph network to fully capture the social information widely existing in practical recommendation scenarios and propose a dynamic-adaptive aggregation method to capture long-term and short-term characters of users and items. Furthermore, different from the discrete optimization approaches used by existing hashing-based recommendation methods, we devise an end-to-end hashing learning approach that incorporates balanced and de-correlated constraints to learn compact and informative binary hash codes tailored for recommendation scenarios. Extensive experiments on three widely evaluated recommendation datasets demonstrate the superiority of the proposed method.

With the explosive growth of multimedia contents, multimedia retrieval is facing unprecedented challenges on both storage cost and retrieval speed. Hashing technique can project the high-dimensional data into compact binary hash codes. With it, the most time-consuming semantic similarity computation during the multimedia retrieval process can be significantly accelerated with fast Hamming distance computation, and meanwhile the storage cost can be reduced greatly by the binary embedding. In the light of this, multi-modal hashing has recently received considerable attention to support large-scale multimedia retrieval. Different from uni-modal hashing, the multi-modal hashing focuses on modeling the multi-modal semantics and further preserving them into binary hash codes with hash learning. In this paper, we first systematically review the existing learning to hash methods for efficient multimedia retrieval, categorizing them according to the multimedia retrieval tasks, the specific multi-modal semantic modeling techniques, and hash learning strategies. Thereafter, we present the performance comparison results. We ultimately discuss the challenges and potential research directions that may require further investigation in multi-modal hash learning.

Conventional domain adaptive (DA) methods for person re-identification (ReID) face knowledge transfer challenges when labeled data from the source domain cannot be accessed due to privacy constraints. Although the methods operating under source-absent DA settings attempt to address this challenge by using models pretrained on the source domain in their mutual teaching frameworks, failing to capture domain divergence in scenarios in which the source data are completely inaccessible can simultaneously introduce issues related to mutual convergence. In response, we introduce an adversarial attacks-driven mutual teaching (AAMT) framework as an innovative and applicable source-free DA person ReID scheme. Specifically, we first carefully develop a perturbation generator to generate source-style adversarial examples by leveraging a pretrained source model. Then, these diverse adversarial examples are employed to attack the mutual teaching model, implicitly measuring the domain divergence. Accordingly, we design a contrastive learning loss to enlarge the differences between the training pairs and further mitigate the mutual convergence issue. Extensive experiments demonstrate that AAMT outperforms the existing methods under both conventional and source-absent DA settings, achieving state-of-the-art performance.

Face anti-spoofing (FAS) plays a crucial role in securing face recognition systems against presentation attacks. However, existing FAS methods often struggle to generalize to unseen attacks and domains. Existing generalizable FAS studies generally leverage domain generalization (DG) techniques for exploiting intermediate features that support generalization while neglecting the task-specific nature of FAS. In this paper, we argue that the FAS task is an imbalanced classification problem, which renders it unsuitable to be handled by a standard discriminative classifier. In contrast, we propose a novel approach for FAS by modeling the problem from a generative perspective using an energy-based model (EBM). The EBM captures the distribution of genuine faces and detects spoofing attempts as deviations from this distribution. We train the EBM using a discriminative objective and an energy regularization term to shape the learned distribution and improve generalization. To enhance the robustness to unseen domains, we introduce an energy-based domain augmentation technique that explores the latent space around the source distribution guided by the EBM. We further leverage a meta-learning framework and a gradient-based variant to leverage the augmented data for domain generalization. For practicability, we consider a practical setting where samples are holistically collected under different environments without distinct domain labels, and show that our method can naturally harness this challenging setting by training with cluster labels. Extensive experiments on four FAS datasets demonstrate the superiority of our method in both intra- and cross-dataset settings, outperforming state-of-the-art approaches.

Shared-account cross-domain sequential recommendation (SCSR) task aims to recommend the next item via leveraging the mixed user behaviors in multiple domains. It is gaining immense research attention as more and more users tend to sign up on different platforms and share accounts with others to access domain-specific services. Existing works on SCSR mainly rely on mining sequential patterns via recurrent neural network (RNN)-based models, which suffer from the following limitations: 1) RNN-based methods overwhelmingly target discovering sequential dependencies in single-user behaviors and they are not expressive enough to capture the relationships among multiple entities in SCSR; 2) all existing methods bridge two domains via knowledge transfer in the latent space and ignore the explicit cross-domain graph structure; and 3) none existing studies consider the time interval information among items, which is essential in the sequential recommendation for characterizing different items and learning discriminative representations for them. In this work, we propose a new graph-based solution, namely, time interval-enhanced domain-aware graph convolutional network (TiDA-GCN), to address the above challenges. Specifically, we first link users and items in each domain as a graph. Then, we devise a domain-aware graph convolution network to learn user-specific node representations. To fully account for users' domain-specific preferences on items, two effective attention mechanisms are further developed to selectively guide the message-passing process. Moreover, to further enhance item- and account-level representation learning, we incorporate the time interval into the message passing and design an account-aware self-attention module for learning items' interactive characteristics. Experiments demonstrate the superiority of our proposed method from various aspects.

The goal of talking face generation is to synthesize a sequence of face images of the specified identity, ensuring the mouth movements are synchronized with the given audio. Recently, image-based talking face generation has emerged as a popular approach. It could generate talking face images synchronized with the audio merely depending on a facial image of arbitrary identity and an audio clip. Despite the accessible input, it forgoes the exploitation of the audio emotion, inducing the generated faces to suffer from emotion unsynchronization, mouth inaccuracy, and image quality deficiency. In this article, we build a bistage audio emotion-aware talking face generation (AMIGO) framework, to generate high-quality talking face videos with cross-modally synced emotion. Specifically, we propose a sequence-to-sequence (seq2seq) cross-modal emotional landmark generation network to generate vivid landmarks, whose lip and emotion are both synchronized with input audio. Meantime, we utilize a coordinated visual emotion representation to improve the extraction of the audio one. In stage two, a feature-adaptive visual translation network is designed to translate the synthesized landmarks into facial images. Concretely, we proposed a feature-adaptive transformation module to fuse the high-level representations of landmarks and images, resulting in significant improvement in image quality. We perform extensive experiments on the multi-view emotional audio-visual dataset (MEAD) and crowd-sourced emotional multimodal actors dataset (CREMA-D) benchmark datasets, demonstrating that our model outperforms state-of-the-art benchmarks.

Unsupervised Non-overlapping Cross-domain Recommendation (UNCR) is the task that recommends source domain items to the target domain users, which is more challenging as the users are non-overlapped, and its learning process is unsupervised. Unsupervised Non-overlapping Cross-domain Recommendation UNCR is still unsolved due to the following: (1) Previous studies need extra auxiliary information to learn transferable features when aligning two domains, which is unrealistic and hard to obtain due to privacy concerns. (2) Since the adoption of the shared network, existing works cannot well eliminate the domain-specific features in the common feature space, which may incorporate domain noise and harm the cross-domain recommendation. In this work, we propose a domain adaption-based method, namely DA-DAN, to address the above challenges. Specifically, to let DA-DAN be free of auxiliary information, we learn users’ preferences by only exploring their sequential patterns, and propose an improved self-attention layer to model them. To well eliminate the domain-specific features from the common feature space, we resort to a dual generative adversarial network with a multi-target adversarial loss, where two generators and discriminators are leveraged to model each domain separately. Experimental results on three real-world datasets demonstrate the advantage of DA-DAN compared with the state-of-the-art recommendation baselines. Moreover, our source codes have been publicly released. 1

Cross-domain Recommendation is the task that tends to improve the recommendations in the sparse target domain by leveraging the information from other rich domains. Existing methods of cross-domain recommendation mainly focus on overlapping scenarios by assuming users are totally or partially overlapped, which are taken as bridges to connect different domains. However, this assumption does not always hold, since it is illegal to leak users’ identity information to other domains. Conducting Non-overlapping MCR (NMCR) is challenging, since (1) the absence of overlapping information prevents us from directly aligning different domains, and this situation may get worse in the MCR scenario, and (2) the distribution between source and target domains makes it difficult for us to learn common information across domains. To overcome the above challenges, we focus on NMCR and devise MCRPL as our solution. To address Challenge 1, we first learn shared domain-agnostic and domain-dependent prompts and pre-train them in the pre-training stage. To address Challenge 2, we further update the domain-dependent prompts with other parameters kept fixed to transfer the domain knowledge to the target domain. We conduct experiments on five real-world domains, and the results show the advance of our MCRPL method compared with several recent SOTA baselines. Moreover, our source codes have been publicly released. 1

Data scarcity is a perpetual challenge of recommendation systems, and researchers have proposed a variety of cross-domain recommendation methods to alleviate the problem of data scarcity in target domains. However, in many real-world cross-domain recommendation systems, the source domain and the target domain are sampled from different data distributions, which obstructs the cross-domain knowledge transfer. In this article, we propose to specifically align the data distributions between the source domain and the target domain to alleviate imbalanced sample distribution and thus challenge the data scarcity issue in the target domain. Technically, our proposed approach builds a dual adversarial adaptation (DAA) framework to adversarially train the target model together with a pre-trained source model. Two domain discriminators play the two-player minmax game with the target model and guide the target model to learn reliable domain-invariant features that can be transferred across domains. At the same time, the target model is calibrated to learn domain-specific information of the target domain. In addition, we formulate our approach as a plug-and-play module to boost existing recommendation systems. We apply the proposed method to address the issues of insufficient data and imbalanced sample distribution in real-world Click-through Rate/Conversion Rate predictions on two large-scale industrial datasets. We evaluate the proposed method in scenarios with and without overlapping users/items, and extensive experiments verify that the proposed method is able to significantly improve the prediction performance on the target domain. For instance, our method can boost PLE with a performance improvement of 15.4% in terms of Area Under Curve compared with single-domain PLE on our private game dataset. In addition, our method is able to surpass single-domain MMoE by 6.85% on the public datasets. Code: https://github.com/TL-UESTC/DAA .

Deep cross-modal hashing has promoted the field of multi-modal retrieval due to its excellent efficiency and storage, but its vulnerability to backdoor attacks is rarely studied. Notably, current deep cross-modal hashing methods inevitably require large-scale training data, resulting in poisoned samples with imperceptible triggers that can easily be camouflaged into the training data to bury backdoors in the victim model. Nevertheless, existing backdoor attacks focus on the uni-modal vision domain, while the multi-modal gap and hash quantization weaken their attack performance. In addressing the aforementioned challenges, we undertake an invisible black-box backdoor attack against deep cross-modal hashing retrieval in this article. To the best of our knowledge, this is the first attempt in this research field. Specifically, we develop a flexible trigger generator to generate the attacker’s specified triggers, which learns the sample semantics of the non-poisoned modality to bridge the cross-modal attack gap. Then, we devise an input-aware injection network, which embeds the generated triggers into benign samples in the form of sample-specific stealth and realizes cross-modal semantic interaction between triggers and poisoned samples. Owing to the knowledge-agnostic of victim models, we enable any cross-modal hashing knockoff to facilitate the black-box backdoor attack and alleviate the attack weakening of hash quantization. Moreover, we propose a confusing perturbation and mask strategy to induce the high-performance victim models to focus on imperceptible triggers in poisoned samples. Extensive experiments on benchmark datasets demonstrate that our method has a state-of-the-art attack performance against deep cross-modal hashing retrieval. Besides, we investigate the influences of transferable attacks, few-shot poisoning, multi-modal poisoning, perceptibility, and potential defenses on backdoor attacks. Our codes and datasets are available at https://github.com/tswang0116/IB3A.

Domain adaption (DA) for person re-identification (ReID) has attained considerable progress by transferring knowledge from a source domain with labels to a target domain without labels. Nonetheless, most of the existing methods require access to source data, which raises privacy concerns. Source-free DA has recently emerged as a response to these privacy challenges, yet its direct application to open-set pedestrian re-identification tasks is hindered by the reliance on a shared category space in existing methods. Current source-free DA approaches for person ReID still encounter several obstacles, particularly the divergence-agnostic problem and the notable domain divergence due to the absent source data. In this article, we introduce an Instance-level Adversarial Mutual Teaching (IAMT) framework, which utilizes adversarial views to tackle the challenges mentioned above. Technically, we first elaborately develop a variance-based division (VBD) module to segregate the target data into instance-level subsets based on their similarity and dissimilarity to the source using the source-trained model, implicitly tackling the divergence-agnostic problem. To mitigate domain divergence, we additionally introduce a dynamic adversarial alignment (DAA) strategy, aiming to enhance the consistence of feature distribution across domains by employing adversarial instances from the target data to confuse the discriminators. Experiments reveal the superiority of the IAMT over state-of-the-art methods for DA person ReID tasks, while preserving the privacy of the source data.

Most cross-modal retrieval methods assume the multi-modal training data is complete and has a one-to-one correspondence. However, in the real world, multi-modal data generally suffers from missing modality information due to the uncertainty of data collection and storage processes, which limits the practical application of existing cross-modal retrieval methods. Although some solutions have been proposed to generate the missing modality data using a single pseudo sample, this may lead to incomplete semantic restoration and sub-optimal retrieval results due to the limited semantic information it provides. To address this challenge, this article proposes an Incomplete Cross-Modal Retrieval with Deep Correlation Transfer (ICMR-DCT) method that can robustly model incomplete multi-modal data and dynamically capture the adjacency semantic correlation for cross-modal retrieval. Specifically, we construct intra-modal graph attention-based auto-encoder to learn modality-invariant representations by performing semantic reconstruction through intra-modality adjacency correlation mining. Then, we design dual cross-modal alignment constraints to project multi-modal representations into a common semantic space, thus bridging the heterogeneous modality gap and enhancing the discriminability of the common representation. We further introduce semantic preservation to enhance adjacency semantic information and achieve cross-modal semantic correlation. Moreover, we propose a nearest-neighbor weighting integration strategy with cross-modal correlation transfer to generate the missing modality data according to inter-modality mapping relations and adjacency correlations between each sample and its neighbors, which improves the robustness of our method against incomplete multi-modal training data. Extensive experiments on three widely tested benchmark datasets demonstrate the superior performance of our method in cross-modal retrieval tasks under both complete and incomplete retrieval scenarios. Our used datasets and source codes are available at https://github.com/shidan0122/DCT.git .

Multi-behavioral recommender systems have emerged as a solution to address data sparsity and cold-start issues by incorporating auxiliary behaviors alongside target behaviors. However, existing models struggle to accurately capture varying user preferences across different behaviors and fail to account for diverse item preferences within behaviors. Various user preference factors (such as price or quality) entangled in the behavior may lead to sub-optimization problems. Furthermore, these models overlook the personalized nature of user behavioral preferences by employing uniform transformation networks for all users and items. To tackle these challenges, we propose the Disentangled Cascaded Graph Convolutional Network (Disen-CGCN), a novel multi-behavior recommendation model. Disen-CGCN employs disentangled representation techniques to effectively separate factors within user and item representations, ensuring their independence. In addition, it incorporates a multi-behavioral meta-network, enabling personalized feature transformation across user and item behaviors. Furthermore, an attention mechanism captures user preferences for different item factors within each behavior. By leveraging attention weights, we aggregate user and item embeddings separately for each behavior, computing preference scores that predict overall user preferences for items. Our evaluation of benchmark datasets demonstrates the superiority of Disen-CGCN over state-of-the-art models, showcasing an average performance improvement of 7.07% and 9.00% on respective datasets. These results highlight Disen-CGCN’s ability to effectively leverage multi-behavioral data, leading to more accurate recommendations.

Sarcasm is a sophisticated linguistic phenomenon that is prevalent on today's social media platforms. Multi-modal sarcasm detection aims to identify whether a given sample with multi-modal information (i.e., text and image) is sarcastic. This task's key lies in capturing both inter- and intra-modal incongruities within the same context. Although existing methods have achieved compelling success, they are disturbed by irrelevant information extracted from the whole image and text, or overlooking some important information due to the incomplete input. To address these limitations, we propose a Mutual-enhanced Incongruity Learning Network for multi-modal sarcasm detection, named MILNet. In particular, we design a local semantic-guided incongruity learning module and a global incongruity learning module. Moreover, we introduce a mutual enhancement module to take advantage of the underlying consistency between the two modules to boost the performance. Extensive experiments on a widely-used dataset demonstrate the superiority of our model over cutting-edge methods.

Accurate estimation of customer lifetime value (LTV), which reflects the potential consumption of a user over a period of time, is crucial for the revenue management of online advertising platforms. However, predicting LTV in real-world applications is not an easy task since the user consumption data is usually insufficient within a specific domain. To tackle this problem, we propose a novel cross-domain adaptative framework (CDAF) to leverage consumption data from different domains. The proposed method is able to simultaneously mitigate the data scarce problem and the distribution gap problem caused by data from different domains. To be specific, our method firstly learns a LTV prediction model from a different but related platform with sufficient data provision. Subsequently, we exploit domain-invariant information to mitigate data scarce problem by minimizing the Wasserstein discrepancy between the encoded user representations of two domains. In addition, we design a dual-predictor schema which not only enhances domain-invariant information in the semantic space but also preserves domain-specific information for accurate target prediction. The proposed framework is evaluated on five datasets collected from real historical data on the advertising platform of Tencent Games. Experimental results verify that the proposed framework is able to significantly improve the LTV prediction performance on this platform. For instance, our method can boost DCNv2 with the improvement of 13.7% in terms of AUC on dataset G2. Code: https://github.com/TL-UESTC/CDAF.

The occluded target person often lead to incorrect matching results, so eliminating the interference of background clutter is a key matter. To deal with the challenging occluded person re-identification (Re-ID) tasks, this paper proposes a new grouped pose estimation occlusion generation (GPEOG) network to fully use the person grouped keypoint information and the stable non-occluded features, and make the extracted features more robust and discriminative. The local branch uses the proposed Dynamic Adaptive module (DAM) to automatically adjust the patch size during training process and provides adaptive local features. The occlusion-suppression generation branch mainly includes the proposed effective occlusion suppression (EOS) module. It judges whether the person’s keypoint groups are occluded, and then generates the masks of the corresponding parts to suppress occlusion. Extensive experiments show that the proposed method has obvious advantages compared with several state-of-the-art methods.

Although deep cross-modal hashing methods have shown superiorities for cross-modal retrieval recently, there is a concern about potential data privacy leakage when training the models. Federated learning adopts a distributed machine learning strategy, which can collaboratively train models without leaking local private data. It is a promising technique to support privacy-preserving cross-modal hashing. However, existing federated learning-based cross-modal retrieval methods usually rely on a large number of semantic annotations, which limits the scalability of the retrieval models. Furthermore, they mostly update the global models by aggregating local model parameters, ignoring the differences in the quantity and category of multi-modal data from multiple clients. To address these issues, we propose a Prototype Transfer-based Federated Unsupervised Cross-modal Hashing(PT-FUCH) method for solving the privacy leakage problem in cross-modal retrieval model learning. PT-FUCH protects local private data by exploring unified global prototypes for different clients, without relying on any semantic annotations. Global prototypes are used to guide the local cross-modal hash learning and promote the alignment of the feature space, thereby alleviating the model bias caused by the difference in the distribution of local multi-modal data and improving the retrieval accuracy. Additionally, we design an adaptive cross-modal knowledge distillation to transfer valuable semantic knowledge from modal-specific global models to local prototype learning processes, reducing the risk of overfitting. Experimental results on three benchmark cross-modal retrieval datasets validate that our PT-FUCH method can achieve outstanding retrieval performance when trained under distributed privacy-preserving mode. The source codes of our method are available at https://github.com/exquisite1210/PT-FUCH_P.

