Robust Multimodal Learning (RML) aims to address the issues of unreliable predictions of multimodal models. Nevertheless, previous RML works often struggle to distinguish between different categories that rely on identical intra-modal cues, making ambiguous predictions. We defined this degree of ``uncertain'' in extracting discriminative features of a multimodal model as vagueness. Neglecting such vagueness, as previous RML works commonly do, will undermine the ability to extract unique semantics of each category in multimodal models, further resulting in worse robustness under disturbances that affect semantic representations. Additionally, this vagueness will lead the parameter updating processes towards unreliable fusion, thus diverting the learning processes of the multimodal model from learning unique features of each category. Based on the above insight, we propose a novel robust multimodal learning approach, termed Hyper-Opinion Quantifying Vagueness (HOQV). Specifically, we first introduce hyper-opinion to capture and quantify the vagueness of multimodal learning in discriminating representations of different categories. Moreover, to mitigate the interference in parameter updating of unreliable representations with high vagueness, we also design the Hyper-Opinion Gradient Modulation to guide the optimization processes. We evaluate our HOQV on six datasets with different disturbances, including noise and adversarial attack, and demonstrate that our proposed method achieves state-of-the-art performance consistently.

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.

Predicting the popularity of user-generated content (UGC) is a crucial but challenging task in social media analysis. While existing retrieval-augmented models enhance predictions by supplying rich contextual information, they remain limited by a fundamental precision-recall dilemma: enlarging the retrieval set increases coverage but introduces noisy, irrelevant context that harms prediction. In this work, we propose a unified framework that learns to retrieve, filter, and predict. Central to our approach is a Mixture-of-Logits-based retrieval module that replaces static similarity metrics with a dynamic, multi-faceted scoring function, enabling the retriever to be directly optimized by the prediction objective. Then an uncertainty-aware filter is designed to perform differentiable subset selection and refine the selected representations using the information bottleneck principle. At last, to enhance predictive robustness, we introduce a confidence-weighted test-time perturbation strategy. By learning to retrieve UGCs that are beneficial for prediction and filtering out uncertainty, our framework provides more relevant and reliable context. Extensive experiments demonstrate that the proposed framework achieves state-of-the-art performance, consistently outperforming strong baselines.

Mitigating the detrimental effects of noisy labels on the training process has become increasingly critical, as obtaining entirely clean or human-annotated samples for large-scale pretraining tasks is often impractical.Nonetheless, existing noise mitigation methods often encounter limitations in practical applications due to their task-specific design, model dependency, and significant computational overhead.In this work, we exploit the properties of high-dimensional orthogonality to identify a robust and effective boundary in cone space for separating clean and noisy samples.Building on this, we propose One-Step Antinoise (OSA), a model-agnostic noisy label mitigation paradigm that employs an estimator model and a scoring function to assess the noise level of input pairs through just one-step inference.We empirically validate the superiority of OSA, demonstrating its enhanced training robustness, improved task transferability, streamlined deployment, and reduced computational overhead across diverse benchmarks, models, and tasks.Our code is released at https://github.com/leolee99/OSA. Clarify data Warm upRectify data

Egocentric Task Verification (ETV) aims to determine if the operation flows of procedural tasks in egocentric videos align with the logic of given rules. Early works adopt the video-based verification paradigm that compares a reference video to the testing video, which limits the flexibility of model deployment. Recent researches incorporate reference textual rules instead of videos, describing the operational logic with natural language, but also raises the challenges of cross-modal heterogeneity and hierarchical misalignment between the two modalities. While previous works mainly address the cross-modal heterogeneity between vision and text modalities, they inevitably suffer from two additional key challenges: (1) Existing methods are mostly developed in synthetic domains, yet have not considered the issues of synthetic-to-realistic generalization challenges in real-world applications. (2) The intricate relations between visual content and textual rule involve multiple matching correlations, indicating high-order matching interactions. To address these issues, we proposed the Generalizable Egocentric Task Verification (GETV), and construct a cross-domain ETV benchmark dataset, EgoCross. It features synthetic-to-real cross-domain evaluation, covering both synthetic datasets for training and realistic datasets for testing, across three different types of tasks. Furthermore, we also propose a novel method for this challenge, termed Cross-modal Hybrid Hypergraph Matching (CHHM), which models the logical cross-modal matching in the GETV challenge as a heterogeneous hybrid hypergraph learning process, thus addressing intrinsic multiple matching correlations. Additionally, to tackle the problems of synthetic-to-realistic generalization, we enhance the cross-modal matching process with prototype-based graph representation alignment, which effectively mitigates the cross-domain gap. Extensive experiments on the existing two ETV benchmark datasets, i.e., EgoTV and CSV-NL, and our proposed GETV dataset EgoCross, demonstrate our approach establishes new state-of-the-art performance on both intra-domain and cross-domain challenges.

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.

Deep neural networks often fail to adapt representations to novel tasks under distribution shifts, especially when only a few examples are available. This paper identifies a core obstacle behind this failure: Channel Bias, where networks develop a rigid emphasis on feature dimensions that were discriminative for the source task, but this emphasis is misaligned and fails to adapt to the distinct needs of a novel task. This bias leads to a striking and detrimental consequence: Feature Redundancy. We demonstrate that for few-shot tasks, classification accuracy is significantly improved by using as few as 1-5% of the most discriminative feature dimensions, revealing that the vast majority are actively harmful. Our theoretical analysis confirms that this redundancy originates from confounding feature dimensions-those with high intra-class variance but low inter-class separability-which are especially problematic in low-data regimes. This "Less is More" phenomenon is a defining characteristic of the few-shot setting, diminishing as more samples become available. To address this, we propose a simple yet effective soft-masking method, Augmented Feature Importance Adjustment (AFIA), which estimates feature importance from augmented data to mitigate the issue. By establishing the cohesive link from channel bias to its consequence of extreme feature redundancy, this work provides a foundational principle for few-shot representation transfer and a practical method for developing more robust few-shot learning algorithms.

Inertial Measurement Units (IMUs) can capture intricate kinematic behaviors, thereby enhancing the performance of human action recognition methods. Consequently, this technology has recently garnered considerable attention within this domain. However, existing methods either encounter limitations in instance-level visual representation due to self-occlusion or fail to fully utilize the potential of complex kinematic information, making it challenging to adequately capture the intricate relationships between the two data sources. In this paper, we tackle this issue by addressing the problem through causal learning and Fourier learning. Specifically, we introduce a novel framework calledCausal-Inspired Fourier Representation Learning (CIFRL)for Wearable IMUs and Egocentric Action Recognition, which aims to enhance cross-modal feature alignment. The framework consists of two key components: (1) Temporal Causal Modeling (TCM), designed for video interpretation from a causal perspective; (2) Spectral-Temporal Learning (STL), which aims to decompose the inertial data using Fourier representation and align cross-modal features. We evaluate our proposed framework on the WEAR and CMU-MMAC benchmarks. Empirical results demonstrate the superior performance of our CIFRL approach compared to state-of-the-art methods. Our code is available at https://github.com/Adrianos1219/CIFRL.