An ideal multi-modal recommendation system is supposed to be timely updated with the latest modality information and interaction data because the distribution discrepancy between new data and historical data will lead to severe recommendation performance deterioration. However, upgrading a recommendation system with numerous new data consumes much time and computing resources. To mitigate this problem, we propose a Task-Adversarial Adaptation (TAA) framework, which is able to align data distributions and reduce resource consumption at the same time. This framework is specifically designed to align distributions of embedded features for different recommendation tasks between the source domain (i.e., historical data) and the target domain (i.e., new data). Technically, we design a domain feature discriminator for each task to distinguish which domain a feature comes from. By the two-player min-max game between the feature discriminator and the feature embedding network, the feature embedding network is able to align the source and target data distributions. With the ability to align source and target distributions, we are able to reduce the number of training samples by random sampling. In addition, we formulate the proposed approach as a plug-and-play module to accelerate the model training and improve the performance of mainstream multi-modal multi-task recommendation systems. We evaluate our method by predicting the Click-Through Rate (CTR) in e-commerce scenarios. Extensive experiments verify that our method is able to significantly improve prediction performance and accelerate model training on the target domain. For instance, our method is able to surpass the previous state-of-the-art method by 2.45% in terms of Area Under Curve (AUC) on AliExpress_US dataset while only utilizing one percent of the target data in training. Code: https://github.com/TL-UESTC/TAA.

Continual test-time domain adaptation (TTA) is a challenging topic in the field of source-free domain adaptation, which focuses on addressing cross-domain multimedia information during inference with a continuously changing data distribution. Previous methods have been found to lack noise robustness, leading to a significant increase in errors under strong noise. In this paper, we address the noise-robustness problem in continual TTA by offering three effective recipes to mitigate it. At the category level, we employ the Taylor cross-entropy loss to alleviate the low confidence category bias commonly associated with cross-entropy. At the sample level, we reweight the target samples based on uncertainty to prevent the model from overfitting on noisy samples. Finally, to reduce pseudo-label noise, we propose a soft ensemble negative learning mechanism to guide the model optimization using ensemble complementary pseudo labels. Our method achieves state-of-the-art performance on three widely used continual TTA datasets, particularly in the strong noise setting that we introduced.

Multi-behavior recommendation, which exploits auxiliary behaviors (e.g., click and cart) to help predict users’ potential interactions on the target behavior (e.g., buy), is regarded as an effective way to alleviate the data sparsity or cold-start issues in recommendation. Multi-behaviors are often taken in certain orders in real-world applications (e.g., click>cart>buy). In a behavior chain, a latter behavior usually exhibits a stronger signal of user preference than the former one does. Most existing multi-behavior models fail to capture such dependencies in a behavior chain for embedding learning. In this work, we propose a novel multi-behavior recommendation model with cascading graph convolution networks (named MB-CGCN). In MB-CGCN, the embeddings learned from one behavior are used as the input features for the next behavior’s embedding learning after a feature transformation operation. In this way, our model explicitly utilizes the behavior dependencies in embedding learning. Experiments on two benchmark datasets demonstrate the effectiveness of our model on exploiting multi-behavior data. It outperforms the best baseline by 33.7% and 35.9% on average over the two datasets in terms of Recall@10 and NDCG@10, respectively.

Many current video and text cross-modal retrieval research works focus on narrowing the semantic gap between video and text, but ignore the semantic difference between different sampled frames in the same video and the correlation of feature distribution of objects contained in different sampled frames in the same video, as a result, the features of the sampled frames in the final learned video cannot well represent the semantic features of the whole video. To overcome the shortcomings of existing studies, we first use a pre-trained video frame classification-aggregation network to make the object categories contained in different sampled frames in the same video be more close to the important object categories contained in the whole video, so as to promote the feature distribution of different sampled frames in the same video to be consistent, and increase the relevance of object features in different frames. Then we propose a video internal frame aggregation loss module to solve the problem of inconsistent feature distribution between different frame features encoded by video encoder in the same video and the aggregation feature of the sampled frame, thus enhancing the ability of video sampled frame aggregation feature representation. Experiments conducted on three common datasets MSVD, MSR-VTT and DiDeMo demonstrate the validity of the proposed approach.

Generalized zero-shot learning (GZSL) aims to recognize both seen and unseen samples by leveraging the connections between semantic and visual representations. Recently, a majority of GZSL methods focus on generating visual features for unseen categories conditioned on category-level semantic attributes. However, there is a considerable gap between generated features and real unseen features since the generator is trained with only seen samples. The final classifier may get confused by the unfaithful generated features and make misclassification. To alleviate this issue, we propose a dual-aligned feature confusion alleviation (DFCA) framework that simultaneously generates faithful and discriminative features for unseen categories. Specifically, our DFCA attains the faithfulness via a conditional invertible neural network (cINN) and aligns the generated visual features and reconstructed semantic conditions with their real counterparts, respectively. To further encourage distinguishable synthetic features, we learn discriminative category-level semantic conditions for cINN with an attributes mapping layer. To verify the proposed method, we conduct extensive experiments on five widely used benchmarks. Experimental results show that our method outperforms previous state-of-the-arts and successfully alleviates features confusion problem in GZSL. For instance, our method achieves the best performance in terms of seen accuracy, unseen accuracy and harmonic mean accuracy on FLO.

Zero-shot Learning (ZSL) aims to recognize novel classes through seen knowledge. The canonical approach to ZSL leverages a visual-to-semantic embedding to map the global features of an image sample to its semantic representation. These global features usually overlook the fine-grained information which is vital for knowledge transfer between seen and unseen classes, rendering these features sub-optimal for ZSL task, especially the more realistic Generalized Zero-shot Learning (GZSL) task where global features of similar classes could hardly be separated. To provide a remedy to this problem, we propose Language-Augmented Pixel Embedding (LAPE) that directly bridges the visual and semantic spaces in a pixel-based manner. To this end, we map the local features of each pixel to different attributes and then extract each semantic attribute from the corresponding pixel. However, the lack of pixel-level annotation conduces to an inefficient pixel-based knowledge transfer. To mitigate this dilemma, we adopt the text information of each attribute to augment the local features of image pixels which are related to the semantic attributes. Experiments on four ZSL benchmarks demonstrate that LAPE outperforms current state-of-the-art methods. Comprehensive ablation studies and analyses are provided to dissect what factors lead to this success.

Deep cross-modal hashing has achieved excellent retrieval performance with the powerful representation capability of deep neural networks. Regrettably, current methods are inevitably vulnerable to adversarial attacks, especially well-designed subtle perturbations that can easily fool deep cross-modal hashing models into returning irrelevant or the attacker’s specified results. Although adversarial attacks have attracted increasing attention, there are few studies on specialized attacks against deep cross-modal hashing. To solve these issues, we propose a targeted adversarial attack method against deep cross-modal hashing retrieval in this paper. To the best of our knowledge, this is the first work in this research field. Concretely, we first build a progressive fusion module to extract fine-grained target semantics through a progressive attention mechanism. Meanwhile, we design a semantic adaptation network to generate the target prototype code and reconstruct the category label, thus realizing the semantic interaction between the target semantics and the implicit semantics of the attacked model. To bridge modality gaps and preserve local example details, a semantic translator seamlessly translates the target semantics and then embeds them into benign examples in collaboration with a U-Net framework. Moreover, we construct a discriminator for adversarial training, which enhances the visual realism and category discrimination of adversarial examples, thus improving their targeted attack performance. Extensive experiments on widely tested cross-modal retrieval datasets demonstrate the superiority of our proposed method. Also, transferable attacks show that our generated adversarial examples have well generalization capability on targeted attacks. The source codes and datasets are available athttps://github.com/tswang0116/TA-DCH.

The bi-classifier paradigm is widely adopted as an adversarial method to address domain shift challenge in unsupervised domain adaptation (UDA) by evenly training two classifiers. In this paper, we report that although the generalization ability of the feature extractor can be strengthened by the two even classifiers, the decision boundaries of the two classifiers would be shrank to the source domain in the adversarial process, which weakens the discriminative ability of the learned model. To tame this dilemma, we disentangle the function of the two classifiers and introduce uneven bi-classifier learning for domain adaptation. Specifically, we leverage the F-norm (Frobenius Norm) of classifier predictions instead of the classifier disagreement to achieve adversarial learning. By this way, our feature extractor can be adversarially trained with a single classifier and the other classifier is used for preserving the target-specific decision boundaries. The proposed uneven bi-classifier learning protocol can simultaneously enhance the generalization ability of the feature extractor and expand the decision boundary of the target classifier. Extensive experiments on large-scale datasets prove that our method can significantly surpass previous domain adaptation methods, even with only a single classifier being involved.

The bi-classifier paradigm is a common practice in unsupervised domain adaptation (UDA), where two classifiers are leveraged to guide the model to learn domain invariant features. Previous approaches only focused on the consistency of the outputs between classifiers, but ignored the classification certainty of each classifier. Therefore, existing methods in some cases may mislead the classifiers into the wrong direction of ambiguous outputs and subsequently undermine the discriminability. To challenge this problem, in this paper we propose Classification Certainty Maximization (CCM) which considers both the joint certainty between classifiers and the individual certainty of each classifier via a novel formulation, and derived their optimal weight ratios by theoretical derivation from the perspective of gradient. In addition, we also propose a dynamic centroid update strategy to mitigate the domain gaps at the feature level. Extensive experiments on four widely used UDA datasets show that CCM performs better than the existing state-of-the-art domain adaptation methods. Notably, our dynamic centroid update strategy can be used as a plug-and-play module for existing bi-classifier domain adaptation methods to boost classification accuracy.

Multiview spectral clustering (MVSC) has achieved state-of-the-art clustering performance on multiview data. Most existing approaches first simply concatenate multiview features or combine multiple view-specific graphs to construct a unified fusion graph and then perform spectral embedding and cluster label discretization with k -means to obtain the final clustering results. They suffer from an important drawback: all views are treated as fixed when fusing multiple graphs and equal when handling the out-of-sample extension. They cannot adaptively differentiate the discriminative capabilities of multiview features. To alleviate these problems, we propose a flexible MVSC with self-adaptation (FMSCS) method in this article. A self-adaptive learning scheme is designed for structured graph construction, multiview graph fusion, and out-of-sample extension. Specifically, we learn a fusion graph with a desirable clustering structure by adaptively exploiting the complementarity of different view features under the guidance of a proper rank constraint. Meanwhile, we flexibly learn multiple projection matrices to handle the out-of-sample extension by adaptively adjusting the view combination weights according to the specific contents of unseen data. Finally, we derive an alternate optimization strategy that guarantees desirable convergence to iteratively solve the formulated unified learning model. Extensive experiments demonstrate the superiority of our proposed method compared with state-of-the-art MVSC approaches. For the purpose of reproducibility, we provide the code and testing datasets at https://github.com/shidan0122/FMICS.

Unsupervised feature selection chooses a subset of discriminative features to reduce feature dimension under the unsupervised learning paradigm. Although lots of efforts have been made so far, existing solutions perform feature selection either without any label guidance or with only single pseudo label guidance. They may cause significant information loss and lead to semantic shortage of the selected features as many real-world data, such as images and videos are generally annotated with multiple labels. In this paper, we propose a new Unsupervised Adaptive Feature Selection with Binary Hashing (UAFS-BH) model, which learns binary hash codes as weakly-supervised multi-labels and simultaneously exploits the learned labels to guide feature selection. Specifically, in order to exploit the discriminative information under the unsupervised scenarios, the weakly-supervised multi-labels are learned automatically by specially imposing binary hash constraints on the spectral embedding process to guide the ultimate feature selection. The number of weakly-supervised multi-labels (the number of "1" in binary hash codes) is adaptively determined according to the specific data content. Further, to enhance the discriminative capability of binary labels, we model the intrinsic data structure by adaptively constructing the dynamic similarity graph. Finally, we extend UAFS-BH to multi-view setting as Multi-view Feature Selection with Binary Hashing (MVFS-BH) to handle the multi-view feature selection problem. An effective binary optimization method based on the Augmented Lagrangian Multiple (ALM) is derived to iteratively solve the formulated problem. Extensive experiments on widely tested benchmarks demonstrate the state-of-the-art performance of the proposed method on both single-view and multi-view feature selection tasks. For the purpose of reproducibility, we provide the source codes and testing datasets at https://github.com/shidan0122/UMFS.git..

Unsupervised multi-view feature selection aims to select informative features with multi-view features and unsupervised learning. It is a challenging problem due to the absence of explicit semantic supervision. Recently, graph theory and hard pseudo-label learning have been adopted to solve multi-view feature selection problems under the unsupervised learning paradigm. However, graph-based methods are difficult to support large-scale real scenarios due to the high computational complexity of graph construction. Moreover, existing methods based on hard pseudo-label learning generally result in significant information loss. In this article, we propose an Adaptive Collaborative Soft Label Learning (ACSLL) model for unsupervised multi-view feature selection. In this model, collaborative soft label learning and multi-view feature selection are integrated into a unified framework. Specifically, we learn the pseudo soft labels from each view feature by a simple and efficient method and fuse them with an adaptive weighting strategy into a joint soft label matrix. This matrix is further used for guiding the feature selection process to identify valuable features. An effective optimization strategy guaranteed with proven convergence is derived to iteratively solve this problem. Experiments demonstrate the superiority of the proposed method in both feature selection accuracy and efficiency.

Semi-supervised feature selection methods jointly exploit the labelled and unlabeled samples when selecting the features. Under the semi-supervised learning scenario, the number of labelled data significantly impacts the feature selection performance. In this paper, we introduce the label learning with binary hashing to the research field of feature selection and propose a novel Semi-supervised Feature Selection with Binary Label Learning (SFS-BLL) model. Specifically, we learn the binary hash codes as the pseudo labels by specially imposing binary hash constraints on the spectral embedding process to increase the number of labels. Meanwhile, we propose a self-weighted sparse regression module which exploits the learned labels and given manual labels together with importance differentiation to guide the feature selection process. Finally, we develop an effective discrete optimization method based on the Alternating Direction Method of Multipliers (ADMM) to iteratively optimize the binary labels and the feature selection matrix. Extensive experiments on widely tested benchmarks demonstrate the superiority of the proposed method from various aspects.

Hashing is an effective technique to improve the efficiency of large-scale recommender system by representing both users and items into binary codes. However, existing hashing-based recommendation methods still suffer from two important problems: 1) Cold-start. They employ the user-item interactions and single auxiliary information to learn the binary hash codes. But the full interaction history is not always available and the single auxiliary information may be missing. 2) Efficient optimization. They learn the hash codes with two-step relaxed optimization or one-step discrete hash optimization based on the cyclic coordinate descent, which results in significant quantization loss or still consumes considerable computation time. In this paper, we propose a Multi-modal Discrete Collaborative Filtering (MDCF) for efficient cold-start recommendation. We map the multi-modal features of users and items to a consensus Hamming space based on the matrix factorization framework. Specifically, a low-rank self-weighted multi-modal fusion module is designed to adaptively fuse the multi-modal features into binary hash codes. Additionally, to support large-scale recommendation, a fast discrete optimization method based on augmented Lagrangian multiplier is developed to directly compute the binary hash codes with simple operations. Experiments show the superior performance of the proposed method over state-of-the-art baselines.

Cross-modal hashing has garnered considerable attention and gained great success in many cross-media similarity search applications due to its prominent computational efficiency and low storage overhead. However, it still remains challenging how to effectively take multilevel advantages of semantics on the entire database to jointly bridge the semantic and heterogeneity gaps across different modalities. In this paper, we propose a novel Modality-Invariant Asymmetric Networks (MIAN) architecture, which explores the asymmetric intra- and inter-modal similarity preservation under a probabilistic modality alignment framework. Specifically, an intra-modal asymmetric network is conceived to capture the query-vs-all internal pairwise similarities for each modality in a probabilistic asymmetric learning manner. Moreover, an inter-modal asymmetric network is deployed to fully harness the cross-modal semantic similarities supported by the maximum inner product search formula between two distinct hash embeddings. Particularly, the pairwise, piecewise and transformed semantics are jointly considered into one unified semantic-preserving hash codes learning scheme. Furthermore, we construct a modality alignment network to distill the redundancy-free visual features and maximize the conditional bottleneck information between different modalities. Such a network could close the heterogeneity and domain shift across different modalities. Extensive experiments evidence that our MIAN approach can outperform the state-of-the-art cross-modal hashing methods.

Unsupervised cross-modal hashing has attracted considerable attention to support large-scale cross-modal retrieval. Although promising progresses have been made so far, existing methods still suffer from limited capability on excavating and preserving the intrinsic multi-modal semantics. In this paper, we propose a Correlation-Identity Reconstruction Hashing (CIRH) method to alleviate this challenging problem. We develop a new unsupervised deep cross-modal hash learning framework to model and preserve the heterogeneous multi-modal correlation semantics into both hash codes and functions, and simultaneously, we involve both the hash codes and functions with the descriptive identity semantics. Specifically, we construct a multi-modal collaborated graph to model the heterogeneous multi-modal correlations, and jointly perform the intra-modal and cross-modal semantic aggregation on homogeneous and heterogeneous graph networks to generate a multi-modal complementary representation with correlation reconstruction. Furthermore, an identity semantic reconstruction process is designed to involve the generated representation with identity semantics by reconstructing the input modality representations. Finally, we propose a correlation-identity consistent hash function learning strategy to transfer the modelled multi-modal semantics into the neural networks of modality-specific deep hash functions. Experiments demonstrate the superior performance of the proposed method on both retrieval accuracy and efficiency. We provide our source codes and experimental datasets athttps://github.com/XizeWu/CIRH

Using hashing to learn the binary codes of users and items significantly improves the efficiency and reduces the space consumption of the recommender system. However, existing hashing-based recommender systems remain black boxes without any explainable outputs that illustrate why the system recommends the items. In this paper, we present a new end-to-end discrete recommendation framework based on the multi-task learning to simultaneously perform explainable and efficient recommendation. Toward this goal, an Explainable Discrete Collaborative Filtering (EDCF) method is proposed to preserve the user-item interaction features and semantic text features into binary hash codes by adaptively exploiting the correlations between the preference prediction task and the explanation generation task. At the online recommendation stage, EDCF makes efficient top-K recommendation by calculating the Hamming distances between the feature hash codes, and simultaneously generates natural language explanations for recommendation results through the explanation generation module. To obtain the hash codes directly from the end-to-end neural network, we introduce an attentive TextCNN and an Adaptive Tanh layer in the preference prediction task. For explanation generation, Long Short-Term Memory is employed to generate the explanations for recommendation results from the binary hash codes of user and item. Experiments demonstrate the superiority of the proposed method.

Multimedia applications often involve knowledge transfer across domains, e.g., from images to texts, where Unsupervised Domain Adaptation (UDA) can be used to reduce the domain shifts. Most of the UDA methods are based on adversarial learning. However, previous adversarial domain adaptation methods may suffer from three issues. First, although the features learned by previous methods could fool the domain classifier to make false classification predictions, they may not be domain-invariant. Second, the limited number of training samples make the latent space of features not smooth and continuous enough. Third, the target domain features may lack discriminability. In this paper, we propose a novel adversarial domain adaptation method named Adversarial Mixup Ratio Confusion (AMRC) to alleviate all the above issues. Specifically, we propose a new adversarial training pattern that uses mixup to generate multiple features with different mixup ratios, which represent different intermediate states between the source and target domain. Then, on one hand, we train an estimator to estimate the mixup ratio as accurately as possible. On the other hand, we train a generator to make the estimator be uncertain about the mixup ratio. In this way, our method could learn a continuous and domain-invariant latent space. Furthermore, we apply the intra-domain and cross-domain mixup regularizations to ensure the smoothness and continuity of the latent space, while making the classifier behave more linearly on in-between samples. At last, we exploit the sharpened pseudo-labels of the target samples for self-supervised learning to enhance the discriminability of the target features.The experimental results on 3 benchmarks verify the effectiveness of our method.