The growing prevalence of hate videos promoting intolerance, bigotry, and discrimination presents significant psychosocial threats to both individuals and society. Current detection methods often rely on black-box models, which lack interpretability — a crucial factor for fostering more reliable content moderation and trustworthy AI. To bridge this gap, we propose MATCH, the first attempt to achieve interpretable hate video detection via multiple Large Multimodal Model (LMM) agent collaboration. Our method facilitates a noveldiversely generate-then-verifyparadigm, where LMM agents work in tandem to generate diverse clues and verify them to yield more faithful explanations. MATCH begins by proposing a new Dual-Perspective Proposing paradigm, where two LMM agents are regarded asProposersto independently identify evidential clues from opposing angles – hate and non-hate. Leveraging these comprehensive clues, we introduce an innovative Spatiotemporal Evidence-Grounded Verification mechanism. In this mechanism, a third LMM agent acts as aVerifier, rigorously validating and reconciling the proposed clues against spatiotemporal evidences directly extracted from video content, yielding coherent and faithful explanations. Finally, these explanations are integrated with video features, enabling accurate identification of complex and ambiguous hateful content. Extensive experiments conducted on three benchmark datasets demonstrate that MATCH not only achieves state-of-the-art performance, but also provides reliable and trustworthy rationales for the predictions. Code is available at https://anonymous.4open.science/r/MATCH-HVD.

General Text-to-3D (GT23D) generation is crucial for creating diverse 3D content across objects and scenes, yet it faces two key challenges: 1) ensuring semantic consistency between input text and generated 3D models, and 2) maintaining multi-view consistency across different perspectives within 3D. Existing approaches typically address only one of these challenges, often leading to suboptimal results in semantic fidelity and structural coherence. To overcome these limitations, we propose SeMv-3D, a novel framework that jointly enhances semantic alignment and multi-view consistency in GT23D generation. At its core, we introduce Triplane Prior Learning (TPL), which effectively learns triplane priors by capturing spatial correspondences across three orthogonal planes using a dedicated Orthogonal Attention mechanism, thereby ensuring geometric consistency across viewpoints. Additionally, we present Prior-based Semantic Aligning in Triplanes (SAT), which enables consistent any-view synthesis by leveraging attention-based feature alignment to reinforce the correspondence between textual semantics and triplane representations. Extensive experiments demonstrate that our method sets a new state-of-the-art in multi-view consistency, while maintaining competitive performance in semantic consistency compared to methods focused solely on semantic alignment. These results emphasize the remarkable ability of our approach to effectively balance and excel in both dimensions, establishing a new benchmark in the field.

To facilitate smart wearable devices or human-like robotics with real-time first-person perspective perception ability, recent researchers proposed the Egocentric Online Action Segmentation (EOAS) task. It requires models to recognize what is happening in egocentric streaming videos and discriminate the starting and ending times of an activity in a real-time manner. However, compared with offline-recorded exocentric videos, egocentric streaming videos cannot provide equivalent sufficient temporal-spatial cues due to the limited perspective and unknown coming frames. Hence, it raises a high demand for the long-term episodic memory ability of models. To this end, most previous approaches work on compressing long-term memory into feature representations. In this paper, we propose a novel EOAS paradigm, termed Parametric Context Memory Learning (PCML), which integrates episodic memory into learnable parameters and keeps dynamic updates according to real-time frames. Concretely, we design the Parametric Context Perception layer and construct a novel Episodic Semantic Memorization Network (ESMN) based on it, which integrates episodic memory into learnable parameters and keeps dynamic updates with real-time frames. We evaluate our proposed method on three public egocentric streaming video benchmarks including EgoPER, EgoProceL, and GTEA. Extensive experiments demonstrate the ESMN model significantly outperforms recent state-of-the-art methods. Our code is available at https://github.com/XunCHN/PCML.

Recently, the adversarial vulnerability of deep neu ral networks (DNNs) has raised increasing attention. Among all the threat models, no-box attacks are the most practical but extremely challenging since they neither rely on any knowledge of the target model or similar substitute model, nor access the dataset for training a new substitute model. Although a recent method has attempted such an attack in a loose sense, its performance is not good enough and computational overhead of training is expensive. In this paper, we move a step forward and show the existence of a training-free adversarial perturbation under the no-box threat model, which can be successfully used to attack different DNNs in real-time. Motivated by our observation that high-frequency component (HFC) is dominant in low-level features and plays a crucial role in classification, we attack an image mainly by suppression of the original HFC and adding of noisy HFC. We empirically and experimentally analyze the requirements of effective noisy HFC and show that it should be regionally homogeneous, repeating and dense. Remarkably, on ImageNet dataset, our method attacks ten well-known models with a success rate of 98.13% on average, which outperforms state-of-the-art no-box attacks by 6.41%. Furthermore, our method is even competitive to mainstream transfer-based black box attacks. Our code is publicly available1

Understanding and predicting the popularity of online User-Generated Content (UGC) is critical for various social and recommendation systems. Existing efforts have focused on extracting predictive features and using pre-trained deep models to learn and fuse multimodal UGC representations. However, the dissemination of social UGCs is not an isolated process in social network; rather, it is influenced by contextual relevant UGCs and various exogenous factors, including social ties, trends, user interests, and platform algorithms. In this work, we propose a retrieval-based framework to enhance the popularity prediction of multimodal UGCs. Our framework extends beyond a simple semantic retrieval, incorporating a meta retrieval strategy that queries a diverse set of relevant UGCs by considering multimodal content semantics, and metadata from user and post. Moreover, to eliminate irrelevant and noisy UGCs in retrieval, we introduce a new measure called Relative Retrieval Contribution to Prediction (RRCP), which selectively refines the retrieved UGCs. We then aggregate the contextual UGC knowledge using vision-language graph neural networks, and fuse them with an RRCP-Attention-based prediction network. Extensive experiments on three large-scale social media datasets demonstrate significant improvements ranging from 26.68% to 48.19% across all metrics compared to strong baselines.

Haonan Zhang, Run Luo, Xiong Liu, Yuchuan Wu, Ting-En Lin, Pengpeng Zeng, Qiang Qu, Feiteng Fang, Min Yang, Lianli Gao, Jingkuan Song, Fei Huang, Yongbin Li. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Prompt tuning (PT) has long been recognized as an effective and efficient paradigm for transferring large pre-trained vision-language models (VLMs) to downstream tasks by learning a tiny set of context vectors. Nevertheless, in this work, we reveal that freezing the parameters of VLMs during learning the context vectors neither facilitates the transferability of pre-trained knowledge nor improves the memory and time efficiency significantly. Upon further investigation, we find that reducing both the length and width of the feature-gradient propagation flows of the full fine-tuning (FT) baseline is key to achieving effective and efficient knowledge transfer. Motivated by this, we propose Skip Tuning, a novel paradigm for adapting VLMs to downstream tasks. Unlike existing PT or adapter-based methods, Skip Tuning applies Layer-wise Skipping (LSkip) and Classwise Skipping (CSkip) upon the FT baseline without introducing extra context vectors or adapter modules. Extensive experiments across a wide spectrum of benchmarks demonstrate the superior effectiveness and efficiency of our Skip Tuning over both PT and adapter-based methods. Code: https://github.com/Koorye/SkipTuning.

Natural Language-based Egocentric Task Verification (NLETV) aims to equip agents to determine if operation flows of procedural tasks in egocentric videos align with natural language instructions. Describing rules with natural language provides generalizable applications, but also raises cross-modal heterogeneity and hierarchical misalignment challenges. In this paper, we proposed a novel approach termed Procedural Heterogeneous Graph Completion (PHGC), which addresses these challenges with heterogeneous graphs representing the logic in rules and operation flows. Specifically, our PHGC method mainly consists of three key components: (1) Heterogeneous Graph Construction module that defines objective states and operation flows as vertices, with temporal and sequential relations as edges. (2) Cross-Modal Path Finding module that aligns semantic relations between hierarchical video and text elements. (3) Discriminative Entity Representation module excavates hidden entities that integrate general logical relations and discriminative cues to reveal final verification results. Additionally, we further constructed a new dataset called CSV-NL comprised of realistic videos. Extensive experiments on the two benchmark datasets covering both digital and physical scenarios, i.e., EgoTV and CSV-NL, demonstrate that our proposed PHGC establishes state-of-the-art performance across different settings. Our code and dataset are available at https://github.com/XunCHN/PHGC.

Cross-Modal Task Verification (CMTV) assesses whether a procedural task is executed accurately according to language-based rules, presenting challenges due to its multi-modal and chronological nature. Existing methods using graph or neuro-symbolic approaches face two issues: (1) Conventional methods only model linear sequential relationships among intra-modal nodes, ignoring implicit relationships between non-neighboring nodes. (2) Directed graphs model pairwise cross-modal relationships but overlook cases where a step corresponds to multiple video segments. To address these issues, we propose Hypergraph-based Sequential Matching (HSM) with two components: (1) Temporal Complementary Hypergraph Module (TCHM), a hierarchical sequential hyperedge construction method that focuses on both sequential connections and implicit relationships across nodes. (2) Step-wise Hypergraph Modeling (SHM), a novel hypergraph-based alignment mechanism that better aligns an action description with multiple video segments, improving task verification accuracy. We evaluate HSM on EgoTV and CTV datasets, demonstrating its superiority over state-of-the-art methods.

Recent large-scale video datasets have facilitated the generation of diverse videos of Video Diffusion Models (VDMs). Nonetheless, some complex actions have still struggled to be generated by those VDMs, leading to a reduction in video generalization. Some researchers attempt to use video editing methods for complex action generation. However, the actions in generated videos are often identical to the reference video, resulting in a lack of diversity. To this end, we first propose Acton In-Context Learning (AICL), a novel approach to generate intricate actions by emulating motions from pre-existing videos in the inference stage using a plug-and-play method. Specifically, the Action Perceiver (AP), is introduced to distill action features from reference videos, which requires training on only a small dataset. Leveraging the knowledge from pre-trained VDMs, Action Integration is introduced for incorporating new action features extracted by AP into VDMs through the additional layers. Extensive experiments demonstrate that AICL is not merely replicating the motion from references, and it significantly improves the generation of realistic actions, even in situations where existing VDMs might directly fail.

By incorporating visual inputs, Multimodal Large Language Models (MLLMs) extend LLMs to support visual reasoning. However, this integration also introduces new vulnerabilities, making MLLMs susceptible to multimodal jailbreak attacks and hindering their safe deployment. Existing defense methods, including Image-to-Text Translation, Safe Prompting, and Multimodal Safety Tuning, attempt to address this by aligning multimodal inputs with LLMs’ built-in safeguards. Yet, they fall short in uncovering root causes of multimodal vulnerabilities, particularly how harmful multimodal tokens trigger jailbreak in MLLMs? Consequently, they remain vulnerable to text-driven multimodal attacks, often exhibiting overdefensive behaviors and imposing heavy training overhead. To bridge this gap, we present an comprehensive analysis of where, how and which harmful multimodal tokens bypass safeguards in MLLMs. Surprisingly, we find that less than 1% tokens in early-middle layers are responsible for inducing unsafe behaviors, highlighting the potential of precisely removing a small subset of harmful tokens, without requiring safety tuning, can still effectively improve safety against jailbreaks. Motivated by this, we propose Safe Prune-then-Restore (SafePTR), an training-free defense framework that selectively prunes harmful tokens at vulnerable layers while restoring benign features at subsequent layers. Without incurring additional computational overhead, SafePTR significantly enhances the safety of MLLMs while preserving efficiency. Extensive evaluations across three MLLMs and five benchmarks demonstrate SafePTR’s state-of-the-art performance in mitigating jailbreak risks without compromising utility.

Multimodal large language models (MLLMs) face an inherent trade-off between faithfulness and creativity, as different tasks require varying degrees of associative reasoning. However, existing methods lack the flexibility to modulate this reasoning strength, limiting MLLMs' adaptability across factual and creative scenarios. To bridge this gap, we propose equipping MLLMs with mechanisms that enable flexible control over associative reasoning. We begin by investigating the internal mechanisms underlying associative behavior in MLLMs and find that: (1) middle layers play a pivotal role in shaping model’s associative tendencies, (2) modifying representations in these layers effectively regulates associative reasoning strength, and (3) hallucinations can be exploited to derive steering vectors that guide this modulation. Building on these findings, we introduce Flexible Association Control (FlexAC), a lightweight and training-free framework for modulating associative behavior in MLLMs. FlexAC first induces hallucination-guided intermediate representations to encode associative directions. Then, it selects high-association instances to construct effective associative steering vectors, whose strengths are adaptively calibrated to balance creative guidance with output stability. Finally, recognizing the multi-dimensional nature of associative reasoning, FlexAC incorporates task-specific associative vectors derived from a forward pass on a few target-domain samples, enabling models to follow diverse associative directions and better adapt to creative tasks. Notably, our method achieves up to a 5.8× improvement in creativity on Creation-MMBench and a 29\% reduction in hallucination rate on CHAIR, surpassing existing baselines and demonstrating its effectiveness in enabling flexible control over associative reasoning in MLLMs. Our code is available at https://github.com/ylhz/FlexAC.

Recent advances in model pre-training give rise to task adaptation-based few-shot learning (FSL), where the goal is to adapt a pre-trained task-agnostic model for capturing task-specific knowledge with a few-labeled support samples of the target task. Nevertheless, existing approaches may still fail in the open world due to the inevitable in-distribution (ID) and out-of-distribution (OOD) noise from both support and query samples of the target task. With limited support samples available, i) the adverse effect of the dual noises can be severely amplified during task adaptation, and ii) the adapted model can produce unreliable predictions on query samples in the presence of the dual noises. In this work, we propose DEnoised Task Adaptation (DETA++) for reliable FSL. DETA++ uses a Contrastive Relevance Aggregation (CoRA) module to calculate image and region weights for support samples, based on which a clean prototype loss and a noise entropy maximization loss are proposed to achieve noise-robust task adaptation. Additionally, DETA++ employs a memory bank to store and refine clean regions for each inner-task class, based on which a Local Nearest Centroid Classifier (LocalNCC) is devised to yield noise-robust predictions on query samples. Moreover, DETA++ utilizes an Intra-class Region Swapping (IntraSwap) strategy to rectify ID class prototypes during task adaptation, enhancing the model's robustness to the dual noises. Extensive experiments demonstrate the effectiveness and flexibility of DETA++.