Although there are lots of studies on scene text recognition, few of them focus on the recognition of the incomplete text. The recognition performance of existing text recognition algorithms on the incomplete text is far from the expected, and the recognition of the incomplete text is still challenging. In this paper, an end-to-end Two-Stage Inpainting Network for Incomplete Text (TSINIT) is proposed to reconstruct the incomplete text into the complete one even when the text is in various styles and with various backgrounds, and the reconstructed text can be recognized by the existing text recognition algorithms correctly. The proposed TSINIT is divided into text extraction module (TEM) and text reconstruction module (TRM) to make the inpainting only focus on the text. TEM separates the incomplete text from the background and character-like regions at the pixel level, which can reduce the ambiguity of text reconstruction caused by the background. TRM reconstructs the incomplete text towards the most possible text with the consideration of the abstract and semantic structures of the text. Furthermore, we build a synthetic incomplete text dataset (SITD), which contains contaminated and abraded text images. SITD is divided into 6 incomplete levels according to the number of pixels in the incomplete regions and the ratio of the incomplete characters to all characters. The experimental results show that the proposed method has better inpainting ability for the incomplete text compared with traditional image inpainting algorithms on the proposed SITD and real images. When using the same text recognition method, the recognition accuracy of the incomplete text on SITD can be improved much more with the help of the proposed TSINIT than with the traditional image inpainting methods.

Inspired by the powerful representation capability of deep neural networks, deep cross-modal hashing methods have recently drawn much attention and various deep cross-modal hashing methods have been developed. However, two key problems have not been solved well yet: 1) With advanced neural network models, how to seek the multi-modal alignment space which can effectively model the intrinsic multi-modal correlations and reduce the heterogeneous modality gaps. 2) How to effectively and efficiently preserve the modelled multi-modal semantic correlations into the binary hash codes under the deep learning paradigm. In this paper, we propose aHierarchical Message Aggregation Hashing(HMAH) method within an efficient teacher-student learning framework. Specifically, on the teacher end, we develop hierarchical message aggregation networks to construct a multi-modal complementary space by aggregating the semantic messages hierarchically across different modalities, which can better align the heterogeneous modalities and model the fine-grained multi-modal correlations. On the student end, we train a couple of student modules that learn hash functions to support cross-modal retrieval. We design a cross-modal correlation knowledge distillation strategy which seamlessly transfers the modelled fine-grained multi-modal semantic correlations from the teacher to the lightweight student modules. With the fine-grained knowledge supervision from teacher module, the semantic representation capability of hash functions can be enhanced. In addition, the whole learning framework avoids the time-consuming finetuning on the pre-trained deep models as existing methods and it is computationally efficient. Experimental results demonstrate the significant performance improvement of the proposed method on both retrieval accuracy and efficiency, compared with the state-of-the-art deep cross-modal hashing methods.

Multi-modal hashing technology can support large-scale multimedia retrieval well, because of its fast query speed and low storage consumption. Although many multi-modal hashing methods have been developed in the literature, they still suffer from three important problems: 1) Most multi-modal hashing methods assume that multi-modal data are complete. This ideal assumption limits their application to practical retrieval scenarios, where the modality-missing is common. 2) Existing partial multi-modal hashing methods directly model incomplete multi-modal data for hash learning, which may result in partial multi-modal semantics in the learned hash codes. 3) Most of the methods are based on the shallow learning framework, which inevitably suffers from limited representation capability. To solve the above problems, we propose a flexible deep partial multi-modal hash learning framework, named Neighbor-aware Completion Hashing (NCH). Our framework jointly performs the cross-modal completion learning for incomplete multi-modal data and the multi-modal hash learning. It can not only support model training with incomplete multi-modal data but also handle incomplete multi-modal queries. Besides, we design a neighbor-aware completion learning module to capture neighbor semantics and generate distribution-consistent completed features. Finally, we conduct extensive experiments to evaluate our method on both fully-paired and partial multi-modal retrieval scenarios. The experimental results verify the superiority of our proposed method over the state-of-the-art baselines. The experimental codes of our method are released at:https://github.com/FutureTwT/NCH.

Deep cross-modal hashing retrieval models inherit the vulnerability of deep neural networks. They are vulnerable to adversarial attacks, especially for the form of subtle perturbations to the inputs. Although many adversarial attack methods have been proposed to handle the robustness of hashing retrieval models, they still suffer from two problems: (1) Most of them are based on the white-box settings, which is usually unrealistic in practical application. (2) Iterative optimization for the generation of adversarial examples in them results in heavy computation. To address these problems, we propose an Efficient Query-based Black-Box Attack (EQB 2 A) against deep cross-modal hashing retrieval, which can efficiently generate adversarial examples for the black-box attack. Specifically, by sending a few query requests to the attacked retrieval system, the cross-modal retrieval model stealing is performed based on the neighbor relationship between the retrieved results and the query, thus obtaining the knockoffs to substitute the attacked system. A multi-modal knockoffs-driven adversarial generation is proposed to achieve efficient adversarial example generation. While the entire network training converges, EQB 2 A can efficiently generate adversarial examples by forward-propagation with only given benign images. Experiments show that EQB 2 A achieves superior attacking performance under the black-box setting.

Cross-domain recommendation aims to exploit heterogeneous information from a data-sufficient domain (source domain) to transfer knowledge to a data-scarce domain (target domain). A majority of existing methods focus on unidirectional transfer that leverages the domain-shared information to facilitate the recommendation of the target domain. Nevertheless, it is more beneficial to improve the recommendation performance of both domains simultaneously via a dual transfer learning schema, which is known as bidirectional cross-domain recommendation (BCDR). Existing BCDR methods have their limitations, since they only perform bidirectional transfer learning based on domain-shared representations while neglecting rich information that is private to each domain. In this article, we argue that users may have domain-biased preferences due to the characteristics of that domain. Namely, the domain-specific preference information also plays a critical role in the recommendation. To effectively leverage the domain-specific information, we propose a M ulti-level A ttention-based D omain D isentanglement framework dubbed MADD for BCDR, which explicitly leverages the attention mechanism to construct personalized preference with both domain-invariant and domain-specific features obtained by disentangling raw user embeddings. Specifically, the domain-invariant feature is exploited by domain-adversarial learning while the domain-specific feature is learned by imposing an orthogonal loss. We then conduct a reconstruction process on disentangled features to ensure semantic-sufficiency. After that, we devise a multi-level attention mechanism for these disentangled features, which determines their contributions to the final personalized user preference embedding by dynamically learning the attention scores of individual features. We train the model in a multi-task learning fashion to benefit both domains. Extensive experiments on real-world datasets demonstrate that our model significantly outperforms state-of-the-art cross-domain recommendation approaches.

Generalized zero-shot learning (GZSL) aims to recognize samples whose categories may not have been seen at training. Recognizing unseen classes as seen ones or vice versa often leads to poor performance in GZSL. Therefore, distinguishing seen and unseen domains is naturally an effective yet challenging solution for GZSL. In this paper, we present a novel method which leverages both visual and semantic modalities to distinguish seen and unseen categories. Specifically, our method deploys two variational autoencoders to generate latent representations for visual and semantic modalities in a shared latent space, in which we align latent representations of both modalities by Wasserstein distance and reconstruct two modalities with the representations of each other. In order to learn a clearer boundary between seen and unseen classes, we propose a two-stage training strategy which takes advantage of seen and unseen semantic descriptions and searches a threshold to separate seen and unseen visual samples. At last, a seen expert and an unseen expert are used for final classification. Extensive experiments on five widely used benchmarks verify that the proposed method can significantly improve the results of GZSL. For instance, our method correctly recognizes more than 99% samples when separating domains and improves the final classification accuracy from 72.6% to 82.9% on AWA1.

Multi-view clustering has attracted more attention recently since many real-world data are comprised of different representations or views. Recent multi-view clustering works mainly exploit the instance consistency to obtain the shared representations across different views, and apply a single-view clustering method to perform data partitions. However, these existing methods often ignore the inconsistency of instance associations within the views, which may enlarge the intra-class diversity among the views and therefore degrade the clustering performance. To address this issue, this paper proposes an efficient mutual contrastive teacher-student leaning (MC-TSL) model to enhance the multi-view clustering, which is the first attempt to study the inconsistency distillation for consistency learning. First, the proposed MC-TSL approach exploits a view-specific encoder with two heads, an instance encoding head and a semantic distillation head, respectively, for capturing the consistent and discriminative feature representations. To be specific, the former head exploits a cross-view contrastive learning method to obtain a redundancy-free consistent representation at the instance level, while the latter head designs a mutual teacher-student learning module to capture the intra-view information at semantic level. By training these two heads in an end-to-end manner, the discriminative multi-view embeddings are efficiently obtained and refined by minimizing the weighted sum of the reconstruction loss, contrastive loss and contrast distillation loss. Extensive experiments verify the superiorities of the proposed MC-TSL framework and show its competitive clustering performances.

One compelling application of artificial intelligence is to generate a video of a target person performing arbitrary desired motion (from a source person). While the state-of-the-art methods are able to synthesize a video demonstrating similar broad stroke motion details, they are generally lacking in texture details. A pertinent manifestation appears as distorted face, feet, and hands, and such flaws are very sensitively perceived by human observers. Furthermore, current methods typically employ GANs with a L2 loss to assess the authenticity of the generated videos, inherently requiring a large amount of training samples to learn the texture details for adequate video generation. In this work, we tackle these challenges from three aspects: 1) We disentangle each video frame into foreground (the person) and background, focusing on generating the foreground to reduce the underlying dimension of the network output. 2) We propose a theoretically motivated Gromov-Wasserstein loss that facilitates learning the mapping from a pose to a foreground image. 3) To enhance texture details, we encode facial features with geometric guidance and employ local GANs to refine the face, feet, and hands. Extensive experiments show that our method is able to generate realistic target person videos, faithfully copying complex motions from a source person. Our code and datasets are released at https://github.com/Sifann/FakeMotion.

Recent studies have verified the success of deep hashing for efficient image retrieval. However, most existing methods require abundant human labeling data to optimize the large number of involved network parameters, which consequently restricts the scalability of deep image hashing. Alternatively, learning from freely available web images that inherently include rich semantics is a promising strategy. Nevertheless, the domain distribution gap will prevent transferring the semantics involved in the source web images to the target images. Besides, most existing deep image hashing methods suffer from excessive training time to achieve satisfactory performance without explicit supervision. How to efficiently train the deep image hashing network is another important problem that needs to be seriously considered. In this paper, we propose a Webly Supervised Image Hashing (WSIH) with a well-designed lightweight network. Our model enhances the semantics of unsupervised image hashing with the weak supervision from freely available web images, and simultaneously avoids involving over-abundant parameters in the deep network architecture. Particularly, we train a concept prototype learning network on the web images, learning well-trained network parameters and the prototype codes that hold the discriminative semantics of the potential visual concepts in target images. Further, we meticulously design a lightweight siamese network architecture and a dual-level transfer mechanism to efficiently translate the semantics learned from source web images to the target images. Experiments on two widely-tested image datasets show the superiority of the proposed method in both retrieval accuracy and training efficiency compared to state-of-the-art image hashing methods.The source codes of our method are available at: https://github.com/christinecui/WSIH.

With various unforeseeable face presentation attacks (PA) springing up, face anti-spoofing (FAS) urgently needs to generalize to unseen scenarios. Research on generalizable FAS has lately attracted growing attention. Existing methods cast FAS as a vanilla binary classification problem and address it by a standard discriminative classifier p(y|x) under a domain generalization framework. However, discriminative models are unreliable for samples far away from the training distribution. In this paper, we resort to an energy-based model (EBM) to tackle FAS in a generative perspective. Our motivation is to model the joint density p(x,y), which allows to compute not only p(y|x) but also p(x). Due to the intractability of direct modeling, we use EBMs as an alternative to probabilistic estimation. With energy-based training, real faces are encouraged to get low free energy associated with the marginal probability p(x) of real faces, and all samples with high free energy are regarded as fake faces, thus rejecting any kind of PA out of the distribution of real faces. To learn to generalize to unseen domains, we generate diverse and novel populations in feature space under the guidance of energy model. Our model is updated in a meta-learning schema, where the original source samples are utilized for meta-training and the generated ones for meta-testing. We validate our method on four widely used FAS datasets. Comprehensive experimental results demonstrate the effectiveness of our method compared with state-of-the-arts.

Unsupervised domain adaptation (UDA) aims at transferring knowledge from one labeled source domain to a related but unlabeled target domain. Recently, active domain adaptation (ADA) has been proposed as a new paradigm which significantly boosts performance of UDA with minor additional labeling. However, existing ADA methods require source data to explicitly measure the domain gap between the source domain and the target domain, which is restricted in many real-world scenarios. In this work, we handle ADA with only a source-pretrained model and unlabeled target data, proposing a new setting named source-free active domain adaptation. Specifically, we propose a Locality Preserving Transfer (LPT) framework which preserves and utilizes locality structures on target data to achieve adaptation without source data. Meanwhile, a label propagation strategy is adopted to improve the discriminability for better adaptation. After LPT, unique samples with insignificant locality structure are identified by an energy-based approach for active annotation. An energy-based pseudo labeling strategy is further applied to generate labels for reliable samples. Finally, with supervision from the annotated samples and pseudo labels, a well adapted model is obtained. Extensive experiments on three widely used UDA benchmarks show that our method is comparable or superior to current state-of-the-art active domain adaptation methods even without access to source data.

Unsupervised Domain Adaptation (UDA) has been shown to alleviate the heavy annotations for semantic segmentation. Recently, numerous self-training approaches are proposed to address the challenging cross-domain semantic segmentation problem. However, there still exists two open issues: (1) The generated pseudo-labels are inevitably noisy without external supervision. (2) These is a performance gap between UDA models and the fully-supervised model. In this paper, we propose to investigate Active Learning (AL) that selects a small portion of unlabeled pixels (or images) to be annotated, which leads to an impressive performance gain. Specifically, we propose a novel Uncertainty-aware Boundary Discovery (UBD) strategy that selects the uncertain pixels in the boundary areas that contains rich contextual information. Technically, we firstly select the pixels with top entropy values, and then re-select the pixels that are exclusive to their neighbors. We leverage the Kullback-Leibler divergence between one pixel's softmax prediction and its neighbors' to measure its "exclusivity". Extensive experiments show that our approach outperforms previous methods with both pixel-level and image-level label acquisition protocols.

Multi-modal hashing learns binary hash codes with extremely low storage cost and high retrieval speed. It can support efficient multi-modal retrieval well. However, most existing methods still suffer from three important problems: 1) Limited semantic representation capability with shallow learning. 2) Mandatory feature-level multi-modal fusion ignores heterogeneous multi-modal semantic gaps. 3) Direct coarse pairwise semantic preserving cannot effectively capture the fine-grained semantic correlations. For solving these problems, in this paper, we propose a Bit-aware Semantic Transformer Hashing (BSTH) framework to excavate bit-wise semantic concepts and simultaneously align the heterogeneous modalities for multi-modal hash learning on the concept-level. Specifically, the bit-wise implicit semantic concepts are learned with the transformer in a self-attention manner, which can achieve implicit semantic alignment on the fine-grained concept-level and reduce the heterogeneous modality gaps. Then, the concept-level multi-modal fusion is performed to enhance the semantic representation capability of each implicit concept and the fused concept representations are further encoded to the corresponding hash bits via bit-wise hash functions. Further, to supervise the bit-aware transformer module, a label prototype learning module is developed to learn prototype embeddings for all categories that capture the explicit semantic correlations on the category-level by considering the co-occurrence priors. Experiments on three widely tested multi-modal retrieval datasets demonstrate the superiority of the proposed method from various aspects.

Conventional machine learning algorithms suffer the problem that the model trained on existing data fails to generalize well to the data sampled from other distributions. To tackle this issue, unsupervised domain adaptation (UDA) transfers the knowledge learned from a well-labeled source domain to a different but related target domain where labeled data is unavailable. The majority of existing UDA methods assume that data from the source domain and the target domain are available and complete during training. Thus, the divergence between the two domains can be formulated and minimized. In this paper, we consider a more practical yet challenging UDA setting where either the source domain data or the target domain data are unknown. Conventional UDA methods would fail this setting since the domain divergence is agnostic due to the absence of the source data or the target data. Technically, we investigate UDA from a novel view-adversarial attack-and tackle the divergence-agnostic adaptive learning problem in a unified framework. Specifically, we first report the motivation of our approach by investigating the inherent relationship between UDA and adversarial attacks. Then we elaborately design adversarial examples to attack the training model and harness these adversarial examples. We argue that the generalization ability of the model would be significantly improved if it can defend against our attack, so as to improve the performance on the target domain. Theoretically, we analyze the generalization bound for our method based on domain adaptation theories. Extensive experimental results on multiple UDA benchmarks under conventional, source-absent and target-absent UDA settings verify that our method is able to achieve a favorable performance compared with previous ones. Notably, this work extends the scope of both domain adaptation and adversarial attack, and expected to inspire more ideas in the community.

In recent years, remarkable progress in zero-shot learning (ZSL) has been achieved by generative adversarial networks (GAN). To compensate for the lack of training samples in ZSL, a surge of GAN architectures have been developed by human experts through trial-and-error testing. Despite their efficacy, however, there is still no guarantee that these hand-crafted models can consistently achieve good performance across diversified datasets or scenarios. Accordingly, in this paper, we turn to neural architecture search (NAS) and make the first attempt to bring NAS techniques into the ZSL realm. Specifically, we propose a differentiable GAN architecture search method over a specifically designed search space for zero-shot learning, referred to as ZeroNAS. Considering the relevance and balance of the generator and discriminator, ZeroNAS jointly searches their architectures in a min-max player game via adversarial training. Extensive experiments conducted on four widely used benchmark datasets demonstrate that ZeroNAS is capable of discovering desirable architectures that perform favorably against state-of-the-art ZSL and generalized zero-shot learning (GZSL) approaches. Source code is at https://github.com/caixiay/ZeroNAS.

Label Distribution Learning (LDL) can better describe the real-world data by learning a set of label distributions instead of discrete binary labels. Particularly, hashing-based LDL has achieved promising performance due to its desirable advantages of fast similarity computation and extremely low storage cost. However, existing hashing-based LDL methods are still shallow learning methods, which cannot deeply capture the implicit data semantics, and meanwhile fail to fully model the semantic data relations. In this letter, we propose an effective and efficient Deep Discrete Hashing for Label Distribution Learning (DDH-LDL) method, which develops the first deep hashing framework for LDL. Specifically, DDH-LDL captures implicit semantic information by multi-layer non-linear transformation, and simultaneously preserves the modeled semantic relations of instances into hash codes via semantic message aggregation on Graph Convolutional Network (GCN). Furthermore, we elaborately design a discrete optimization module that is seamlessly integrated into our proposed deep hashing framework to reduce the binary quantization errors. Experiments on several widely tested datasets verify the superiority of the proposed method on both learning accuracy and efficiency.