Approximate nearest neighbor search (ANNS) is a fundamental problem in vector databases and AI infrastructures. Recent graph-based ANNS algorithms have achieved high search accuracy with practical efficiency. Despite the advancements, these algorithms still face performance bottlenecks in production, due to the random memory access patterns of graph-based search and the high computational overheads of vector distance. In addition, the performance of a graph-based ANNS algorithm is highly sensitive to parameters, while selecting the optimal parameters is cost-prohibitive, e.g., manual tuning requires repeatedly re-building the index. This paper introduces VSAG , an open-source framework that aims to enhance the in production performance of graph-based ANNS algorithms. VSAG has been deployed at scale in the services of Ant Group, and it incorporates three key optimizations: ( i) efficient memory access : it reduces L3 cache misses with pre-fetching and cache-friendly vector organization; ( ii) automated parameter tuning : it automatically selects performance-optimal parameters without requiring index rebuilding; ( iii) efficient distance computation : it leverages modern hardware, scalar quantization, and smartly switches to low-precision representation to dramatically reduce the distance computation costs. We evaluate VSAG on real-world datasets. The experimental results show that VSAG achieves the state-of-the-art performance and provides up to 4× speedup over HNSWlib (an industry-standard library) while ensuring the same accuracy.

Adapting large-scale image-text pre-training models, e.g., CLIP, to the video domain represents the current state-of-the-art for text-video retrieval. The primary approaches involve transferring text-video pairs to a common embedding space and leveraging cross-modal interactions on specific entities for semantic alignment. Though effective, these paradigms entail prohibitive computational costs, leading to inefficient retrieval. To address this, we propose a simple yet effective method, Global-Local Semantic Consistent Learning (GLSCL), which capitalizes on latent shared semantics across modalities for text-video retrieval. Specifically, we introduce a parameter-free global interaction module to explore coarse-grained alignment. Then, we devise a shared local interaction module that employs several learnable queries to capture latent semantic concepts for learning fine-grained alignment. Furthermore, an Inter-Consistency Loss (ICL) is devised to accomplish the concept alignment between the visual query and corresponding textual query, and an Intra-Diversity Loss (IDL) is developed to repulse the distribution within visual (textual) queries to generate more discriminative concepts. Extensive experiments on five widely used benchmarks (i.e., MSR-VTT, MSVD, DiDeMo, LSMDC, and ActivityNet) substantiate the superior effectiveness and efficiency of the proposed method. Remarkably, our method achieves comparable performance with SOTA as well as being nearly 220 times faster in terms of computational cost. Code is available at: https://github.com/zchoi/GLSCL.

Despite demonstrating impressive capabilities in comprehending multi-modal contexts, large vision-language models (LVLMs) are invariably prone to generate unreliable answers, i.e., hallucinations. Existing methods mainly mitigate this hallucination by introducing specific designed datasets or employing contrastive decoding techniques. However, these methods heavily rely on the quality of constructed datasets and negative samples, overlooking the inherent ambiguity in reasoning caused by over-reliance on linguistic priors and data complexity, termed reasoning uncertainty. This oversight hinders the models from effectively identifying the causal relationships behind each token, increasing their susceptibility to hallucinations. To address this issue, we propose a novel framework namedReasoningUncertainty-guidedRefinement (RUR)for mitigating hallucinations in LVLMs from an uncertainty perspective. Specifically, unlike conventional uncertainty quantification methods, we first extract the causal reasoning relationships between tokens by exploiting the link between structural causal models and the Transformer architecture. Based on this relationship, we then employ the Subjective Logic principle to model the reasoning uncertainty at both token and sentence levels, which reflects the unreliability degree of generated tokens and sentences. Finally, guided by reasoning uncertainty, we develop multi-level uncertainty-based adjustment to eliminate deceptive tokens exhibiting severe uncertainty and mitigate potential hallucinations in sentences. Extensive experiments demonstrate that our RUR method consistently achieves state-of-the-art performance on five benchmarks.

Normalizing flows, a category of probabilistic models famed for their capabilities in modeling complex data distributions, have exhibited remarkable efficacy in unsupervised anomaly detection. This paper explores the potential of normalizing flows in multi-class anomaly detection, wherein the normal data is compounded with multiple classes without providing class labels. Through the integration of vector quantization (VQ), we empower the flow models to distinguish different concepts of multi-class normal data in an unsupervised manner, resulting in a novel flow-based unified method, named VQ-Flow. Specifically, our VQ-Flow leverages hierarchical vector quantization to estimate two relative codebooks: a Conceptual Prototype Codebook (CPC) for concept distinction and its concomitant Concept-Specific Pattern Codebook (CSPC) to capture concept-specific normal patterns. The flow models in VQ-Flow are conditioned on the concept-specific patterns captured in CSPC, capable of modeling specific normal patterns associated with different concepts. Moreover, CPC further enables our VQ-Flow for concept-aware distribution modeling, faithfully mimicking the intricate multi-class normal distribution through a mixed Gaussian distribution reparametrized on the conceptual prototypes. Through the introduction of vector quantization, the proposed VQ-Flow advances the state-of-the-art in multi-class anomaly detection within a unified training scheme, yielding the Det./Loc. AUROC of 99.5%/98.3% on MVTec AD.

Unsupervised anomaly detection (UAD) attracts a lot of research interest and drives widespread applications, where only anomaly-free samples are available for training. Some UAD applications intend to locate the anomalous regions further even without any anomaly information. Although the absence of anomalous samples and annotations deteriorates the UAD performance, an inconspicuous, yet powerful statistics model, the normalizing flows, is appropriate for anomaly detection (AD) and localization in an unsupervised fashion. The flow-based probabilistic models, only trained on anomaly-free data, can efficiently distinguish unpredictable anomalies by assigning them much lower likelihoods than normal data. Nevertheless, the size variation of unpredictable anomalies introduces another inconvenience to the flow-based methods for high-precision AD and localization. To generalize the anomaly size variation, we propose a novel multiscale flow-based framework (MSFlow) composed of asymmetrical parallel flows followed by a fusion flow to exchange multiscale perceptions. Moreover, different multiscale aggregation strategies are adopted for image-wise AD and pixel-wise anomaly localization according to the discrepancy between them. The proposed MSFlow is evaluated on three AD datasets, significantly outperforming existing methods. Notably, on the challenging MVTec AD benchmark, our MSFlow achieves a new state-of-the-art (SOTA) with a detection AUORC score of up to 99.7%, localization AUCROC score of 98.8% and PRO score of 97.1%.

Recently Text-to-Video (T2V) synthesis has undergone a breakthrough by training transformers or diffusion models on large-scale datasets. Nevertheless, inferring such large models incurs huge costs. Previous inference acceleration works either require costly retraining or are model-specific. To address this issue, instead of retraining we explore the inference process of two mainstream T2V models using transformers and diffusion models. The exploration reveals the redundancy in temporal attention modules of both models, which are commonly utilized to establish temporal relations among frames. Consequently, we propose a training-free and generalized pruning strategy called F3-Pruning to prune redundant temporal attention weights. Specifically, when aggregate temporal attention values are ranked below a certain ratio, corresponding weights will be pruned. Extensive experiments on three datasets using a classic transformer-based model CogVideo and a typical diffusion-based model Tune-A-Video verify the effectiveness of F3-Pruning in inference acceleration, quality assurance and broad applicability.