The completeness of semantic expression plays an important role in cross-modal retrieval tasks, which contributes to align the cross-modal data and thus narrow the modality gap. But due to the abstractness of semantics, the same topic may have different aspects to be well described so it may be incomplete to express semantics with only one sample. In order to obtain semantic complementary information and strengthen similar information for samples with the same semantics, we utilize a graph convolutional network (GCN) to reconstruct the sample representation based on the adjacency relationship between the sample itself and its neighborhoods. We construct a local graph for each instance, and propose a novel Graph Feature Generator based on GCN and a fully-connected network to reconstruct node features based on local graph and map the features of two modalities into a common space. The Graph Feature Generator and Graph Feature Discriminator adopt a minimax game strategy to generate modality-invariant graph feature representations. Experiments on three benchmark datasets demonstrate the superiority of our proposed model compared with several state-of-the-art methods.

In order to carry out more accurate retrieval across image-text modalities, some scholars use fine-grained feature to align image and text. Most of them directly use attention mechanism to align image regions and words in the sentence, and ignore the fact that semantics related to an object is abstract and cannot be accurately expressed by object information alone. To overcome this weakness, we propose a hierarchical feature aggregation algorithm based on graph convolutional networks (GCN) to facilitate object semantic integrity by integrating attributes of an object and relations between objects hierarchically in both image and text modalities. In order to eliminate the semantic gap between modalities, we propose a cross-modal feature fusion method based on transformer to generate modal-specific feature representations by integrating both the object feature and global feature from the other modality. Then we map the fusion feature into a common space. Experiment results on the most frequently-used datasets MSCOCO and Flickr30K show the effectiveness of the proposed model compared with the latest methods.

Zero-shot learning (ZSL) is a pretty intriguing topic in the computer vision community since it handles novel instances and unseen categories. In a typical ZSL setting, there is a main visual space and an auxiliary semantic space. Most existing ZSL methods handle the problem by learning either a visual-to-semantic mapping or a semantic-to-visual mapping. In other words, they investigate a unilateral connection from one end to the other. However, the connection between the visual space and the semantic space are bilateral in reality, that is, the visual space depicts the semantic space; the semantic space, on the other hand, describes the visual space. In this article, therefore, we investigate the bilateral connections in ZSL and present a novel model, called Boomerang-GAN, by taking advantage of conditional generative adversarial networks (GANs). Specifically, we generate unseen visual samples from their category semantic embeddings by a conditional GAN. Different from the existing generative ZSL methods that only consider generating visual features from class descriptions, our method also considers that the generated visual features can be translated back to their corresponding semantic embeddings by introducing a multimodal cycle-consistent loss. Extensive experiments of both ZSL and generalized ZSL on five widely used datasets verify that our method is able to outperform previous state-of-the-art approaches in both recognition and segmentation tasks.

Multi-modal hashing learns compact binary hash codes by collaborating heterogeneous multi-modal features at both the model training and online retrieval stages to support large-scale multimedia retrieval. Previous multi-modal hashing methods mainly focus on supervised and unsupervised hashing. The performance of supervised hashing largely relies on the number of labeled data, which is practically expensive to obtain. Unsupervised hashing methods cannot effectively capture the semantic correlations of multi-modal data without any labels for supervision. In this paper, we propose an Efficient Semi-supervised Multi-modal Hashing with Importance Differentiation Regression (ESMH-IDR) model, which can alleviate the existing problems by learning from both labeled and unlabeled data. Specifically, in this paper, we develop an efficient semi-supervised multi-modal hash code learning module. It learns the hash codes for labeled data in an efficient asymmetric way, and simultaneously performs nonlinear regression using the same projection matrix as the labeled samples to preserve the intrinsic data structure of unlabeled data. Besides, different from existing methods, we propose an importance differentiation regression strategy to learn hash functions by specially considering the different importance of hash codes learned from the labeled and unlabeled samples. Finally, we develop an efficient discrete optimization method guaranteed with convergence to iteratively solve the hash optimization problem. Experiments on several public multimedia retrieval datasets demonstrate the superiority of our proposed method on both retrieval effectiveness and efficiency. Our source codes and testing datasets can be obtained at https://github.com/ChaoqunZheng/ESMH.

Identifying gene-drug interactions is vital to understanding biological mechanisms and achieving precise drug repurposing. High-throughput technologies produce a large amount of pharmacological and genomic data, providing an opportunity to explore the associations between oncogenic genes and therapeutic drugs. However, most studies only focus on "one-to-one" or "one-to-many" interactions, ignoring the multivariate patterns between genes and drugs. In this article, a high-order graph matching model with hypergraph constraints is proposed to discover the gene-drug common regulatory modules. Moreover, the prior knowledge is formulated into hypergraph constraints to reveal their multiple correspondences, penalizing the tensor matching process. The experimental results on the synthetic data demonstrate the proposed model is robust to noise contamination and outlier corruption, achieving a better performance than four state-of-the-art methods. We then evaluate the statistical power of our proposed method on the pharmacogenomics data. Our identified gene-drug common modules not only show significantly enriched pathways associated with cancer but also manifest the highly close gene-drug interactions.

It is widely acknowledged that the success of deep learning is built upon large-scale training data and tremendous computing power. However, the data and computing power are not always available for many real-world applications. In this paper, we address the machine learning problem where it lacks training data and limits computing power. Specifically, we investigate domain adaptation which is able to transfer knowledge from one labeled source domain to an unlabeled target domain, so that we do not need much training data from the target domain. At the same time, we consider the situation that the running environment is confined, e.g., in edge computing the end device has very limited running resources. Technically, we present the Faster Domain Adaptation (FDA) protocol and further report two paradigms of FDA: early stopping and amid skipping. The former accelerates domain adaptation by multiple early exit points. The latter speeds up the adaptation by wisely skip several amid neural network blocks. Extensive experiments on standard benchmarks verify that our method is able to achieve the comparable and even better accuracy but employ much less computing resources. To the best of our knowledge, there are very few works which investigated accelerating knowledge adaptation in the community. This work is expected to inspire the topic for more discussion.

As important side information, attributes have been widely exploited in the existing recommender system for better performance. However, in the real-world scenarios, it is common that some attributes of items/users are missing (e.g., some movies miss the genre data). Prior studies usually use a default value (i.e., “other”) to represent the missing attribute, resulting in sub-optimal performance. To address this problem, in this paper, we present an attribute-aware attentive graph convolution network (A${^2}$-GCN). In particular, we first construct a graph, where users, items, and attributes are three types of nodes and their associations are edges. Thereafter, we leverage the graph convolution network to characterize the complicated interactions among$<$users, items, attributes$>$. Furthermore, to learn the node representation, we adopt the message-passing strategy to aggregate the messages passed from the other directly linked types of nodes (e.g., a user or an attribute). Towards this end, we are capable of incorporating associate attributes to strengthen the user and item representation learning, and thus naturally solve the attribute missing problem. Given that for different users, the attributes of an item have different influence on their preference to this item, we design a novel attention mechanism to filter the message passed from an item to a target user by considering the attribute information. Extensive experiments have been conducted on several publicly accessible datasets to justify our model, demonstrating that our model outperforms several state-of-the-art methods and demonstrate the effectiveness of our attention method.

Due to its powerful capability of representation learning and efficient computation, deep hashing has made significant progress in large-scale image retrieval. It has been recognized that deep neural networks are vulnerable to adversarial examples, which is a practical secure problem but seldom studied in deep hashing-based retrieval field. In this paper, we propose a novel prototype-supervised adversarial network (ProS-GAN), which formulates a flexible generative architecture for efficient and effective targeted hashing attack.To the best of our knowledge, this is one of the first generation-based methods to attack deep hashing networks. Generally, our proposed framework consists of three parts,i.e., a PrototypeNet, a Generator and a Discriminator. Specifically, the designed PrototypeNet embeds the target label into the semantic representation and learns the prototype code as the category-level representative of the target label. Moreover, the semantic representation and the original image are jointly fed into the generator for flexible targeted attack. Particularly, the prototype code is adopted to supervise the generator to construct the targeted adversarial example by minimizing the Hamming distance between the hash code of the adversarial example and the prototype code. Furthermore, the generator fools the discriminator to simultaneously encourage the adversarial examples visually realistic and the semantic representation informative. Extensive experiments demonstrate that the proposed framework can efficiently produce adversarial examples with better targeted attack performance and transferability over state-of-the-art targeted attack methods of deep hashing. The source code is available athttps://github.com/xunguangwang/ProS-GAN_Trans.

Domain adaptation is proposed to deal with the challenging problem where the probability distribution of the training source is different from the testing target. Recently, adversarial learning has become the dominating technique for domain adaptation. Usually, adversarial domain adaptation methods simultaneously train a feature learner and a domain discriminator to learn domain-invariant features. Accordingly, how to effectively train the domain-adversarial model to learn domain-invariant features becomes a challenge in the community. To this end, we propose in this article a novel domain adaptation scheme named adversarial entropy optimization (AEO) to address the challenge. Specifically, we minimize the entropy when samples are from the independent distributions of source domain or target domain to improve the discriminability of the model. At the same time, we maximize the entropy when features are from the combined distribution of source domain and target domain so that the domain discriminator can be confused and the transferability of representations can be promoted. This minimax regime is well matched with the core idea of adversarial learning, empowering our model with transferability as well as discriminability for domain adaptation tasks. Also, AEO is flexible and compatible with different deep networks and domain adaptation frameworks. Experiments on five data sets show that our method can achieve state-of-the-art performance across diverse domain adaptation tasks.

Multi-modal hashing supports efficient multimedia retrieval well. However, existing methods still suffer from two problems: (1) Fixed multi-modal fusion. They collaborate the multi-modal features with fixed weights for hash learning, which cannot adaptively capture the variations of online streaming multimedia contents. (2) Binary optimization challenge. To generate binary hash codes, existing methods adopt either two-step relaxed optimization that causes significant quantization errors or direct discrete optimization that consumes considerable computation and storage cost. To address these problems, we first propose a Supervised Multi-modal Hashing with Online Query-adaption method. A self-weighted fusion strategy is designed to adaptively preserve the multi-modal features into hash codes by exploiting their complementarity. Besides, the hash codes are efficiently learned with the supervision of pair-wise semantic labels to enhance their discriminative capability while avoiding the challenging symmetric similarity matrix factorization. Further, we propose an efficient Unsupervised Multi-modal Hashing with Online Query-adaption method with an adaptive multi-modal quantization strategy. The hash codes are directly learned without the reliance on the specific objective formulations. Finally, in both methods, we design a parameter-free online hashing module to adaptively capture query variations at the online retrieval stage. Experiments validate the superiority of our proposed methods.

Venue categories used in location-based social networks often exhibit a hierarchical structure, together with the category sequences derived from users’ check-ins. The two data modalities provide a wealth of information for us to capture the semantic relationships between those categories. To understand the venue semantics, existing methods usually embed venue categories into low-dimensional spaces by modeling the linear context (i.e., the positional neighbors of the given category) in check-in sequences. However, the hierarchical structure of venue categories, which inherently encodes the relationships between categories, is largely untapped. In this article, we propose a venue C ategory E mbedding M odel named Hier-CEM , which generates a latent representation for each venue category by embedding the Hier archical structure of categories and utilizing multiple types of context. Specifically, we investigate two kinds of hierarchical context based on any given venue category hierarchy and show how to model them together with the linear context collaboratively. We apply Hier-CEM to three tasks on two real check-in datasets collected from Foursquare. Experimental results show that Hier-CEM is better at capturing both semantic and sequential information inherent in venues than state-of-the-art embedding methods.

Item-based collaborative filtering (ICF) enjoys the advantages of high recommendation accuracy and ease in online penalization and thus is favored by the industrial recommender systems. ICF recommends items to a target user based on their similarities to the previously interacted items of the user. Great progresses have been achieved for ICF in recent years by applying advanced machine learning techniques (e.g., deep neural networks) to learn the item similarity from data. The early methods simply treat all the historical items equally and recently proposed methods attempt to distinguish the different importance of historical items when recommending a target item. Despite the progress, we argue that those ICF models neglect the diverse intents of users on adopting items (e.g., watching a movie because of the director, leading actors, or the visual effects). As a result, they fail to estimate the item similarity on a finer-grained level to predict the user’s preference to an item, resulting in sub-optimal recommendation. In this work, we propose a general feature-level attention method for ICF models. The key of our method is to distinguish the importance of different factors when computing the item similarity for a prediction. To demonstrate the effectiveness of our method, we design a light attention neural network to integrate both item-level and feature-level attention for neural ICF models. It is model-agnostic and easy-to-implement. We apply it to two baseline ICF models and evaluate its effectiveness on six public datasets. Extensive experiments show the feature-level attention enhanced models consistently outperform their counterparts, demonstrating the potential of differentiating user intents on the feature-level for ICF recommendation models.

Deep hashing has great potential in large-scale visual similarity search due to its preferable efficiency in storage and computation. Technically, deep hashing for visual similarity search inherits the powerful representation capability of deep neural networks, and it encodes visual features into compact binary codes by preserving representative semantic visual features. Works in this field mainly focus on building the relationship between the visual and objective hash spaces, while they seldom study the triadic cross-domain semantic knowledge transfer among visual, semantic, and hashing spaces, leading to a serious semantic ignorance problem during space transformation. In this article, we propose a novel deep tripartite semantically interactive hashing framework, dubbed Semantically Cycle-consistent Hashing Networks (SCHNs), for discriminative hash code learning. Particularly, we construct a flexible semantic space and a transitive latent space, in conjunction with the visual space, to jointly deduce the privileged discriminative hash space. Specifically, a new semantic space is conceived to strengthen the flexibility and completeness of categories in the semantic feature inference phase. At the same time, a transitive latent space is formulated to explore and uncover the shared semantic interactivity embedded in visual and semantic features. Moreover, to further ensure semantic consistency across multiple spaces, we propose to build a cyclic adversarial learning module to preserve and keep their semantic concurrence during space transformation. Notably, our SCHN, for the first time, establishes the cyclic principle of deep semantic-preserving hashing by adaptive semantic parsing across different spaces in a single-modal visual similarity search. In addition, the entire learning framework is jointly optimized in an end-to-end manner. Extensive experiments performed on diverse large-scale datasets evidence the superiority of our method against other state-of-the-art deep hashing algorithms. The source codes of this article are available at https://github.com/JalinWang/SCHN.

Crowd emotional contagion is affected by physical cyberspace and virtual cyberspace at the same time. In addition, the individual personality also plays an important role in crowd emotional contagion. However, few existing works have investigated the two factors jointly. To solve this problem, we propose a personalized virtual and physical cyberspace-based emotional contagion model (PVP-ECM) to simulate the process of crowd emotional contagion. First, we construct an individual emotion model and propose the personalized emotional contagion rules to consider the influences of the individual personality on crowd emotional contagion coupling the virtual and physical cyberspaces. Second, we use mean field theory to derive an evolution process and obtain mean field equations for the PVP-ECM. Then, we solve the PVP-ECM numerically using the finite difference method. Third, we construct a personalized BA scale-free network for the PVP-ECM simulation to further verify the stability of the model. Finally, we perform the PVP-ECM simulation and implement a simulation system to visualize the results of our theoretical analysis. The experimental results show that our approach can simulate the process of crowd emotional contagion more realistically. The proposed method can provide guidance for coping with the personalized crowd emotional contagion of public emergencies.

In this paper, we propose a novel method, referred to as incomplete multi-view tensor spectral clustering with missing-view inferring (IMVTSC-MVI) to address the challenging multi-view clustering problem with missing views. Different from the existing methods which commonly focus on exploring the certain information of the available views while ignoring both of the hidden information of the missing views and the intra-view information of data, IMVTSC-MVI seeks to recover the missing views and explore the full information of such recovered views and available views for data clustering. In particular, IMVTSC-MVI incorporates the feature space based missing-view inferring and manifold space based similarity graph learning into a unified framework. In such a way, IMVTSC-MVI allows these two learning tasks to facilitate each other and can well explore the hidden information of the missing views. Moreover, IMVTSC-MVI introduces the low-rank tensor constraint to capture the high-order correlations of multiple views. Experimental results on several datasets demonstrate the effectiveness of IMVTSC-MVI for incomplete multi-view clustering.

Open Set Domain Adaptation (OSDA) is a challenging domain adaptation setting which allows the existence of unknown classes on the target domain. Although existing OSDA methods are good at classifying samples of known classes, they ignore the classification ability for the unknown samples, making them unbalanced OSDA methods. To alleviate this problem, we propose a balanced OSDA methods which could recognize the unknown samples while maintain high classification performance for the known samples. Specifically, to reduce the domain gaps, we first project the features to a hyperspherical latent space. In this space, we propose to bound the centroid deviation angles to not only increase the intra-class compactness but also enlarge the inter-class margins. With the bounded centroid deviation angles, we employ the statistical Extreme Value Theory to recognize the unknown samples that are misclassified into known classes. In addition, to learn better centroids, we propose an improved centroid update strategy based on sample reweighting and adaptive update rate to cooperate with centroid alignment. Experimental results on three OSDA benchmarks verify that our method can significantly outperform the compared methods and reduce the proportion of the unknown samples being misclassified into known classes.

Unsupervised Domain Adaptation (UDA) aims to generalize the knowledge learned from a well-labeled source domain to an unlabled target domain. Recently, adversarial domain adaptation with two distinct classifiers (biclassifier) has been introduced into UDA which is effective to align distributions between different domains. Previous bi-classifier adversarial learning methods only focus on the similarity between the outputs of two distinct classifiers. However, the similarity of the outputs cannot guarantee the accuracy of target samples, i.e., traget samples may match to wrong categories even if the discrepancy between two classifiers is small. To challenge this issue, in this paper, we propose a cross-domain gradient discrepancy minimization (CGDM) method which explicitly minimizes the discrepancy of gradients generated by source samples and target samples. Specifically, the gradient gives a cue for the semantic information of target samples so it can be used as a good supervision to improve the accuracy of target samples. In order to compute the gradient signal of target smaples, we further obtain target pseudo labels through a clustering-based self-supervised learning. Extensive experiments on three widely used UDA datasets show that our method surpasses many previous state-of-the-arts.

Shared-account Cross-domain Sequential Recommendation (SCSR) is the task of recommending the next item based on a sequence of recorded user behaviors, where multiple users share a single account, and their behaviours are available in multiple domains. Existing work on solving SCSR mainly relies on mining sequential patterns via RNN-based models, which are not expressive enough to capture the relationships among multiple entities. Moreover, all existing algorithms try to bridge two domains via knowledge transfer in the latent space, and the explicit cross-domain graph structure is unexploited. In this work, we propose a novel graph-based solution, namely DA-GCN, to address the above challenges. Specifically, we first link users and items in each domain as a graph. Then, we devise a domain-aware graph convolution network to learn user-specific node representations. To fully account for users' domain-specific preferences on items, two novel attention mechanisms are further developed to selectively guide the message passing process. Extensive experiments on two real-world datasets are conducted to demonstrate the superiority of our DA-GCN method.

Smart contracts hold digital coins worth billions of dollars, their security issues have drawn extensive attention in the past years. Towards smart contract vulnerability detection, conventional methods heavily rely on fixed expert rules, leading to low accuracy and poor scalability. Recent deep learning approaches alleviate this issue but fail to encode useful expert knowledge. In this paper, we explore combining deep learning with expert patterns in an explainable fashion. Specifically, we develop automatic tools to extract expert patterns from the source code. We then cast the code into a semantic graph to extract deep graph features. Thereafter, the global graph feature and local expert patterns are fused to cooperate and approach the final prediction, while yielding their interpretable weights. Experiments are conducted on all available smart contracts with source code in two platforms, Ethereum and VNT Chain. Empirically, our system significantly outperforms state-of-the-art methods. Our code is released.

Hashing learns compact binary codes to store and retrieve massive data efficiently. Particularly, unsupervised deep hashing is supported by powerful deep neural networks and has the desirable advantage of label independence. It is a promising technique for scalable image retrieval. However, deep models introduce a large number of parameters, which is hard to optimize due to the lack of explicit semantic labels and brings considerable training cost. As a result, the retrieval accuracy and training efficiency of existing unsupervised deep hashing are still limited. To tackle the problems, in this paper, we propose a simple and efficient Lightweight Augmented Graph Network Hashing (LAGNH) method with a two-pronged strategy. For one thing, we extract the inner structure of the image as the auxiliary semantics to enhance the semantic supervision of the unsupervised hash learning process. For another, we design a lightweight network structure with the assistance of the auxiliary semantics, which greatly reduces the number of network parameters that needs to be optimized and thus greatly accelerates the training process. Specifically, we design a cross-modal attention module based on the auxiliary semantic information to adaptively mitigate the adverse effects in the deep image features. Besides, the hash codes are learned by multi-layer message passing within an adversarial regularized graph convolutional network. Simultaneously, the semantic representation capability of hash codes is further enhanced by reconstructing the similarity graph. Experimental results show that our method achieves significant performance improvement compared with the state-of-the-art unsupervised deep hashing methods in terms of both retrieval accuracy and efficiency. Notably, on MS-COCO dataset, our method achieves more than 10% improvement on retrieval precision and 2.7x speedup on training time compared with the second best result.

Conventional machine learning models are often vulnerable to samples with different distributions from the ones of training samples, which is known as domain shift. Domain Generalization (DG) challenges this issue by training a model based on multiple source domains and generalizing it to arbitrary unseen target domains. In spite of remarkable results made in DG, a majority of existing works lack a deep understanding of the feature representations learned in DG models, resulting in limited generalization ability when facing domainsout-of-distribution. In this paper, we aim to learn a domain transformation space via a domain transformer network (DTN) which explicitly mines the relationship among multiple domains and constructs transferable feature representations for down-stream tasks by interpreting each feature as a semantically weighted combination of multiple domain-specific features. Our DTN is encouraged to meta-learn the properties and characteristics of domains during the training process based on multiple seen domains, making transformed feature representations more semantical, thus generalizing better to unseen domains. Once the model is constructed, the feature representations of unseen target domains can also be inferred adaptively by selectively combining the feature representations from the diverse set of seen domains. We conduct extensive experiments on five DG benchmarks and the results strongly demonstrate the effectiveness of our approach.

Cross-domain Facial Expression Recognition (FER) is challenging due to the difficulty of concurrently handling the domain shift and semantic gap during domain adaptation. Existing methods mainly focus on reducing the domain discrepancy for transferable features but fail to decrease the semantic one, which may result in negative transfer. To this end, we propose Joint Discriminative and Mutual Adaptation Networks (JDMAN), which collaboratively bridge the domain shift and semantic gap by domain- and category-level co-adaptation based on mutual information and discriminative metric learning techniques. Specifically, we design a mutual information minimization module for domain-level adaptation, which narrows the domain shift by simultaneously distilling the domain-invariant components and eliminating the untransferable ones lying in different domains. Moreover, we propose a semantic metric learning module for category-level adaptation, which can close the semantic discrepancy during discriminative intra-domain representation learning and transferable inter-domain knowledge discovery. These two modules are jointly leveraged in our JDMAN to safely transfer the source knowledge to target data in an end-to-end manner. Extensive experimental results on six databases show that our method achieves state-of-the-art performance. The code of our JDMAN is available at https://github.com/YingjianLi/JDMAN.

Conventional Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a well-labeled source domain to an unlabeled target domain only when data from both domains is simultaneously accessible, which is challenged by the recent Source-free Domain Adaptation (SFDA). However, we notice that the performance of existing SFDA methods would be dramatically degraded by intra-domain class imbalance and inter-domain label shift. Unfortunately, class-imbalance is a common phenomenon in real-world domain adaptation applications. To address this issue, we present Imbalanced Source-free Domain Adaptation (ISFDA) in this paper. Specifically, we first train a uniformed model from the source domain, and then propose secondary label correction, curriculum sampling, plus intra-class tightening and inter-class separation to overcome the joint presence of covariate shift and label shift. Extensive experiments on three imbalanced benchmarks verify that ISFDA could perform favorably against existing UDA and SFDA methods under various conditions of class-imbalance, and outperform existing SFDA methods by over 15% in terms of per-class average accuracy on a large-scale long-tailed imbalanced dataset.

Multi-modal hashing makes an important contribution to multimedia retrieval, where a key challenge is to encode heterogeneous modalities into compact hash codes. To solve this dilemma, graph-based multi-modal hashing methods generally define individual affinity matrix of each independent modality and apply linear algorithm for heterogeneous modalities fusion and compact hash learning. Several other methods construct graph Laplacian matrix based on semantic information to help learn discriminative hash code. However, these conventional methods roughly ignore the structural similarity of training set and the complex relations among multi-modal samples, which leads to unsatisfactory complementarity of fused hash codes. More notably, they are faced with two other important problems: huge computing and storage costs caused by graph construction and partial modality feature lost problem when incomplete query sample comes. In this paper, we propose a Flexible Graph Convolutional Multi-modal Hashing (FGCMH) method that adopts GCNs with linear complexity to preserve both the modality-individual and modality-fused structural similarity for discriminative hash learning. Necessarily, accurate multimedia retrieval can be performed on complete and incomplete datasets with our method. Specifically, multiple modality-individual GCNs under semantic guidance are proposed to act on each individual modality independently for intra-modality similarity preserving, then the output representations are fused into a fusion graph with adaptive weighting scheme. Hash GCN and semantic GCN, which share parameters in the first two layers, propagate fusion information and generate hash codes under high-level label space supervision. In the query stage, our method adaptively captures various multi-modal contents in a flexible and robust way, even if partial modality features are lost. Experimental results on three publicly datasets show the flexibility and effectiveness of our proposed method.

Motion prediction is a classic problem in computer vision, which aims at forecasting future motion given the observed pose sequence. Various deep learning models have been proposed, achieving state-of-the-art performance on motion prediction. However, existing methods typically focus on modeling temporal dynamics in the pose space. Unfortunately, the complicated and high dimensionality nature of human motion brings inherent challenges for dynamic context capturing. Therefore, we move away from the conventional pose based representation and present a novel approach employing a phase space trajectory representation of individual joints. Moreover, current methods tend to only consider the dependencies between physically connected joints. In this paper, we introduce a novel convolutional neural model to effectively leverage explicit prior knowledge of motion anatomy, and simultaneously capture both spatial and temporal information of joint trajectory dynamics. We then propose a global optimization module that learns the implicit relationships between individual joint features. Empirically, our method is evaluated on large-scale 3D human motion benchmark datasets (i.e., Human3.6M, CMU MoCap). These results demonstrate that our method sets the new state-of-the-art on the benchmark datasets. Our code is released at https://github.com/Pose-Group/TEID.

Domain adaptive semantic segmentation is recognized as a promising technique to alleviate the domain shift between the labeled source domain and the unlabeled target domain in many real-world applications, such as automatic pilot. However, large amounts of source domain data often introduce significant costs in storage and training, and sometimes the source data is inaccessible due to privacy policies. To address these problems, we investigate domain adaptive semantic segmentation without source data, which assumes that the model is pre-trained on the source domain, and then adapting to the target domain without accessing source data anymore. Since there is no supervision from the source domain data, many self-training methods tend to fall into the winner-takes-all dilemma, where the majority classes totally dominate the segmentation networks and the networks fail to classify the minority classes. Consequently, we propose an effective framework for this challenging problem with two components: positive learning and negative learning. In positive learning, we select the class-balanced pseudo-labeled pixels with intra-class threshold, while in negative learning, for each pixel, we investigate which category the pixel does not belong to with the proposed heuristic complementary label selection. Notably, our framework can be easily implemented and incorporated with other methods to further enhance the performance. Extensive experiments on two widely-used synthetic-to-real benchmarks demonstrate our claims and the effectiveness of our framework, which outperforms the baseline with a large margin. Code is available at https://github.com/fumyou13/LDBE.

The recommender systems, which merely leverage user-item interactions for user preference prediction (such as the collaborative filtering-based ones), often face dramatic performance degradation when the interactions of users or items are insufficient. In recent years, various types of side information have been explored to alleviate this problem. Among them, knowledge graph (KG) has attracted extensive research interests as it can encode users/items and their associated attributes in the graph structure to preserve the relation information. In contrast, less attention has been paid to the item-item co-occurrence information (i.e., co-view), which contains rich item-item similarity information. It provides information from a perspective different from the user/item-attribute graph and is also valuable for the CF recommendation models. In this work, we make an effort to study the potential of integrating both types of side information (i.e., KG and item-item co-occurrence data) for recommendation. To achieve the goal, we propose a unified graph-based recommendation model (UGRec), which integrates the traditional directed relations in KG and the undirected item-item co-occurrence relations simultaneously. In particular, for a directed relation, we transform the head and tail entities into the corresponding relation space to model their relation; and for an undirected co-occurrence relation, we project head and tail entities into a unique hyperplane in the entity space to minimize their distance. In addition, a head-tail relation-aware attentive mechanism is designed for fine-grained relation modeling.

Graph Convolution Networks (GCNs) manifest great potential in recommendation. This is attributed to their capability on learning good user and item embeddings by exploiting the collaborative signals from the high-order neighbors. Like other GCN models, the GCN based recommendation models also suffer from the notorious over-smoothing problem – when stacking more layers, node embeddings become more similar and eventually indistinguishable, resulted in performance degradation. The recently proposed LightGCN and LR-GCN alleviate this problem to some extent, however, we argue that they overlook an important factor for the over-smoothing problem in recommendation, that is, high-order neighboring users with no common interests of a user can be also involved in the user’s embedding learning in the graph convolution operation. As a result, the multi-layer graph convolution will make users with dissimilar interests have similar embeddings. In this paper, we propose a novel Interest-aware Message-Passing GCN (IMP-GCN) recommendation model, which performs high-order graph convolution inside subgraphs. The subgraph consists of users with similar interests and their interacted items. To form the subgraphs, we design an unsupervised subgraph generation module, which can effectively identify users with common interests by exploiting both user feature and graph structure. To this end, our model can avoid propagating negative information from high-order neighbors into embedding learning. Experimental results on three large-scale benchmark datasets show that our model can gain performance improvement by stacking more layers and outperform the state-of-the-art GCN-based recommendation models significantly.

Accurately identifying the interactions between genomic factors and the response of cancer drugs plays important roles in drug discovery, drug repositioning and cancer treatment. A number of studies revealed that interactions between genes and drugs were 'many-genes-to-many drugs' interactions, i.e. common modules, opposed to 'one-gene-to-one-drug' interactions. Such modules fully explain the interactions between complex biological regulatory mechanisms and cancer drugs. However, strategies for effectively and robustly identifying the underlying common modules among pharmacogenomics data remain to be improved. In this paper, we aim to provide a detailed evaluation of three categories of state-of-the-art common module identification techniques from a machine learning perspective, including non-negative matrix factorization (NMF), partial least squares (PLS) and network analyses. We first evaluate the performance of six methods, namely SNMNMF, NetNMF, SNPLS, O2PLS, NSBM and HOGMMNC, using two series of simulated data sets with different noise levels and outlier ratios. Then, we conduct experiments using a real world data set of 2091 genes and 101 drugs in 392 cancer cell lines and compare the real experimental results from the aspect of biological process term enrichment, gene-drug and drug-drug interactions. Finally, we present interesting findings from our evaluation study and discuss the advantages and drawbacks of each method. Supplementary information: Supplementary file is available at Briefings in Bioinformatics online.

Unsupervised domain adaptation addresses the problem of transferring knowledge from a well-labeled source domain to an unlabeled target domain where the two domains have distinctive data distributions. Thus, the essence of domain adaptation is to mitigate the distribution divergence between the two domains. The state-of-the-art methods practice this very idea by either conducting adversarial training or minimizing a metric which defines the distribution gaps. In this paper, we propose a new domain adaptation method named adversarial tight match (ATM) which enjoys the benefits of both adversarial training and metric learning. Specifically, at first, we propose a novel distance loss, named maximum density divergence (MDD), to quantify the distribution divergence. MDD minimizes the inter-domain divergence ("match" in ATM) and maximizes the intra-class density ("tight" in ATM). Then, to address the equilibrium challenge issue in adversarial domain adaptation, we consider leveraging the proposed MDD into adversarial domain adaptation framework. At last, we tailor the proposed MDD as a practical learning loss and report our ATM. Both empirical evaluation and theoretical analysis are reported to verify the effectiveness of the proposed method. The experimental results on four benchmarks, both classical and large-scale, show that our method is able to achieve new state-of-the-art performance on most evaluations.

Recent studies show that hashing technology can achieve efficient similarity searching and many works have been done on supervised deep hash learning. However, under unsupervised scenarios, there are several issues to be solved when learning hashing codes based on visual features for image retrieval and clustering. In this article, we propose a simple but effective Unsupervised Deep K-means Hashing (UDKH) method to simultaneously alleviate the problems of image retrieval and clustering within a single learning framework. UDKH progressively improves the quality of cluster labels and binary hash codes by minimizing pair-wise supervision loss and optimizing the binary K-means to generate discriminative hash codes under the supervision of the learned cluster labels for effective image retrieval. Since the learned hash codes are discriminative, UDKH also improves the image clustering accuracy. Experiments on test datasets demonstrate its effectiveness for image retrieval and clustering.

Social network stores and disseminates a tremendous amount of user shared images. Deep hashing is an efficient indexing technique to support large-scale social image retrieval, due to its deep representation capability, fast retrieval speed and low storage cost. Particularly, unsupervised deep hashing has well scalability as it does not require any manually labelled data for training. However, owing to the lacking of label guidance, existing methods suffer from severe semantic shortage when optimizing a large amount of deep neural network parameters. Differently, in this paper, we propose aDual-level Semantic Transfer Deep Hashing(DSTDH) method to alleviate this problem with a unified deep hash learning framework. Our model targets at learning the semantically enhanced deep hash codes by specially exploiting the user-generated tags associated with the social images. Specifically, we design a complementary dual-level semantic transfer mechanism to efficiently discover the potential semantics of tags and seamlessly transfer them into binary hash codes. On the one hand, instance-level semantics are directly preserved into hash codes from the associated tags with adverse noise removing. Besides, an image-concept hypergraph is constructed for indirectly transferring the latent high-order semantic correlations of images and tags into hash codes. Moreover, the hash codes are obtained simultaneously with the deep representation learning by the discrete hash optimization strategy. Extensive experiments on two public social image retrieval datasets validate the superior performance of our method compared with state-of-the-art hashing methods. The source codes of our method can be obtained athttps://github.com/research2020-1/DSTDH

Domain adaptation is suitable for transferring knowledge learned from one domain to a different but related domain. Considering the substantially large domain discrepancies, learning a more generalized feature representation is crucial for domain adaptation. On account of this, we propose an adaptive component embedding (ACE) method, for domain adaptation. Specifically, ACE learns adaptive components across domains to embed data into a shared domain-invariant subspace, in which the first-order statistics is aligned and the geometric properties are preserved simultaneously. Furthermore, the second-order statistics of domain distributions is also aligned to further mitigate domain shifts. Then, the aligned feature representation is classified by optimizing the structural risk functional in the reproducing kernel Hilbert space (RKHS). Extensive experiments show that our method can work well on six domain adaptation benchmarks, which verifies the effectiveness of ACE.

Social networks allow users to actively upload images and descriptive tags, which has led to an explosive growth in the number of social images. Multi-view hashing is an efficient technique for supporting large-scale social image retrieval because of its desirable capabilities of encoding multi-view features into compact binary hash codes with extremely low storage costs and fast retrieval speeds. However, existing methods require multi-view features to be fully paired at both the offline model training and online query stages. This requirement cannot be easily satisfied for social image retrieval, where social images that lack descriptive tags are common in social networks. In this paper, we propose anUnsupervised Adaptive Partial Multi-view Hashing(UAPMH) method to handle the partial-view hashing problem for efficient social image retrieval. Specifically, the shared and view-specific latent representations of fully paired and partial-view images, respectively, are learned separately by an adaptive partial multi-view matrix factorization module within the identical semantic space. In particular, instead of adopting simple fixed view combination weights, we develop a parameter-free weight learning scheme to adaptively learn the weights to capture the view variations and the discriminative capabilities of different views. With such a design, our model can sufficiently exploit the available partial-view samples with separate hash code learning and effectively preserve the latent relations of images and tags in hash codes with semantic space sharing. Moreover, to avoid relaxing errors and improve the learning efficiency, binary hash codes are directly learned in a fast mode with simple and efficient operations. Finally, we extend UAPMH to the supervised learning paradigm asSupervised Adaptive Partial Multi-view Hashing(SAPMH) with the supervision of pair-wise semantic labels to further enhance the discriminative capability of hash codes. The experiments demonstrate the state-of-the-art performance of the proposed approaches on public social image retrieval datasets. Our source codes and testing datasets can be obtained athttps://github.com/ChaoqunZheng/APMH.

Hashing is an effective technique to address the large-scale recommendation problem, due to its high computation and storage efficiency on calculating the user preferences on items. However, existing hashing-based recommendation methods still suffer from two important problems: 1) Their recommendation process mainly relies on the user-item interactions and single specific content feature. When the interaction history or the content feature is unavailable (the cold-start problem), their performance will be seriously deteriorated. 2) Existing methods learn the hash codes with relaxed optimization or adopt discrete coordinate descent to directly solve binary hash codes, which results in significant quantization loss or consumes considerable computation time. In this paper, we propose a fast cold-start recommendation method, called Multi-Feature Discrete Collaborative Filtering (MFDCF), to solve these problems. Specifically, a low-rank self-weighted multi-feature fusion module is designed to adaptively project the multiple content features into binary yet informative hash codes by fully exploiting their complementarity. Additionally, we develop a fast discrete optimization algorithm to directly compute the binary hash codes with simple operations. Experiments on two public recommendation datasets demonstrate that MFDCF outperforms the state-of-the-arts on various aspects.

Learning the relationship between the multi-modal data, e.g., texts, images and videos, is a classic task in the multimedia community. Cross-modal retrieval (CMR) is a typical example where the query and the corresponding results are in different modalities. Yet, a majority of existing works investigate CMR with an ideal assumption that the training samples in every modality are sufficient and complete. In real-world applications, however, this assumption does not always hold. Mismatch is common in multi-modal datasets. There is a high chance that samples in some modalities are either missing or corrupted. As a result, incomplete CMR has become a challenging issue. In this paper, we propose a Dual-Aligned Variational Autoencoders (DAVAE) to address the incomplete CMR problem. Specifically, we propose to learn modality-invariant representations for different modalities and use the learned representations for retrieval. We train multiple autoencoders, one for each modality, to learn the latent factors among different modalities. These latent representations are further dual-aligned at the distribution level and the semantic level to alleviate the modality gaps and enhance the discriminability of representations. For missing instances, we leverage generative models to synthesize latent representations for them. Notably, we test our method with different ratios of random incompleteness.Extensive experiments on three datasets verify that our method can consistently outperform the state-of-the-arts.