The goal of Universal Cross-Domain Retrieval (UCDR) is to achieve robust performance in generalized test scenarios, wherein data may belong to strictly unknown do-mains and categories during training. Recently, pre-trained models with prompt tuning have shown strong generalization capabilities and attained noteworthy achievements in various downstream tasks, such as few-shot learning and video-text retrieval. However, applying them directly to UCDR may not be sufficient to handle both domain shift (i.e., adapting to unfamiliar domains) and semantic shift (i.e., transferring to unknown categories). To this end, we propose Prompting-to-Simulate (ProS), the first method to apply prompt tuning for UCDR. ProS employs a two-step process to simulate Content-aware Dynamic Prompts (CaDP) which can impact models to produce generalized features for UCDR. Concretely, in Prompt Units Learning stage, we introduce two Prompt Units to individually capture domain and semantic knowledge in a mask-and-align way. Then, in Context-aware Simulator Learning stage, we train a Content-aware Prompt Simulator under a simulated test scenario to produce the corresponding CaDP. Extensive experiments conducted on three benchmark datasets show that our method achieves new state-of-the-art performance without bringing excessive parameters. Code is available at https://github.com/fangkaipeng/ProS.

This work breaks through the Base-New Tradeoff (BNT) dilemma in prompt tuning, i.e., the better the tuned model generalizes to the base (or target) task, the worse it generalizes to new tasks, and vice versa. Specifically, through an in-depth analysis of the learned features of the base and new tasks, we observe that the BNT stems from a channel bias issue - the vast majority of feature channels are occupied by base-specific knowledge, leading to the collapse of task-shared knowledge important to new tasks. To address this, we propose the Decoupled Prompt Tuning (DePT) framework, which decouples base-specific knowledge from feature channels into an isolated feature space during prompt tuning, so as to maximally preserve task-shared knowl-edge in the original feature space for achieving better zero-shot generalization on new tasks. Importantly, our DePT is orthogonal to existing prompt tuning approaches, and can enhance them with negligible additional computational cost. Extensive experiments on several datasets show the flexibility and effectiveness of DePT. Code is available at https://github.com/Koorye/DePT.

The video composition task aims to integrate specified foregrounds and backgrounds from different videos into a harmonious composite. Current approaches, predominantly trained on videos with adjusted foreground color and lighting, struggle to address deep semantic disparities beyond superficial adjustments, such as domain gaps. Therefore, we propose a training-free pipeline employing a pre-trained diffusion model imbued with semantic prior knowledge, which can process composite videos with broader semantic disparities. Specifically, we process the video frames in a cascading manner and handle each frame in two processes with the diffusion model. In the inversion process, we propose Balanced Partial Inversion to obtain generation initial points that balance reversibility and modifiability. Then, in the generation process, we further propose Inter-Frame Augmented attention to augment foreground continuity across frames. Experimental results reveal that our pipeline successfully ensures the visual harmony and inter-frame coherence of the outputs, demonstrating efficacy in managing broader semantic disparities.

Binarization demonstrates significant advantages in resource-limited devices, particularly for recent Vision Transformers (ViTs). To alleviate performance degradation during binarization, Knowledge Distillation (KD) is a crucial and beneficial technique. However, we identify that distilling ViTs in conventional methods overlooks high-frequency information, which loses fine-grained features and results in performance degradation. To address this challenge, we introduce a plug-and-play Binarized Frequency-enhanced Distillation (BFD) to preserve high-frequency information effectively. Specifically, High-Frequency Enhanced Distillation (HFED) is proposed to transmit attention maps from teacher to student in frequency domain, which enhances high-frequency information. Additionally, based on the finding that the frequency proportion varies across different layers, we further propose Progressive Frequency Partitioning (PFP) to distinguish frequency flexibly. Extensive experiments demonstrate the effectiveness of our BFD across a set of ViT variants. We demonstrate superior performance of 51.65% over ViT-B on TinyImageNet, and outperform SOTA by a substantial margin of 20.70% on ImageNet.

Parameter-efficient fine-tuning (PEFT), updating only a small set of parameters either inherently in the model or additionally introduced, reduces the cost of adaptation of large vision models (e.g. Vision Transformers) and avoids overfitting to few-shot samples. However, the selection of parameters to update often follows heuristic criteria, thus lacking systematic analysis and may lead to suboptimal results. In this work, we adopt the concept of skilled parameter localization (SPL) from the NLP community, which can identify the location of task-specific parameters in a fine-tuned model automatically given any task. By applying this technique to ViTs, we observe that while the task-specific (skilled) parameters scatter in the parameter space across different tasks, the out-projection bias of attention and MLP layers are often concentrated with these skilled parameters. Inspired by this, we propose Out-projection Bias Fine-Tuning, or OBFT, a simple yet effective PEFT method that conducts few-shot adaptation solely relying on the out-projection bias of attention and MLP modules in pre-trained ViTs. We demonstrate the effectiveness and efficiency of our OBFT over 10 diverse datasets: 1) OBFT achieves superior parameter efficiency than a broad spectrum of PEFT strategies; 2) by updating only 0.01% parameters of ViTs, OBFT attains comparable performance with full fine-tuning, while significantly reducing training costs, as it does not need to maintain optimizer states for most parameters.

Temporal Sentence Grounding (TSG), which aims to localize events in untrimmed videos with a given language query, has been widely studied in the last decades. However, recently researchers have demonstrated that previous approaches are severely limited in out-of-distribution generalization, thus proposing the De-biased TSG challenge which requires models to overcome weakness towards outlier test samples. In this paper, we design a novel framework, termed Counterfactually-Augmented Event Matching (CAEM), which incorporates counterfactual data augmentation to learn event-query joint representations to resist the training bias. Specifically, it consists of three components: (1) A Temporal Counterfactual Augmentation module that generates counterfactual video-text pairs by temporally delaying events in the untrimmed video, enhancing the model's capacity for counterfactual thinking. (2) An Event-Query Matching model that is used to learn joint representations and predict corresponding matching scores for each event candidate. (3) A Counterfact-Adaptive Framework (CAF) that incorporates the counterfactual consistency rules on the matching process of the same event-query pairs, furtherly mitigating the bias learned from training sets. We conduct thorough experiments on two widely used DTSG datasets, i.e., Charades-CD and ActivityNet-CD, to evaluate our proposed CAEM method. Extensive experimental results show our proposed CAEM method outperforms recent state-of-the-art methods on all datasets. Our implementation code is available at https://github.com/CFM-MSG/CAEM_Code.

Visual effects synthesis is crucial in the film and television industry, which aims at enhancing raw footage with virtual elements for greater expressiveness. As the demand for detailed and realistic effects escalates in modern production, professionals are compelled to allocate substantial time and resources to this endeavor. Thus, there is an urgent need to explore more convenient and less resource-intensive methods, such as incorporating the burgeoning Artificial Intelligence Generated Content (AIGC) technology. However, research into this potential integration has yet to be conducted. As the first work to establish a connection between visual effects synthesis and AIGC technology, we start by carefully setting up two paradigms according to the need for pre-produced effects or not: synthesis with reference effects and synthesis without reference effects. Following this, we compile a dataset by processing a collection of effects videos and scene videos, which contains a wide variety of effect categories and scenarios, adequately covering the common effects seen in films and television industry. Furthermore, we explore the capabilities of a pre-trained text-to-video model to synthesize visual effects within these two paradigms. The experimental results demonstrate that the pipeline we established can effectively produce impressive visual effects synthesis outcomes, thereby evidencing the significant potential of existing AIGC technology for application in visual effects synthesis tasks. Our dataset can be found in https://github.com/ruffiann/MagicVFX.