Recently, feature generating methods have been successfully applied to zero-shot learning (ZSL). However, most previous approaches only generate visual representations for zero-shot recognition. In fact, typical ZSL is a classic multi-modal learning protocol which consists of a visual space and a semantic space. In this paper, therefore, we present a new method which can simultaneously generate both visual representations and semantic representations so that the essential multi-modal information associated with unseen classes can be captured. Specifically, we address the most challenging issue in such a paradigm, i.e., how to handle the domain shift and thus guarantee that the learned representations are modality-invariant. To this end, we propose two strategies: 1) leveraging the mutual information between the latent visual representations and the semantic representations; 2) maximizing the entropy of the joint distribution of the two latent representations. By leveraging the two strategies, we argue that the two modalities can be well aligned. At last, extensive experiments on five widely used datasets verify that the proposed method is able to significantly outperform previous the state-of-the-arts.

Unsupervised deep hashing is a promising technique for large-scale image retrieval, as it equips powerful deep neural networks and has advantage on label independence. However, the unsupervised deep hashing process needs to train a large amount of deep neural network parameters, which is hard to optimize when no labeled training samples are provided. How to maintain the well scalability of unsupervised hashing while exploiting the advantage of deep neural network is an interesting but challenging problem to investigate. With the motivation, in this paper, we propose a simple but effective Inter-image Relation Graph Neural Network Hashing (IRGNNH) method. Different from all existing complex models, we discover the latent inter-image semantic relations without any manual labels and exploit them further to assist the unsupervised deep hashing process. Specifically, we first parse the images to extract latent involved semantics. Then, relation graph convolutional network is constructed to model the inter-image semantic relations and visual similarity, which generates representation vectors for image relations and contents. Finally, adversarial learning is performed to seamlessly embed the constructed relations into the image hash learning process, and improve the discriminative capability of the hash codes. Experiments demonstrate that our method significantly outperforms the state-of-the-art unsupervised deep hashing methods on both retrieval accuracy and efficiency.

Unsupervised multi-modal hashing has recently attracted broad attention in research area of large-scale multimedia retrieval for its low storage cost, high retrieval speed, and independence on semantic labels. However, the model learning process of existing methods still suffer from the problem of low efficiency: 1) Many existing methods measure the contributions of different modalities using fixed modality weights. In order to avoid over-fitting, they need an inefficient hyper-parameter adjustment process. 2) Most existing methods adopt inefficient optimization strategies to learn hash codes. In this letter, we propose an unsupervised Efficient Parameter-free Adaptive Multi-modal Hashing (EPAMH) model to adaptively capture the modality variations and preserve the discriminative semantics of multi-modal features into the binary hash codes. Moreover, we directly learn the binary codes with simple and efficient operations, which prevents the relaxing quantization errors and improves the model learning efficiency. Experiments prove the superior performance of EPAMH on three public multimedia retrieval datasets. Our source codes and testing datasets can be obtained at https://github.com/ChaoqunZheng/EPAMH.

Graph-based clustering is one of the major clustering methods. Most of it works in three separate steps: 1) similarity graph construction; 2) clustering label relaxing; and 3) label discretization with k -means (KM). Such common practice has three disadvantages: 1) the predefined similarity graph is often fixed and may not be optimal for the subsequent clustering; 2) the relaxing process of cluster labels may cause significant information loss; and 3) label discretization may deviate from the real clustering result since KM is sensitive to the initialization of cluster centroids. To tackle these problems, in this paper, we propose an effective discrete optimal graph clustering framework. A structured similarity graph that is theoretically optimal for clustering performance is adaptively learned with a guidance of reasonable rank constraints. Besides, to avoid the information loss, we explicitly enforce a discrete transformation on the intermediate continuous label, which derives a tractable optimization problem with a discrete solution. Furthermore, to compensate for the unreliability of the learned labels and enhance the clustering accuracy, we design an adaptive robust module that learns the prediction function for the unseen data based on the learned discrete cluster labels. Finally, an iterative optimization strategy guaranteed with convergence is developed to directly solve the clustering results. Extensive experiments conducted on both real and synthetic datasets demonstrate the superiority of our proposed methods compared with several state-of-the-art clustering approaches.

Recent years have witnessed the wide application of hashing for large-scale image retrieval, because of its high computation efficiency and low storage cost. Particularly, benefiting from current advances in deep learning, supervised deep hashing methods have greatly boosted the retrieval performance, under the strong supervision of large amounts of manually annotated semantic labels. However, their performance is highly dependent upon the supervised labels, which significantly limits the scalability. In contrast, unsupervised deep hashing without label dependence enjoys the advantages of well scalability. Nevertheless, due to the relaxed hash optimization, and more importantly, the lack of semantic guidance, existing methods suffer from limited retrieval performance. In this paper, we propose a SCAlable Deep Hashing (SCADH) to learn enhanced hash codes for social image retrieval. We formulate a unified scalable deep hash learning framework which explores the weak but free supervision of discriminative user tags that are commonly accompanied with social images. It jointly learns image representations and hash functions with deep neural networks, and simultaneously enhances the discriminative capability of image hash codes with the refined semantics from the accompanied social tags. Further, instead of simple relaxed hash optimization, we propose a discrete hash optimization method based on Augmented Lagrangian Multiplier to directly solve the hash codes and avoid the binary quantization information loss. Experiments on two standard social image datasets demonstrate the superiority of the proposed approach compared with stateof- the-art shallow and deep hashing techniques.

Hashing could significantly accelerate large-scale image search by transforming the high-dimensional features into binary Hamming space, where efficient similarity search can be achieved with very fast Hamming distance computation and extremely low storage cost. As an important branch of hashing methods, multi-view hashing takes advantages of multiple features from different views for binary hash learning. However, existing multi-view hashing methods are either based on shallow models which fail to fully capture the intrinsic correlations of heterogeneous views, or unsupervised deep models which suffer from insufficient semantics and cannot effectively exploit the complementarity of view features. In this paper, we propose a novel Deep Collaborative Multi-view Hashing (DCMVH) method to deeply fuse multi-view features and learn multi-view hash codes collaboratively under a deep architecture. DCMVH is a new deep multi-view hash learning framework. It mainly consists of 1) multiple view-specific networks to extract hidden representations of different views, and 2) a fusion network to learn multi-view fused hash code. DCMVH associates different layers with instance-wise and pair-wise semantic labels respectively. In this way, the discriminative capability of representation layers can be progressively enhanced and meanwhile the complementarity of different view features can be exploited effectively. Finally, we develop a fast discrete hash optimization method based on augmented Lagrangian multiplier to efficiently solve the binary hash codes. Experiments on public multi-view image search datasets demonstrate our approach achieves substantial performance improvement over state-of-the-art methods.

Multi-modal hashing methods could support efficient multimedia retrieval by combining multi-modal features for binary hash learning at the both offline training and online query stages. However, existing multi-modal methods cannot binarize the queries, when only one or part of modalities are provided. In this article, we propose a novel Flexible Multi-modal Hashing (FMH) method to address this problem. FMH learns multiple modality-specific hash codes and multi-modal collaborative hash codes simultaneously within a single model. The hash codes are flexibly generated according to the newly coming queries, which provide any one or combination of modality features. Besides, the hashing learning procedure is efficiently supervised by the pair-wise semantic matrix to enhance the discriminative capability. It could successfully avoid the challenging symmetric semantic matrix factorization and O ( n 2 ) storage cost of semantic matrix. Finally, we design a fast discrete optimization to learn hash codes directly with simple operations. Experiments validate the superiority of the proposed approach.

Multi-view hashing can well support large-scale near-duplicate video retrieval, due to its desirable advantages of mutual reinforcement of multiple features, low storage cost, and fast retrieval speed. However, there are still two limitations that impede its performance. First, existing methods only consider local structures in multiple features. They ignore the global structure that is important for near-duplicate video retrieval, and cannot fully exploit the dependence and complementarity of multiple features. Second, existing works always learn hashing functions bit by bit, which unfortunately increases the time complexity of hash function learning. In this paper, we propose a supervised hashing scheme, termed as joint multi-view hashing (JMVH), to address the aforementioned problems. It jointly preserves the global and local structures of multiple features while learning hashing functions efficiently. Specially, JMVH considers features of video as items, based on which an underlying Hamming space is learned by simultaneously preserving their local and global structures. In addition, a simple but efficient multi-bit hash function learning based on generalized eigenvalue decomposition is devised to learn multiple hash functions within a single step. It can significantly reduce the time complexity of conventional hash function learning processes that sequentially learn multiple hash functions bit by bit. The proposed JMVH is evaluated on two public databases: CC_WEB_VIDEO and UQ_VIDEO. Experimental results demonstrate that the proposed JMVH achieves more than a 5 percent improvement compared to several state-of-the-art methods which indicates the superior performance of JMVH.

Many achievements have been made on learning to hash for uni-modal and cross-modal retrieval. However, it is still an unsolved problem that how to directly and efficiently learn discriminative discrete hash codes for the multimedia retrieval, where both query and database samples are represented with heterogeneous multi-modal features. With this motivation, we propose a Fast Discrete Collaborative Multi-modal Hashing (FDCMH) method in this paper. We first propose an efficient collaborative multi-modal mapping that first transforms heterogeneous multi-modal features into the unified factors to exploit the complementarity of multi-modal features and preserve the semantic correlations in multiple modalities with linear computation and space complexity. Such shared factors also bridge the heterogeneous modality gap and remove the inter-modality redundancy. Further, we develop an asymmetric hashing learning module to simultaneously correlate the learned hash codes with low-level data distribution and high-level semantics. In particular, this design could avoid the challenging symmetric semantic matrix factorization and O(n2) memory cost (n is the number of training samples). It can support both computation and memory efficient discrete hash optimization. Experiments on several public multimedia retrieval datasets demonstrate the superiority of the proposed approach compared with state-of-the-art hashing techniques, in terms of both model learning efficiency and retrieval accuracy.

Hashing has recently received substantial attention in large-scale multimedia search for its extremely low-cost storage cost and high retrieval efficiency. However, most existing hashing techniques focus on learning hash codes for single-view or cross-view retrieval. It is still an unsolved problem that how to efficiently learn discriminative binary codes for multi-view data that is common in real world multimedia search. In this paper, we propose an efficient Supervised Discrete Multi-view Hashing (SDMH) to solve the problem. SDMH first properly detects the shared binary hash codes, with an integrated multi-view feature mapping and latent hash coding, by exploiting the complementarity of different view-specific features and removing the involved inter-view redundancy. To further enhance the discriminative capability of hash codes, SDMH directly represses the explicit semantic labels of data samples with their corresponding binary codes. Different from most existing multi-view hashing methods that adopt “relaxing+rounding” hash optimization strategy or the discrete optimization method based on discrete cyclic coordinate descent, an efficient augmented Lagrangian multiplier (ALM) based discrete hash optimization method is developed in this paper to optimize the hash codes within a single step. Experimental results on four benchmark datasets demonstrate the superior performance of the proposed approach over state-of-the-art hashing techniques, in terms of both learning efficiency and retrieval accuracy.

Graph-based clustering methods have achieved remarkable performance by partitioning the data samples into disjoint groups with the similarity graph that characterizes the sample relations. Nevertheless, their learning scheme still suffers from two important problems: 1) the similarity graph directly constructed from the raw features may be unreliable as real-world data always involves adverse noises, outliers, and irrelevant information and 2) most graph-based clustering methods adopt two-step learning strategy that separates the similarity graph construction and clustering into two independent processes. Under such circumstance, the generated graph is unstructured and fixed. It may suffer from a low-quality clustering structure and thus lead to suboptimal clustering performance. To alleviate these limitations, in this article we propose a robust structured graph clustering (RSGC) model. We formulate a novel learning framework to simultaneously learn a robust structured similarity graph and perform clustering. Specifically, the structured graph with proper probabilistic neighborhood assignment is adaptively learned on a robust latent representation that resists the noises and outliers. Furthermore, an explicit rank constraint is imposed on the Laplacian matrix to structurize the graph such that the number of the connected components is exactly equal to the ground-truth cluster number. To solve the challenging objective formulation, we propose to first transform it into an equivalent one that can be tackled more easily. An iterative solution based on the augmented Lagrangian multiplier is then derived to solve the model. In RSGC, the discrete cluster labels can be directly obtained by partitioning the learned similarity graph without reliance on label discretization strategy as most graph-based clustering methods. Experiments on both synthetic and real data sets demonstrate the superiority of the proposed method compared with the state-of-the-art clustering techniques.

Due to the complex and dynamic environment of social media, user generated contents (UGCs) may inadvertently leak users’ personal aspects, such as the personal attributes, relationships and even the health condition, and thus place users at high privacy risks. Limited research efforts, thus far, have been dedicated to the privacy detection from users’ unstructured data (i.e., UGCs). Moreover, existing efforts mainly focus on applying conventional machine learning techniques directly to traditional hand-crafted privacy-oriented features, ignoring the powerful representing capability of the advanced neural networks. In light of this, in this article, we present a fine-grained privacy detection network (GrHA) equipped with graph-regularized hierarchical attentive representation learning. In particular, the proposed GrHA explores the semantic correlations among personal aspects with graph convolutional networks to enhance the regularization for the UGC representation learning, and, hence, fulfil effective fine-grained privacy detection. Extensive experiments on a real-world dataset demonstrate the superiority of the proposed model over state-of-the-art competitors in terms of eight standard metrics. As a byproduct, we have released the codes and involved parameters to facilitate the research community.

Text classification is one of the fundamental tasks in natural language processing. Recently, deep neural networks have achieved promising performance in the text classification task compared to shallow models. Despite of the significance of deep models, they ignore the fine-grained (matching signals between words and classes) classification clues since their classifications mainly rely on the text-level representations. To address this problem, we introduce the interaction mechanism to incorporate word-level matching signals into the text classification task. In particular, we design a novel framework, EXplicit interAction Model (dubbed as EXAM), equipped with the interaction mechanism. We justified the proposed approach on several benchmark datasets including both multilabel and multi-class text classification tasks. Extensive experimental results demonstrate the superiority of the proposed method. As a byproduct, we have released the codes and parameter settings to facilitate other researches.

Zero-shot learning (ZSL) and cold-start recommendation (CSR) are two challenging problems in computer vision and recommender system, respectively. In general, they are independently investigated in different communities. This paper, however, reveals that ZSL and CSR are two extensions of the same intension. Both of them, for instance, attempt to predict unseen classes and involve two spaces, one for direct feature representation and the other for supplementary description. Yet there is no existing approach which addresses CSR from the ZSL perspective. This work, for the first time, formulates CSR as a ZSL problem, and a tailor-made ZSL method is proposed to handle CSR. Specifically, we propose a Lowrank Linear Auto-Encoder (LLAE), which challenges three cruxes, i.e., domain shift, spurious correlations and computing efficiency, in this paper. LLAE consists of two parts, a low-rank encoder maps user behavior into user attributes and a symmetric decoder reconstructs user behavior from user attributes. Extensive experiments on both ZSL and CSR tasks verify that the proposed method is a win-win formulation, i.e., not only can CSR be handled by ZSL models with a significant performance improvement compared with several conventional state-of-the-art methods, but the consideration of CSR can benefit ZSL as well.

The linear model is commonly utilized in hashing methods owing to its efficiency. To obtain better accuracy, linear-based hashing methods focus on designing a generalized linear objective function with different constraints or penalty terms that consider neighborhood information. In this study, we propose a novel generalized framework called Model Boost (MoBoost), which can achieve the self-improvement of the linear-based hashing. The proposed MoBoost is used to improve model parameter optimization for linear-based hashing methods without adding new constraints or penalty terms. In the proposed MoBoost, given a linear-based hashing method, we first execute the method several times to get several different hash codes for training samples, and then combine these different hash codes into one set utilizing one novel fusion strategy. Based on this set of hash codes, we learn some new parameters for the linear hash function that can significantly improve accuracy. The proposed MoBoost can be generally adopted in existing linear-based hashing methods, achieving more precise and stable performance compared to the original methods while imposing negligible added expenditure in terms of time and space. Extensive experiments are performed based on three benchmark datasets, and the results demonstrate the superior performance of the proposed framework.

Conventional zero-shot learning (ZSL) methods generally learn an embedding, e.g., visual-semantic mapping, to handle the unseen visual samples via an indirect manner. In this paper, we take the advantage of generative adversarial networks (GANs) and propose a novel method, named leveraging invariant side GAN (LisGAN), which can directly generate the unseen features from random noises which are conditioned by the semantic descriptions. Specifically, we train a conditional Wasserstein GANs in which the generator synthesizes fake unseen features from noises and the discriminator distinguishes the fake from real via a minimax game. Considering that one semantic description can correspond to various synthesized visual samples, and the semantic description, figuratively, is the soul of the generated features, we introduce soul samples as the invariant side of generative zero-shot learning in this paper. A soul sample is the meta-representation of one class. It visualizes the most semantically-meaningful aspects of each sample in the same category. We regularize that each generated sample (the varying side of generative ZSL) should be close to at least one soul sample (the invariant side) which has the same class label with it. At the zero-shot recognition stage, we propose to use two classifiers, which are deployed in a cascade way, to achieve a coarse-to-fine result. Experiments on five popular benchmarks verify that our proposed approach can outperform state-of-the-art methods with significant improvements.

Deep hashing has recently received attention in cross-modal retrieval for its impressive advantages. However, existing hashing methods for cross-modal retrieval cannot fully capture the heterogeneous multi-modal correlation and exploit the semantic information. In this paper, we propose a novel Fusion-supervised Deep Cross-modal Hashing (FDCH) approach. Firstly, FDCH learns unified binary codes through a fusion hash network with paired samples as input, which effectively enhances the modeling of the correlation of heterogeneous multi-modal data. Then, these high-quality unified hash codes further supervise the training of the modality-specific hash networks for encoding out-of-sample queries. Meanwhile, both pair-wise similarity information and classification information are embedded in the hash networks under one stream framework, which simultaneously preserves cross-modal similarity and keeps semantic consistency. Experimental results on two benchmark datasets demonstrate the state-of-the-art performance of FDCH.

Hashing can compress high-dimensional data into compact binary codes, while preserving the similarity, to facilitate efficient retrieval and storage. However, when retrieving using an extremely short length hash code learned by the existing methods, the performance cannot be guaranteed because of severe information loss. To address this issue, in this study, we propose a novel supervised short-length hashing (SSLH). In this proposed SSLH, mutual reconstruction between the short-length hash codes and original features are performed to reduce semantic loss. Furthermore, to enhance the robustness and accuracy of the hash representation, a robust estimator term is added to fully utilize the label information. Extensive experiments conducted on four image benchmarks demonstrate the superior performance of the proposed SSLH with short-length hash codes. In addition, the proposed SSLH outperforms the existing methods, with long-length hash codes. To the best of our knowledge, this is the first linear-based hashing method that focuses on both short and long-length hash codes for maintaining high precision.