Binarized Vision Transformers (BiViTs) aim to facilitate the efficient and lightweight utilization of Vision Transformers (ViTs) on devices with limited computational resources. Yet, the current approach to binarizing ViT leads to a substantial performance decrease compared to the full-precision model, posing obstacles to practical deployment. By empirical study, we reveal that spatial interaction (SI) is a critical factor that impacts performance due to lack of token-level correlation, but previous work ignores this factor. To this end, we design a ViT binarization approach dubbed SI-BiViT to incorporate spatial interaction in the binarization process. Specifically, an SI module is placed alongside the Multi-Layer Perceptron (MLP) module to formulate the dual-branch structure. This structure not only leverages knowledge from pre-trained ViTs by distilling over the original MLP, but also enhances spatial interaction via the introduced SI module. Correspondingly, we design a decoupled training strategy to train these two branches more effectively. Importantly, our SI-BiViT is orthogonal to existing Binarized ViTs approaches and can be directly plugged. Extensive experiments demonstrate the strong flexibility and effectiveness of SI-BiViT by plugging our method into four classic ViT backbones in supporting three downstream tasks, including classification, detection, and segmentation. In particular, SI-BiViT enhances the classification performance of binarized ViTs by an average of 10.52% in Top-1 accuracy compared to the previous state-of-the-art. Codes are available at https://github.com/VL-Group/SI-BiViT

Recently, significant advancements have been made in supporting text-video retrieval by transferring large-scale image-text pre-training models through model adaptation, i.e., full fine-tuning, or prompt tuning, a parameter-efficient fine-tuning strategy. While full fine-tuning involves high computational costs, particularly with increasing model size, prompt tuning offers greater flexibility and efficiency by adjusting only a few learnable parameters. However, current prompt tuning methods rely on coarse visual and textual cues for text-video retrieval task, neglecting the domain-specific features when performing the adaptation. This approach may lead to sub-optimal performance due to the incorporation of irrelevant and indiscriminate knowledge. To address such an issue, we present a Multi-grained Prompt Tuning (MPT) for text-video retrieval, that designs a variety of specific prompts to effectively explore semantic interaction across different modalities with diverse granularity. Specifically, we devise a multi-grained video encoder that employs spatial, temporal, and global prompts to transfer the base-generic knowledge from the image-text pre-trained model while comprehensively excavating determinative video-specific characteristics. Meanwhile, we introduce a novel multi-grained text encoder aimed at capturing various levels of textual clues through the utilization of word and phrase prompts. Extensive experiments on four benchmark datasets, i.e., MSR-VTT, ActivityNet, DiDeMo, and LSMDC, demonstrate that MPT achieves outstanding performance, surpassing state-of-the-art methods with negligible computational cost. The codebase is publicly available at: https://github.com/zchoi/MPT.

Instruction tuning demonstrates impressive performance in adapting Multimodal Large Language Models (MLLMs) to follow task instructions and improve generalization ability. By extending tuning across diverse tasks, MLLMs can further enhance their understanding of world knowledge and instruction intent. However, continual instruction tuning has been largely overlooked and there are no public benchmarks available. In this paper, we present CoIN, a comprehensive benchmark tailored for assessing the behavior of existing MLLMs under continual instruction tuning. CoIN comprises 10 meticulously crafted datasets spanning 8 tasks, ensuring diversity and serving as a robust evaluation framework to assess crucial aspects of continual instruction tuning, such as task order, instruction diversity and volume. Additionally, apart from traditional evaluation, we design another LLM-based metric to assess the knowledge preserved within MLLMs for reasoning. Following an in-depth evaluation of several MLLMs, we demonstrate that they still suffer catastrophic forgetting, and the failure in instruction alignment assumes the main responsibility, instead of reasoning knowledge forgetting. To this end, we introduce MoELoRA which is effective in retaining the previous instruction alignment.

Although Large Visual Language Models (LVLMs) have demonstrated exceptional abilities in understanding multimodal data, they invariably suffer from hallucinations, leading to a disconnection between the generated text and the corresponding images. Almost all current visual contrastive decoding methods attempt to mitigate these hallucinations by introducing visual uncertainty information that appropriately widens the contrastive logits gap between hallucinatory and targeted ones. However, due to uncontrollable nature of the global visual uncertainty, they struggle to precisely induce the hallucinatory tokens, which severely limits their effectiveness in mitigating hallucinations and may even lead to the generation of undesired hallucinations. To tackle this issue, we conducted the theoretical analysis to promote the effectiveness of contrast decoding. Building on this insight, we introduce a novel optimization strategy named Hallucination-Induced Optimization (HIO). This strategy seeks to amplify the contrast between hallucinatory and targeted tokens relying on a fine-tuned theoretical preference model (i.e., Contrary Bradley-Terry Model), thereby facilitating efficient contrast decoding to alleviate hallucinations in LVLMs. Extensive experimental research demonstrates that our HIO strategy can effectively reduce hallucinations in LVLMs, outperforming state-of-the-art methods across various benchmarks.

Unsupervised cross-domain image retrieval is designed to facilitate the retrieval between images in different domains in an unsupervised way. Without the guidance of labels, both intra-domain semantic learning and inter-domain semantic alignment pose significant challenges to the model's learning process. The resolution of these challenges relies on the accurate capture of domain-invariant semantic features by the model. Based on this consideration, we propose our Semantic-Attended Mixture of Experts (SA-MoE) model. Leveraging the proficiency of MoE network in capturing visual features, we enhance the model's focus on semantically relevant features through a series of strategies. We first utilize the self-attention mechanism of Vision Transformer to adaptively collect information with different weights on instances from different domains. In addition, we introduce contextual semantic association metrics to more accurately measure the semantic relatedness between instances. By utilizing the association metrics, secondary clustering is performed in the feature space to reinforce semantic relationships. Finally, we employ the metrics for information selection on the fused data to remove the semantic noise. We conduct extensive experiments on three widely used datasets. The consistent comparison results with existing methods indicate that our model possesses the state-of-the-art performance.

Replacing objects in images is a practical functionality of Photoshop, e.g., clothes changing. This task is defined as Unsupervised Deformable-Instances Image-to-Image Translation (UDIT), which maps multiple foreground instances of a source domain to a target domain, involving significant changes in shape. Although previous works incorporate instance masks of source domain for instance shape indication, their translation still fails in shape because of inadequate utilization of shape information in masks. To mitigate this issue, we introduce an effective two-stage pipeline for UDIT called Mask-Guided Deformable-instances GAN++ (MGD-GAN++), which generates target masks in the first stage named Mask Morph and utilizes the masks to guide the synthesis of corresponding instances in the second stage named Mask-Guided Image Generation. To further provide sufficient supervision with existing unpaired datasets, an overall set of training schemes is proposed for the two stages of MGD-GAN++, coined as Aligned Supervision and Inpainting Supervision, respectively. Extensive experiments on four datasets demonstrate the significant advantages of our MGD-GAN++ over existing methods both quantitatively and qualitatively. Furthermore, our training time consumption is hugely reduced compared to the state-of-the-art.

The existing approaches to image captioning tend to adopt Transformer-based architectures with grid features, which represent the state-of-the-art. However, the strategies are prone to address the grid features with a fixed resolution, which often hampers the perception of entities with various scales. In addition, directly applying them may also result in spatial and fine-grained semantic information loss. To this end, we propose a simple yet effective method, named Spatial Pyramid Transformer (SPT). Specifically, it adopts several parameter-shared pyramid structures to perform semantic interactions across different grid resolutions. In each layer, we design a Spatial-aware Pseudo-supervised (SP) module, which aims to adaptively resort to disrupted spatial information among flatted grid features. Moreover, to maintain the model size and enhance semantics, we build a simple weighted residual connection termed as Scale-wise Reinforcement (SR) module to simultaneously explore both low- and high-level encoded features. Extensive experiments on the MS-COCO benchmark demonstrate that our method achieves new state-of-the-art performance without bringing excessive parameters compared with vanilla transformer. In addition, our method is extended to the video captioning task, which further proves the practicability of the proposed method. Code is available at https://github.com/zchoi/SPT.

Prompt tuning, an emerging parameter-efficient strategy, leverages the powerful knowledge of large-scale pre-trained image-text models (e.g., CLIP) to swiftly adapt to downstream tasks. Despite its effectiveness, adapting prompt tuning to text-video retrieval encounters two limitations: i) existing methods adopt two isolated prompt tokens to prompt two modal branches separately, making it challenging to learn a well-aligned unified representation, i.e., modality gap; ii) video encoders typically utilize a fixed pre-trained visual backbone, neglecting the incorporation of spatial-temporal information. To this end, we propose a simple yet effective method, named Unified Modality-aware Prompt Tuning (UMP), for text-video retrieval. Concretely, we first introduce a Unified Prompt Generation (UPG) module to dynamically produce modality-aware prompt tokens, enabling the perception of prior semantic information on both video and text inputs. These prompt tokens are simultaneously injected into two branches that can bridge the semantics gap between two modalities in a unified-adjusting manner. Then, we design a parameter-free Spatial-Temporal Shift (STS) module to facilitate both intra- and inter-communication among video tokens and prompt tokens in the spatial-temporal dimension. Notably, extensive experiments on four widely used benchmarks show that UMP achieves new state-of-the-art performance compared to existing prompt-tuning methods without bringing excessive parameters. Code is available at:https://github.com/zchoi/UMP_TVR.

In weakly supervised video anomaly detection (WVAD), where only video-level labels indicating the presence or absence of abnormal events are available, the primary challenge arises from the inherent ambiguity in temporal annotations of abnormal occurrences. Inspired by the statistical insight that temporal features of abnormal events often exhibit outlier characteristics, we propose a novel method, BN-WVAD, which incorporates BatchNorm into WVAD. In the proposed BN-WVAD, we leverage the Divergence of Feature from the Mean vector (DFM) of BatchNorm as a reliable abnormality criterion to discern potential abnormal snippets in abnormal videos. The proposed DFM criterion is also discriminative for anomaly recognition and more resilient to label noise, serving as the additional anomaly score to amend the prediction of the anomaly classifier that is susceptible to noisy labels. Moreover, a batch-level selection strategy is devised to filter more abnormal snippets in videos where more abnormal events occur. The proposed BN-WVAD model demonstrates state-of-the-art performance on UCF-Crime with an AUC of 87.24%, and XD-Violence, where AP reaches up to 84.93%. Our code implementation is accessible athttps://github.com/cool-xuan/BN-WVAD.

Existing methods of multiple human parsing (MHP) apply deep models to learn instance-level representations for segmenting each person into non-overlapped body parts. However, learned representations often contain many spurious correlations that degrade model generalization, leading learned models to be vulnerable to visually contextual variations in images (e.g., unseen image styles/external interventions). To tackle this, we present a causal property integrated parsing model termed CPI-Parser, which is driven by fundamental causal principles involving two causal properties for human parsing (i.e., the causal diversity and the causal invariance). Specifically, we assume that an image is constructed by a mix of causal factors (the characteristics of body parts) and non-causal factors (external contexts), where only the former ones decide the essence of human parsing. Since causal/non-causal factors are unobservable, the proposed CPI-Parser is required to separate key factors that satisfy the causal properties from an image. In this way, the parser is able to rely on causal factors w.r.t relevant evidence rather than non-causal factors w.r.t spurious correlations, thus alleviating model degradation and yielding improved parsing ability. Notably, the CPI-Parser is designed in a flexible way and can be integrated into any existing MHP frameworks. Extensive experiments conducted on three widely used benchmarks demonstrate the effectiveness and generalizability of our method. Code and models are released (https://github.com/HAG-uestc/CPI-Parser) for research purpose.

In real-world datasets, visually related images often form clusters, and these clusters can be further grouped into larger categories with more general semantics. These inherent hierarchical structures can help capture the underlying distribution of data, making it easier to learn robust hash codes that lead to better retrieval performance. However, existing methods fail to make use of this hierarchical information, which in turn prevents the accurate preservation of relationships between data points in the learned hash codes, resulting in suboptimal performance. In this paper, our focus is on applying visual hierarchical information to self-supervised hash learning and addressing three key challenges, including the construction, embedding, and exploitation of visual hierarchies. We propose a new self-supervised hashing method named Hierarchical Hyperbolic Contrastive Hashing (HHCH), making breakthroughs in three aspects. First, we propose to embed continuous hash codes into hyperbolic space for accurate semantic expression since embedding hierarchies in the hyperbolic space generates less distortion than in the hyper-sphere or Euclidean space. Second, we update the K-Means algorithm to make it run in the hyperbolic space. The proposed hierarchical hyperbolic K-Means algorithm can achieve the adaptive construction of hierarchical semantic structures. Last but not least, to exploit the hierarchical semantic structures in hyperbolic space, we propose the hierarchical contrastive learning algorithm, including hierarchical instance-wise and hierarchical prototype-wise contrastive learning. Extensive experiments on four benchmark datasets demonstrate that the proposed method outperforms state-of-the-art self-supervised hashing methods. Our codes are released at https://github.com/HUST-IDSM-AI/HHCH.git.

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.

When dealing with crowds, occlusions, and truncations in complex scenes, existing solutions for multi-person pose estimation remain challenging. This is because all examples are randomly organized and equally treated by previous methods during training, which ignores that examples vary significantly in their difficulty levels. Once trained, hard examples are underutilized due to the high proportion of simple training examples, resulting in poor model robustness for complex scenes. To tackle this, we propose a novel training strategy termedDMH-CLfor complex pose estimation, brought from curriculum learning (CL) which mainly addresses easy examples in the early training stage and hard ones in the later stage. Different from typical CL methods, we define easy/hard examples via mining both the dataset-specific statistical difficulty and the multi-model evaluated difficulty. After that, we adopt an annealing arrangement strategy to construct learning courses from easy to hard. Furthermore, we introduce a model learning feedback indicator, i.e.,Dynamic Model Hardness (DMH)to conduct course scheduling, and to explicitly explore hard poses and utilize the knowledge learned from easy poses to better handle complex scenes as well. Our DMH-CL is model-agnostic and can be easily applied to various pose estimators including single-stage models and two-stage models, and achieves significant improvements on two challenging benchmarks especially for complex scenes. Notably, it achieves substantial performance gains of 2.6% and 4.6% for hard poses compared to the strong single-stage model PETR on CrowdPose and COCO datasets, respectively. Source codes and models are publicly available online.