Domain adaptation investigates the problem of cross-domain knowledge transfer where the labeled source domain and unlabeled target domain have distinctive data distributions. Recently, adversarial training have been successfully applied to domain adaptation and achieved state-of-the-art performance. However, there is still a fatal weakness existing in current adversarial models which is raised from the equilibrium challenge of adversarial training. Specifically, although most of existing methods are able to confuse the domain discriminator, they cannot guarantee that the source domain and target domain are sufficiently similar. In this paper, we propose a novel approach named cycle-consistent conditional adversarial transfer networks (3CATN) to handle this issue. Our approach takes care of the domain alignment by leveraging adversarial training. Specifically, we condition the adversarial networks with the cross-covariance of learned features and classifier predictions to capture the multimodal structures of data distributions. However, since the classifier predictions are not certainty information, a strong condition with the predictions is risky when the predictions are not accurate. We, therefore, further propose that the truly domain-invariant features should be able to be translated from one domain to the other. To this end, we introduce two feature translation losses and one cycle-consistent loss into the conditional adversarial domain adaptation networks. Extensive experiments on both classical and large-scale datasets verify that our model is able to outperform previous state-of-the-arts with significant improvements.

Lately, generative adversarial networks (GANs) have been successfully applied to zero-shot learning (ZSL) and achieved state-of-the-art performance. By synthesizing virtual unseen visual features, GAN-based methods convert the challenging ZSL task into a supervised learning problem. However, since real unseen visual features are not available at the training stage, GAN-based ZSL methods have to train the GAN generator on the seen categories and further apply it to unseen instances. An inevitable issue of such a paradigm is that the synthesized unseen features are prone to seen references and incapable to reflect the novelty and diversity of real unseen instances. In a nutshell, the synthesized features are confusing. One cannot tell unseen categories from seen ones using the synthesized features. As a result, the synthesized features are too subtle to be classified in generalized zero-shot learning (GZSL) which involves both seen and unseen categories at the test stage. In this paper, we first introduce the feature confusion issue. Then, we propose a new feature generating network, named alleviating feature confusion GAN (AFC-GAN), to challenge the issue. Specifically, we present a boundary loss which maximizes the decision boundary of seen categories and unseen ones. Furthermore, a novel metric named feature confusion score (FCS) is proposed to quantify the feature confusion. Extensive experiments on five widely used datasets verify that our method is able to outperform previous state-of-the-arts under both ZSL and GZSL protocols.

Multi-modal hashing fuses multi-modal features at both offline training and online query stage for compact binary hash learning. It has aroused extensive attention in research filed of efficient large-scale multimedia retrieval. However, existing methods adopt batch-based learning scheme or unsupervised learning paradigm. They cannot efficiently handle the very common online streaming multi-modal data (for batch-learning methods), or learn the hash codes suffering from limited discriminative capability and less flexibility for varied streaming data (for existing online multi-modal hashing methods). In this paper, we develop a supervised Flexible Online Multi-modal Hashing (FOMH) method to adaptively fuse heterogeneous modalities and flexibly learn the discriminative hash code for the newly coming data, even if part of the modalities is missing. Specifically, instead of adopting the fixed weights, the modalities weights in FOMH are automatically learned with the proposed flexible multi-modal binary projection to timely capture the variations of streaming samples. Further, we design an efficient asymmetric online supervised hashing strategy to enhance the discriminative capability of the hash codes, while avoiding the challenging symmetric semantic matrix decomposition and storage cost. Moreover, to support fast hash updating and avoid the propagation of binary quantization errors in online learning process, we propose to directly update the hash codes with an efficient discrete online optimization. Experiments on several public multimedia retrieval datasets validate the superiority of the proposed method from various aspects.

Personalized hashtag recommendation methods aim to suggest users hashtags to annotate, categorize, and describe their posts. The hashtags, that a user provides to a post (e.g., a micro-video), are the ones which in her mind can well describe the post content where she is interested in. It means that we should consider both users' preferences on the post contents and their personal understanding on the hashtags. Most existing methods rely on modeling either the interactions between hashtags and posts or the interactions between users and hashtags for hashtag recommendation. These methods have not well explored the complicated interactions among users, hashtags, and micro-videos. In this paper, towards the personalized micro-video hashtag recommendation, we propose a Graph Convolution Network based Personalized Hashtag Recommendation (GCN-PHR) model, which leverages recently advanced GCN techniques to model the complicate interactions among and learn their representations. In our model, the users, hashtags, and micro-videos are three types of nodes in a graph and they are linked based on their direct associations. In particular, the message-passing strategy is used to learn the representation of a node (e.g., user) by aggregating the message passed from the directly linked other types of nodes (e.g., hashtag and micro-video). Because a user is often only interested in certain parts of a micro-video and a hashtag is typically used to describe the part (of a micro-video) that the user is interested in, we leverage the attention mechanism to filter the message passed from micro-videos to users and hashtags, which can significantly improve the representation capability. Extensive experiments have been conducted on two real-world micro-video datasets and demonstrate that our model outperforms the state-of-the-art approaches by a large margin.

Most existing Zero-Shot Learning (ZSL) approaches adopt the semantic space as a bridge to classify unseen categories. However, it is difficult to transfer knowledge from seen categories to unseen categories through semantic space, since the correlations among categories are uncertain and ambiguous in the semantic space. In this paper, we formulated zero-shot learning as a classifier weight regression problem. Specifically, we propose a novel Residual Graph Convolution Network (ResGCN) which takes word embeddings and knowledge graph as inputs and outputs a visual classifier for each category. ResGCN can effectively alleviate the problem of over-smoothing and over-fitting. During the test, an unseen image can be classified by ranking the inner product of its visual feature and predictive visual classifiers. Moreover, we provide a new method to build a better knowledge graph. Our approach not only further enhances the correlations among categories, but also makes it easy to add new categories to the knowledge graph. Experiments conducted on the large-scale ImageNet 2011 21K dataset demonstrate that our method significantly outperforms existing state-of-the-art approaches.

Multi-modal hashing is an effective technique to support large-scale multimedia retrieval, due to its capability of encoding heterogeneous multi-modal features into compact and similarity-preserving binary codes. Although great progress has been achieved so far, existing methods still suffer from several problems, including: 1) All existing methods simply adopt fixed modality combination weights in online hashing process to generate the query hash codes. This strategy cannot adaptively capture the variations of different queries. 2) They either suffer from insufficient semantics (for unsupervised methods) or require high computation and storage cost (for the supervised methods, which rely on pair-wise semantic matrix). 3) They solve the hash codes with relaxed optimization strategy or bit-by-bit discrete optimization, which results in significant quantization loss or consumes considerable computation time. To address the above limitations, in this paper, we propose an Online Multi-modal Hashing with Dynamic Query-adaption (OMH-DQ) method in a novel fashion. Specifically, a self-weighted fusion strategy is designed to adaptively preserve the multi-modal feature information into hash codes by exploiting their complementarity. The hash codes are learned with the supervision of pair-wise semantic labels to enhance their discriminative capability, while avoiding the challenging symmetric similarity matrix factorization. Under such learning framework, the binary hash codes can be directly obtained with efficient operations and without quantization errors. Accordingly, our method can benefit from the semantic labels, and simultaneously, avoid the high computation complexity. Moreover, to accurately capture the query variations, at the online retrieval stage, we design a parameter-free online hashing module which can adaptively learn the query hash codes according to the dynamic query contents. Extensive experiments demonstrate the state-of-the-art performance of the proposed approach from various aspects.

In this paper, we revisit the classical stochastic jump-diffusion process and develop an effective variant for estimating visibility statuses of objects while tracking them in videos. Dealing with partial or full occlusions is a long standing problem in computer vision but largely remains unsolved. In this paper, we cast the above problem as a Markov decision process and develop a policy-based jump-diffusion method to jointly track object locations in videos and estimate their visibility statuses. Our method employs a set of jump dynamics to change visibility statuses of objects and a set of diffusion dynamics to track objects in videos. Different from the traditional jump-diffusion process that stochastically generates dynamics, we utilize deep policy functions to determine the best dynamic for the present state and learn the optimal policies using reinforcement learning methods. Our method is capable of tracking objects with full or partial occlusions in crowded scenes. We evaluate the proposed method over challenging video sequences and compare it to alternative tracking methods. Significant improvements are made particularly for videos with frequent interactions or occlusions.

Currently, unsupervised heterogeneous domain adaptation in a generalized setting, which is the most common scenario in real-world applications, is under insufficient exploration. Existing approaches either are limited to special cases or require labeled target samples for training. This paper aims to overcome these limitations by proposing a generalized framework, named as transfer independently together (TIT). Specifically, we learn multiple transformations, one for each domain (independently), to map data onto a shared latent space, where the domains are well aligned. The multiple transformations are jointly optimized in a unified framework (together) by an effective formulation. In addition, to learn robust transformations, we further propose a novel landmark selection algorithm to reweight samples, i.e., increase the weight of pivot samples and decrease the weight of outliers. Our landmark selection is based on graph optimization. It focuses on sample geometric relationship rather than sample features. As a result, by abstracting feature vectors to graph vertices, only a simple and fast integer arithmetic is involved in our algorithm instead of matrix operations with float point arithmetic in existing approaches. At last, we effectively optimize our objective via a dimensionality reduction procedure. TIT is applicable to arbitrary sample dimensionality and does not need labeled target samples for training. Extensive evaluations on several standard benchmarks and large-scale datasets of image classification, text categorization and text-to-image recognition verify the superiority of our approach.

Domain adaptation aims to leverage knowledge from a well-labeled source domain to a poorly labeled target domain. A majority of existing works transfer the knowledge at either feature level or sample level. Recent studies reveal that both of the paradigms are essentially important, and optimizing one of them can reinforce the other. Inspired by this, we propose a novel approach to jointly exploit feature adaptation with distribution matching and sample adaptation with landmark selection. During the knowledge transfer, we also take the local consistency between the samples into consideration so that the manifold structures of samples can be preserved. At last, we deploy label propagation to predict the categories of new instances. Notably, our approach is suitable for both homogeneous- and heterogeneous-domain adaptations by learning domain-specific projections. Extensive experiments on five open benchmarks, which consist of both standard and large-scale datasets, verify that our approach can significantly outperform not only conventional approaches but also end-to-end deep models. The experiments also demonstrate that we can leverage handcrafted features to promote the accuracy on deep features by heterogeneous adaptation.

Image aesthetics assessment has emerged as a hot topic in recent years due to its potential in numerous high-level vision applications. In this paper, distinguished from existing studies relying on a single label, we propose quantifying image aesthetics by a distribution over multiple quality levels. The distribution-based representation characterizes the disagreement among users' aesthetic preferences regarding the same image, and is also compatible with the traditional task of aesthetic label prediction. Our framework is developed based on fully convolutional networks and enables inputs of varying sizes. In this way, we circumvent the fixed-size constraint of prevalent convolutional neural networks, and avoid the risk of impairing the intrinsic aesthetic appeal of images. Moreover, given the fact that aesthetic perceiving is coupled with semantic understanding, we present a novel semantic-aware hybrid NEtwork (SANE), which harvests the information from object categorization and scene recognition to enhance image aesthetics assessment. Experiments on two benchmark datasets have well verified the effectiveness of our approach in both scenarios of aesthetic distribution prediction and aesthetic label prediction, and highlighted the benefits of input preserving as well as semantic understanding for images.

In real-world transfer learning tasks, especially in cross-modal applications, the source domain and the target domain often have different features and distributions, which are well known as the heterogeneous domain adaptation (HDA) problem. Yet, existing HDA methods focus on either alleviating the feature discrepancy or mitigating the distribution divergence due to the challenges of HDA. In fact, optimizing one of them can reinforce the other. In this paper, we propose a novel HDA method that can optimize both feature discrepancy and distribution divergence in a unified objective function. Specifically, we present progressive alignment, which first learns a new transferable feature space by dictionary-sharing coding, and then aligns the distribution gaps on the new space. Different from previous HDA methods that are limited to specific scenarios, our approach can handle diverse features with arbitrary dimensions. Extensive experiments on various transfer learning tasks, such as image classification, text categorization, and text-to-image recognition, verify the superiority of our method against several state-of-the-art approaches.

Personalized rating prediction is an important research problem in recommender systems. Although the latent factor model (e.g., matrix factorization) achieves good accuracy in rating prediction, it suffers from many problems including cold-start, non-transparency, and suboptimal results for individual user-item pairs. In this article, we exploit textual reviews and item images together with ratings to tackle these limitations. Specifically, we first apply a proposed multi-modal aspect-aware topic model (MATM) on text reviews and item images to model users’ preferences and items’ features from different aspects , and also estimate the aspect importance of a user toward an item. Then, the aspect importance is integrated into a novel aspect-aware latent factor model (ALFM), which learns user’s and item’s latent factors based on ratings. In particular, ALFM introduces a weight matrix to associate those latent factors with the same set of aspects in MATM, such that the latent factors could be used to estimate aspect ratings. Finally, the overall rating is computed via a linear combination of the aspect ratings, which are weighted by the corresponding aspect importance. To this end, our model could alleviate the data sparsity problem and gain good interpretability for recommendation. Besides, every aspect rating is weighted by its aspect importance, which is dependent on the targeted user’s preferences and the targeted item’s features. Therefore, it is expected that the proposed method can model a user’s preferences on an item more accurately for each user-item pair. Comprehensive experimental studies have been conducted on the Yelp 2017 Challenge dataset and Amazon product datasets. Results show that (1) our method achieves significant improvement compared to strong baseline methods, especially for users with only few ratings; (2) item visual features can improve the prediction performance—the effects of item image features on improving the prediction results depend on the importance of the visual features for the items; and (3) our model can explicitly interpret the predicted results in great detail.

Current recommender systems consider the various aspects of items for making accurate recommendations. Different users place different importance to these aspects which can be thought of as a preference/attention weight vector. Most existing recommender systems assume that for an individual, this vector is the same for all items. However, this assumption is often invalid, especially when considering a user's interactions with items of diverse characteristics. To tackle this problem, in this paper, we develop a novel aspect-aware recommender model named A$^3$NCF, which can capture the varying aspect attentions that a user pays to different items. Specifically, we design a new topic model to extract user preferences and item characteristics from review texts. They are then used to 1) guide the representation learning of users and items, and 2) capture a user's special attention on each aspect of the targeted item with an attention network. Through extensive experiments on several large-scale datasets, we demonstrate that our model outperforms the state-of-the-art review-aware recommender systems in the rating prediction task.

In this paper, we investigate the research problem of unsupervised multi-view feature selection. Conventional solutions first simply combine multiple pre-constructed view-specific similarity structures into a collaborative similarity structure, and then perform the subsequent feature selection. These two processes are separate and independent. The collaborative similarity structure remains fixed during feature selection. Further, the simple undirected view combination may adversely reduce the reliability of the ultimate similarity structure for feature selection, as the view-specific similarity structures generally involve noises and outlying entries. To alleviate these problems, we propose an adaptive collaborative similarity learning (ACSL) for multi-view feature selection. We propose to dynamically learn the collaborative similarity structure, and further integrate it with the ultimate feature selection into a unified framework. Moreover, a reasonable rank constraint is devised to adaptively learn an ideal collaborative similarity structure with proper similarity combination weights and desirable neighbor assignment, both of which could positively facilitate the feature selection. An effective solution guaranteed with the proved convergence is derived to iteratively tackle the formulated optimization problem. Experiments demonstrate the superiority of the proposed approach.

In visual classification tasks, it is hard to tell the subtle differences from one species to another similar breeds. Such a challenging problem is generally known as Fine-Grained Visual Classification (FGVC). In this paper, we propose a novel FGVC approach called Texts Assisted Fine-Grained Visual Classification (TA-FGVC). TA-FGVC reads from texts to gain attention, sees the images with the gained attention and then tells the subtle differences. Technically, we propose a deep neural network which learns a visual-semantic embedding model. The proposed deep architecture mainly consists of two parts: one for visual localization, and the other for visual to semantic projection. The model is fed with both visual features which are extracted from raw images and semantic information which are learned from two sources: gleaned from unannotated texts and gathered from image attributes. At the very last layer of the model, each image is embedded into the semantic space which is related to class labels. Finally, the categorization results from both visual stream and visual-semantic stream are combined to achieve the ultimate decision. Extensive experiments on open standard benchmarks verify the superiority of our model against several state of the art work.

Hashing has recently received great attention in cross-modal retrieval. Cross-modal retrieval aims at retrieving information across heterogeneous modalities (e.g., texts vs. images). Cross-modal hashing compresses heterogeneous high-dimensional data into compact binary codes with similarity preserving, which provides efficiency and facility in both retrieval and storage. In this study, we propose a novel fast discrete cross-modal hashing (FDCH) method with regressing from semantic labels to take advantage of supervised labels to improve retrieval performance. In contrast to existing methods that learn the projection from hash codes to semantic labels, the proposed FDCH regresses the semantic labels of training examples to the corresponding hash codes with a drift. It not only accelerates the hash learning process, but also helps generate stable hash codes. Furthermore, the drift can adjust the regression and enhance the discriminative capability of hash codes. Especially in the case of training efficiency, FDCH is much faster than existing methods. Comparisons with several state-of-the-art techniques on three benchmark datasets have demonstrated the superiority of FDCH under various cross-modal retrieval scenarios.

Although latent factor models (e.g., matrix factorization) achieve good accuracy in rating prediction, they suffer from several problems including cold-start, non-transparency, and suboptimal recommendation for local users or items. In this paper, we employ textual review information with ratings to tackle these limitations. Firstly, we apply a proposed aspect-aware topic model (ATM) on the review text to model user preferences and item features from different aspects, and estimate the aspect importance of a user towards an item. The aspect importance is then integrated into a novel aspect-aware latent factor model (ALFM), which learns user's and item's latent factors based on ratings. In particular, ALFM introduces a weighted matrix to associate those latent factors with the same set of aspects discovered by ATM, such that the latent factors could be used to estimate aspect ratings. Finally, the overall rating is computed via a linear combination of the aspect ratings, which are weighted by the corresponding aspect importance. To this end, our model could alleviate the data sparsity problem and gain good interpretability for recommendation. Besides, an aspect rating is weighted by an aspect importance, which is dependent on the targeted user's preferences and targeted item's features. Therefore, it is expected that the proposed method can model a user's preferences on an item more accurately for each user-item pair locally. Comprehensive experimental studies have been conducted on 19 datasets from Amazon and Yelp 2017 Challenge dataset. Results show that our method achieves significant improvement compared with strong baseline methods, especially for users with only few ratings. Moreover, our model could interpret the recommendation results in depth.

In our daily life, how to match clothing well is always a troublesome problem especially when we are shopping online to select a pair of matched pieces of clothing from tens of thousands available selections. To help common customers overcome selection issues, recent studies in the recommender system area have started to infer the fashion matching results automatically. The traditional fashion recommendation is normally achieved by considering visual similarity of clothing items or/and item co-purchase history from existing shopping transactions. Due to the high complexity of visual features and the lack of historical item purchase records, most of the existing work is unlikely to make an efficient and accurate recommendation. To address the problem, in this paper, we propose a new model called Discrete Supervised Fashion Coordinates Hashing. Its main objective is to learn meaningful yet compact high-level features of clothing items, which are represented as binary hash codes. In detail, this learning process is supervised by a clothing matching matrix, which is initially constructed based on limited known matching pairs and subsequently on the self-augmented ones. The proposed model jointly learns the intrinsic matching patterns from the matching matrix and the binary representations from the clothing items’ images, where the visual feature of each clothing item is discretized into a fixed-length binary vector. The binary representation learning significantly reduces the memory cost and accelerates the recommendation speed. The experiments compared with several state-of-the-art approaches have evidenced the superior performance of the proposed approach on efficient fashion recommendation.

In computer vision, tracking humans across camera views remain challenging, especially for complex scenarios with frequent occlusions, significant lighting changes, and other difficulties. Under such conditions, most existing appearance and geometric cues are not reliable enough to distinguish humans across camera views. To address these challenges, this paper presents a stochastic attribute grammar model for leveraging complementary and discriminative human attributes for enhancing cross-view tracking. The key idea of our method is to introduce a hierarchical representation, parse graph, to describe a subject and its movement trajectory in both space and time domains. These results in a hierarchical compositional representation, comprising trajectory entities of varying level, including human boxes, 3D human boxes, tracklets, and trajectories. We use a set of grammar rules to decompose a graph node (e.g., tracklet) into a set of children nodes (e.g., 3D human boxes), and augment each node with a set of attributes, including geometry (e.g., moving speed and direction), accessories (e.g., bags), and/or activities (e.g., walking and running). These attributes serve as valuable cues, in addition to appearance features (e.g., colors), in determining the associations of human detection boxes across cameras. In particular, the attributes of a parent node are inherited by its children nodes, resulting in consistency constraints over the feasible parse graph. Thus, we cast cross-view human tracking as finding the most discriminative parse graph for each subject in videos. We develop a learning method to train this attribute grammar model from weakly supervised training data. To infer the optimal parse graph and its attributes, we develop an alternative parsing method that employs both top-down and bottom-up computations to search the optimal solution. We also explicitly reason the occlusion status of each entity in order to deal with significant changes of camera viewpoints. We evaluate the proposed method over public video benchmarks, and demonstrate with extensive experiments that our method clearly outperforms the state-of-the-art tracking methods.

Unsupervised hashing can desirably support scalable content-based image retrieval for its appealing advantages of semantic label independence, memory, and search efficiency. However, the learned hash codes are embedded with limited discriminative semantics due to the intrinsic limitation of image representation. To address the problem, in this paper, we propose a novel hashing approach, dubbed as discrete semantic transfer hashing (DSTH). The key idea is to directly augment the semantics of discrete image hash codes by exploring auxiliary contextual modalities. To this end, a unified hashing framework is formulated to simultaneously preserve visual similarities of images and perform semantic transfer from contextual modalities. Furthermore, to guarantee direct semantic transfer and avoid information loss, we explicitly impose the discrete constraint, bit-uncorrelation constraint, and bit-balance constraint on hash codes. A novel and effective discrete optimization method based on augmented Lagrangian multiplier is developed to iteratively solve the optimization problem. The whole learning process has linear computation complexity and desirable scalability. Experiments on three benchmark data sets demonstrate the superiority of DSTH compared with several state-of-the-art approaches.

In this paper, we present an automatic approach for on-line discovery of visual-lingual semantic fragments from weakly labeled Internet images. Instead of learning region-entity correspondences from well-labeled image-sentence pairs, our approach directly collects and enhances the weakly labeled visual contents from the Web and constructs an adaptive visual representation which automatically links generic lingual phrases to their related visual contents. To ensure reliable and efficient semantic discovery, we adopt non-parametric density estimation to re-rank the related visual instances and proposed a fast self-similarity-based quality assessment method to identify the high-quality semantic fragments. The discovered semantic fragments provide an adaptive joint representation for texts and images, based on which lingual-visual similarity can be defined for further co-analysis of heterogeneous multimedia data. Experimental results on semantic fragment quality assessment, sentence-based image retrieval, automatic multimedia insertion and ordering demonstrated the effectiveness of the proposed framework.The experiments show that the proposed methods can make effective use of the Web knowledge, and are able to generate competitive results compared to state-of-the-art approaches in various tasks.

Existing video event classification approaches suffer from limited human-labeled semantic annotations. Weak semantic annotations can be harvested from Web-knowledge without involving any human interaction. However such weak annotations are noisy, thus can not be effectively utilized without distinguishing its reliability. In this paper, we propose a novel approach to automatically maximize the utility of weak semantic annotations (formalized as the semantic relevance of video shots to the target event) to facilitate video event classification. A novel attention model is designed to determine the attention scores of video shots, where the weak semantic relevance is considered as atten-tional guidance. Specifically, our model jointly optimizes two objectives at different levels. The first one is the classification loss corresponding to video-level groundtruth labels, and the second is the shot-level relevance loss corresponding to weak semantic relevance. We use a long short-term memory (LSTM) layer to capture the temporal information carried by the shots of a video. In each timestep, the LSTM employs the attention model to weight the current shot under the guidance of its weak semantic relevance to the event of interest. Thus, we can automatically exploit weak semantic relevance to assist video event classification. Extensive experiments have been conducted on three complex large-scale video event datasets i.e., MEDTest14, ActivityNet and FCVID. Our approach achieves the state-of-the-art classification performance on all three datasets. The significant performance improvement upon the conventional attention model also demonstrates the effectiveness of our model.

Users leave digital footprints when interacting with various music streaming services. Music play sequence, which contains rich information about personal music preference and song similarity, has been largely ignored in previous music recommender systems. In this paper, we explore the effects of music play sequence on developing effective personalized music recommender systems. Towards the goal, we propose to use word embedding techniques in music play sequences to estimate the similarity between songs. The learned similarity is then embedded into matrix factorization to boost the latent feature learning and discovery. Furthermore, the proposed method only considers the k-nearest songs (e.g., k = 5) in the learning process and thus avoids the increase of time complexity. Experimental results on two public datasets demonstrate that our methods could significantly improve the performance of both rating prediction and top-n recommendation tasks.

Advanced hashing technique is essential to facilitate effective large scale online image organization and retrieval, where image contents could be frequently changed. Traditional multi-view hashing methods are developed based on batch-based learning, which leads to very expensive updating cost. Meanwhile, existing online hashing methods mainly focus on single-view data and thus can not achieve promising performance when searching real online images, which are multiple view based data. Further, both types of hashing methods can only produce hash code with fixed length. Consequently they suffer from limited capability to comprehensive characterization of streaming image data in the real world. In this paper, we propose dynamic multi-view hashing (DMVH), which can adaptively augment hash codes according to dynamic changes of image. Meanwhile, DMVH leverages online learning to generate hash codes. It can increase the code length when current code is not able to represent new images effectively. Moreover, to gain further improvement on overall performance, each view is assigned with a weight, which can be efficiently updated during the online learning process. In order to avoid the frequent updating of code length and view weights, an intelligent buffering scheme is also specifically designed to preserve significant data to maintain good effectiveness of DMVH. Experimental results on two real-world image datasets demonstrate superior performance of DWVH over several state-of-the-art hashing methods.

This paper presents a unified framework to learn to quantify perceptual attributes (e.g., safety, attractiveness) of physical urban environments using crowd-sourced street-view photos without human annotations. The efforts of this work include two folds. First, we collect a large-scale urban image dataset in multiple major cities in U.S.A., which consists of multiple street-view photos for every place. Instead of using subjective annotations as in previous works, which are neither accurate nor consistent, we collect for every place the safety score from government's crime event records as objective safety indicators. Second, we observe that the place-centric perception task is by nature a multi-instance regression problem since the labels are only available for places (bags), rather than images or image regions (instances). We thus introduce a deep convolutional neural network (CNN) to parameterize the instance-level scoring function, and develop an EM algorithm to alternatively estimate the primary instances (images or image regions) which affect the safety scores and train the proposed network. Our method is capable of localizing interesting images and image regions for each place. We evaluate the proposed method on a newly created dataset and a public dataset. Results with comparisons showed that our method can clearly outperform the alternative perception methods and more importantly, is capable of generating region-level safety scores to facilitate interpretations of the perception process.

Content-based visual landmark search (CBVLS) enjoys great importance in many practical applications. In this paper, we propose a novel discrete hashing with pair-exemplar (DHPE) to support scalable and efficient large-scale CBVLS. Our approach mainly solves two essential problems in scalable landmark hashing: 1) Intra-landmark visual diversity, and 2) Discrete optimization of hashing codes. Motivated by the characteristic of landmark, we explore the consistent preferences of tourists on landmark as pair-exemplars for scalable discrete hashing learning. In this paper, a pair-exemplar is comprised of a canonical view and the corresponding representative tags. Canonical view captures the key visual component of landmarks, and representative tags potentially involve landmark-specific semantics that can cope with the visual variations of intra-landmark. Based on pair-exemplars, a unified hashing learning framework is formulated to combine visual preserving with exemplar graph and the semantic guidance from representative tags. Further, to guarantee direct semantic transfer for hashing codes and remove information redundancy, we design a novel optimization method based on augmented Lagrange multiplier to explicitly deal with the discrete constraint, the bit-uncorrelated constraint and balance constraint. The whole learning process has linear computation complexity and enjoys desirable scalability. Experiments demonstrate the superior performance of DHPE compared with state-of-the-art methods.

Hashing compresses high-dimensional features into compact binary codes. It is one of the promising techniques to support efficient mobile image retrieval, due to its low data transmission cost and fast retrieval response. However, most of existing hashing strategies simply rely on low-level features. Thus, they may generate hashing codes with limited discriminative capability. Moreover, many of them fail to exploit complex and high-order semantic correlations that inherently exist among images. Motivated by these observations, we propose a novel unsupervised hashing scheme, called topic hypergraph hashing (THH), to address the limitations. THH effectively mitigates the semantic shortage of hashing codes by exploiting auxiliary texts around images. In our method, relations between images and semantic topics are first discovered via robust collective non-negative matrix factorization. Afterwards, a unified topic hypergraph, where images and topics are represented with independent vertices and hyperedges, respectively, is constructed to model inherent high-order semantic correlations of images. Finally, hashing codes and functions are learned by simultaneously enforcing semantic consistence and preserving the discovered semantic relations. Experiments on publicly available datasets demonstrate that THH can achieve superior performance compared with several state-of-the-art methods, and it is more suitable for mobile image retrieval.

As an emerging technology to support scalable content-based image retrieval (CBIR), hashing has recently received great attention and became a very active research domain. In this study, we propose a novel unsupervised visual hashing approach called semantic-assisted visual hashing (SAVH). Distinguished from semi-supervised and supervised visual hashing, its core idea is to effectively extract the rich semantics latently embedded in auxiliary texts of images to boost the effectiveness of visual hashing without any explicit semantic labels. To achieve the target, a unified unsupervised framework is developed to learn hash codes by simultaneously preserving visual similarities of images, integrating the semantic assistance from auxiliary texts on modeling high-order relationships of inter-images, and characterizing the correlations between images and shared topics. Our performance study on three publicly available image collections: Wiki, MIR Flickr, and NUS-WIDE indicates that SAVH can achieve superior performance over several state-of-the-art techniques.

Mobile landmark search (MLS) recently receives increasing attention for its great practical values. However, it still remains unsolved due to two important challenges. One is high bandwidth consumption of query transmission, and the other is the huge visual variations of query images sent from mobile devices. In this paper, we propose a novel hashing scheme, named as canonical view based discrete multimodal hashing (CV-DMH), to handle these problems. First, a submodular function is designed to measure visual representativeness and redundancy of a view set. With it, canonical views, which capture key visual appearances of landmark with limited redundancy, are efficiently discovered with an iterative mining strategy. Second, multimodal sparse coding is applied to transform visual features from multiple modalities into an intermediate representation. It can robustly and adaptively characterize visual contents of varied landmark images with certain canonical views. Finally, compact binary codes are learned on intermediate representation within a tailored discrete binary embedding model which preserves visual relations of images measured with canonical views and removes the involved noises. In this part, we develop a new augmented Lagrangian multiplier (ALM) based optimization method to directly solve the discrete binary codes. We can not only explicitly deal with the discrete constraint, but also consider the bit-uncorrelated constraint and balance constraint together. The proposed solution can desirably avoid accumulated quantization errors in conventional optimization method which simply adopts two-step "relaxing+rounding'' framework. Experiments on real world landmark datasets demonstrate the superior performance of CV-DMH over several state-of-the-art methods.

Cross-modal hashing (CMH) is an efficient technique for the fast retrieval of web image data, and it has gained a lot of attentions recently. However, traditional CMH methods usually apply batch learning for generating hash functions and codes. They are inefficient for the retrieval of web images which usually have streaming fashion. Online learning can be exploited for CMH. But existing online hashing methods still cannot solve two essential problems: efficient updating of hash codes and analysis of cross-modal correlation. In this paper, we propose Online Cross-modal Hashing (OCMH) which can effectively address the above two problems by learning the shared latent codes (SLC). In OCMH, hash codes can be represented by the permanent SLC and dynamic transfer matrix. Therefore, inefficient updating of hash codes is transformed to the efficient updating of SLC and transfer matrix, and the time complexity is irrelevant to the database size. Moreover, SLC is shared by all the modalities, and thus it can encode the latent cross-modal correlation, which further improves the overall cross-modal correlation between heterogeneous data. Experimental results on two real-world multi-modal web image datasets: MIR Flickr and NUS-WIDE, demonstrate the effectiveness and efficiency of OCMH for online cross-modal web image retrieval.

Hashing is one of the promising solutions to support efficient Mobile Image Retrieval (MIR). However, most of existing hashing strategies simply rely on low-level features, which inevitably makes the generated hashing codes less semantic. Moreover, many of them fail to exploit complex and high-order semantic correlations of images. Motivated by these observations, we propose a novel unsupervised hashing scheme, \emph{Topic Hypergraph Hashing} (THH), to address the limitations. A unified topic hypergraph, where images and topics are represented with independent vertices and hyperedges respectively, is first constructed to model latent semantics of images and their correlations. With topic hypergraph model, hashing codes and functions are then learned by simultaneously preserving similarity consistence and semantic correlation. Experiments on standard datasets demonstrate that THH can achieve superior performance compared with several state-of-the-art techniques, and it is more suitable for MIR.

While content-based landmark image search has recently received a lot of attention and became a very active domain, it still remains a challenging problem. Among the various reasons, high diverse visual content is the most significant one. It is common that for the same landmark, images with a wide range of visual appearances can be found from different sources and different landmarks may share very similar sets of images. As a consequence, it is very hard to accurately estimate the similarities between the landmarks purely based on single type of visual feature. Moreover, the relationships between landmark images can be very complex and how to develop an effective modeling scheme to characterize the associations still remains an open question. Motivated by these concerns, we propose multimodal hypergraph (MMHG) to characterize the complex associations between landmark images. In MMHG, images are modeled as independent vertices and hyperedges contain several vertices corresponding to particular views. Multiple hypergraphs are firstly constructed independently based on different visual modalities to describe the hidden high-order relations from different aspects. Then, they are integrated together to involve discriminative information from heterogeneous sources. We also propose a novel content-based visual landmark search system based on MMHG to facilitate effective search. Distinguished from the existing approaches, we design a unified computational module to support query-specific combination weight learning. An extensive experiment study on a large-scale test collection demonstrates the effectiveness of our scheme over state-of-the-art approaches.

Landmark image classification attracts increasing research attention due to its great importance in real applications, ranging from travel guide recommendation to 3-D modelling and visualization of geolocation. While large amount of efforts have been invested, it still remains unsolved by academia and industry. One of the key reasons is the large intra-class variance rooted from the diverse visual appearance of landmark images. Distinguished from most existing methods based on scalable image search, we approach the problem from a new perspective and model landmark classification as multi-modal categorization , which enjoys advantages of low storage overhead and high classification efficiency. Toward this goal, a novel and effective feature representation, called hierarchical multi-modal exemplar (HMME) feature, is proposed to characterize landmark images. In order to compute HMME, training images are first partitioned into the regions with hierarchical grids to generate candidate images and regions. Then, at the stage of exemplar selection, hierarchical discriminative exemplars in multiple modalities are discovered automatically via iterative boosting and latent region label mining. Finally, HMME is generated via a region-based locality-constrained linear coding (RLLC), which effectively encodes semantics of the discovered exemplars into HMME. Meanwhile, dimension reduction is applied to reduce redundant information by projecting the raw HMME into lower-dimensional space. The final HMME enjoys advantages of discriminative and linearly separable. Experimental study has been carried out on real world landmark datasets, and the results demonstrate the superior performance of the proposed approach over several state-of-the-art techniques.

With the rapid growth of data, near-duplicate documents bearing high similarity are abundant. Elimination of near-duplicates can reduce storage cost and improve the quality of search indexes in data mining. A challenging problem is to find near-duplicate records in large-scale collections efficiently. There have already been several efforts on implementing near-duplicate detection on different architectures. In this paper, a new implementation, using a special hash function namely simhash, is proposed to identify near-duplicate documents on CUDA enabled devices. Two mechanisms are designed to achieve higher performance, including swapping and dynamic allocating. Experimental results show that our parallel implementation outperforms the serial CPU version, achieving up to 18 times.

SUMMARY The challenge forSparse Matrix–Vector multiplication(SpMV) performance is memory bandwidth, which mostly depends on input matrices and underlying computing platforms. To solve this challenge, many researchers have explored a variety of optimization techniques. One of the most promising aspects focuses on designing storage formats to represent sparse matrices. However, lots of prior storage formats cannot fully take advantage of the underlying computing platforms, resulting in unsatisfactory performance and large memory footprint. Therefore, a novel storage format, calledSegmented Hybrid ELL + Compressed Sparse Row (CSR)(SHEC for short), is proposed to further improve the throughput and lessen memory footprint onGraphics Processing Unit(GPU). SHEC format employs an interleaved combination pattern, which combines certain amount of compressed rows to form a new SHEC row. Segmentation is brought in to balance load and reduce memory footprint. According to the empirical data, an automatic SHEC‐based SpMV is developed to fit for all the matrices. Experimental results show that SHEC approach outperforms the best results of NVIDIA SpMV library and exhibits a comparable performance with state‐of‐the‐art storage formats on the standard dataset. Copyright © 2012 John Wiley & Sons, Ltd.

Inspired by the success of bag‐of‐words in text retrieval, bag‐of‐visual‐words and its variants are widely used in content‐based image retrieval to describe visual content. Various weighting schemes have also been proposed to integrate different yet complementary visual‐words. However, most of these weighting schemes tend to use fixed weight for every visual‐word extracted from the query image, which may lose the discriminative information. This study presents a novel combining method which captures query‐specific weights for visual‐words in query image. The method mainly contains two stages. Firstly, in offline weight learning, the authors introduce a linear classifier to build a query‐category mapping table, and max‐margin learning to build category‐weight mapping table. Query‐category mapping table is used to map the query image to the most likely image class, and category‐weight mapping table is used to map image class to the weights of visual‐words. Secondly, in online weight mapping, the weights of visual‐words are determined efficiently by looking into the pre‐learned mapping tables. Experimental results on WANG database and Caltech 101 demonstrate that the proposed weighting scheme can effectively weight visual‐words of query image according to their discriminative information. In addition, comparative experiments demonstrate the proposed weighting scheme can obtain higher retrieval performance than other weighting schemes.

Traditional design patent verification based on manual comparison is too labor-intensive, time-consuming and subjective to be applied efficiently in practice. Design patent image retrieval system is designed to retrieve some similar patent images with much visual similarities. Structured features and multiple feature fusion are two main technologies to ensure the retrieval accuracy in the system. Block-wise Dense SIFT (Block-DSIFT), Pyramid Histograms of Orientation Gradients (PHOG), and GIST are proposed as main structured features. A multiple feature fusion algorithm for content-based design patent image retrieval is proposed to formulate the fusion as the linear combination of different matrixes which represent different feature distances between images to improve the precision of retrieval. The weights that reflect the significance of the features are determined by quadratic programming and can be solved efficiently. Experiments on a database of real design patent images show good efficiency and robustness of the proposed method and the system can be applied to design patent copyright validation.