The susceptibility of deep neural networks (DNNs) to adversarial examples has raised significant concerns regarding the security and reliability of artificial intelligence systems. These examples contain maliciously crafted perturbations not perceptible to the human eye but can cause the model to make wrong predictions. Adversarial training (AT) is the de facto standard method for enhancing adversarial robustness. However, the improved robustness is often at the cost of a significant drop in standard accuracy for clean samples. Numerous works have attempted to alleviate this trade-off by identifying its causes. A key factor lies in the variability of clean samples, which leads to different adversarial examples being generated using the same attack strategy. The other factor is the disruption of the underlying data structure caused by adversarial perturbations. To overcome these challenges, we propose a novel adversarial training framework named Hardness-Guided Sample-Dependent Adversarial Training (HGSD-AT), which dynamically adjusts the attack strategy based on the hardness of the current adversarial sample to further improve the robustness of the model. By utilizing the two types of constraints which construct from a temporal perspective and spatial distribution perspective, our method directly learns the impact of attack methods on the model, rather than the indirect effects associated with sample distribution. This approach aims to improve the generation of adversarial examples while simultaneously enhancing the robustness and accuracy of DNNs. Our approach exhibits superior performance in terms of both robustness and natural accuracy compared to state-of-the-art defense methods, as validated through comprehensive experiments conducted on three benchmark datasets.

Video captioning focuses on generating natural language descriptions according to the video content. Existing works mainly explore this multimodal learning with the paired source video and corresponding sentence, which have achieved competitive performances. Nonetheless, learning from video-description pair cannot capture implicit external knowledge, i.e., multiple visual context information and linguistic clues existing in the video-language dataset, which may limit the cognitive capability of the model to generate diverse descriptions. To this end, we propose a Memory-based Augmentation Network (MAN), in which a memory structure is designed to augment the current encoder-decoder framework by incorporating implicit external knowledge with a neural memory. Specifically, we first propose a visual memory for the encoder to store multiple visual contexts across videos in the dataset, which is utilized to obtain memory-augmented contextual features for the source video. In addition, a textual memory is introduced for the decoder to capture the external language clues across sentences in the dataset. It is adapted to capture memory-augmented language features in each time step. The proposed approach is able to capture comprehensive contextual understanding compared to the basic encoder-decoder framework, which is more compatible with the human cognitive process. Extensive experiments on three video captioning datasets including MSVD, MSR-VTT, and VATEX demonstrate the effectiveness of the proposed method.

Multimodal Conditional Image Synthesis(MCIS) aims to generate images according to different modalities input and their combination, which allows users to describe their requirements in complementary ways, e.g. segmentation for shapes and text for attributes. Despite satisfying results in MCIS, a non-trivial issue is neglected. Some modalities are fully optimized and dominate the generation, while other modalities are sub-optimized and fail to contribute their complementary information. We coin this phenomenon as Modality Bias.Our analysis reveals that generative models own greedy nature. Specifically, the modality that shares less semantic gap with the synthesized modality will be greedily incorporated and thus takes a larger proportion in synthesis. The main idea of previous works in Modality Bias is to punish the greedy nature, which hurts the performance of dominant modalities and impedes their contribution to multimodal synthesis. Instead, we propose to utilize the greedy nature by setting dominant modalities as guidance for sub-optimized modalities through coordinated feature space, named Coordinated Knowledge Mining. Afterwards, improved uni-modalities are aggregated by fusing coordinated features to further boost the performance of multimodal image synthesis, called Coordinated Knowledge Fusion. Extensive experiments prove that our method not only increases uni-modal performance by a large margin, but also promotes multimodal image synthesis by fully utilizing complementary information from different modalities.

Building multi-person pose estimation (MPPE) models that can handle complex foreground and uncommon scenes is an important challenge in computer vision. Aside from designing novel models, strengthening training data is a promising direction but remains largely unexploited for the MPPE task. In this article, we systematically identify the key deficiencies of existing pose datasets that prevent the power of well-designed models from being fully exploited and propose the corresponding solutions. Specifically, we find that the traditional data augmentation techniques are inadequate in addressing the two key deficiencies, imbalanced instance complexity (IC) (evaluated by our new metric IC) and insufficient realistic scenes. To overcome these deficiencies, we propose a model-agnostic full-view data generation (Full-DG) method to enrich the training data from the perspectives of both poses and scenes. By hallucinating images with more balanced pose complexity and richer real-world scenes, Full-DG can help improve pose estimators' robustness and generalizability. In addition, we introduce a plug-and-play adaptive category-aware loss (AC-loss) to alleviate the severe pixel-level imbalance between keypoints and backgrounds (i.e., around 1:600). Full-DG together with AC-loss can be readily applied to both the bottom-up and top-down models to improve their accuracy. Notably, plugging into the representative estimators HigherHRNet and HRNet, our method achieves substantial performance gains of 1.0%-2.9% AP on the COCO benchmark, and 1.0%-5.1% AP on the CrowdPose benchmark.

Current Scene Graph Generation (SGG) methods explore contextual information to predict relationships among entity pairs. However, due to the diverse visual appearance of numerous possible subject-object combinations, there is a large intra-class variation within each predicate category, e.g., “man-eating-pizza, giraffe-eating-leaf”, and the severe inter-class similarity between different classes, e.g., “man-holding-plate, man-eating-pizza”, in model's latent space. The above challenges prevent current SGG methods from acquiring robust features for reliable relation prediction. In this paper, we claim that the predicate's category-inherent semantics can serve as class-wise prototypes in the semantic space for relieving the challenges. To the end, we propose the Prototype-based Embedding Network (PE-Net), which models entities/predicates with prototype-aligned compact and distinctive representations and thereby establishes matching between entity pairs and predicates in a common embedding space for relation recognition. Moreover, Prototype-guided Learning (PL) is introduced to help PE-Net efficiently learn such entity-predicate matching, and Prototype Regularization (PR) is devised to relieve the ambiguous entity-predicate matching caused by the predicate's semantic overlap. Extensive experiments demonstrate that our method gains superior relation recognition capability on SGG, achieving new state-of-the-art performances on both Visual Genome and Open Images datasets. The codes are available at https://github.com/VL-Group/PENET.

Domain generalization person re-identification (DG-ReID) aims to train a model on source domains and generalize well on unseen domains. Vision Transformer usually yields better generalization ability than common CNN networks under distribution shifts. However, Transformer-based ReID models inevitably over-fit to domain-specific biases due to the supervised learning strategy on the source domain. We observe that while the global images of different IDs should have different features, their similar local parts (e.g., black backpack) are not bounded by this constraint. Motivated by this, we propose a pure Transformer model (termed Part-aware Transformer) for DG-ReID by designing a proxy task, named Cross-ID Similarity Learning (CSL), to mine local visual information shared by different IDs. This proxy task allows the model to learn generic features because it only cares about the visual similarity of the parts regardless of the ID labels, thus alleviating the side effect of domain-specific biases. Based on the local similarity obtained in CSL, a Part-guided Self-Distillation (PSD) is proposed to further improve the generalization of global features. Our method achieves state-of-the-art performance under most DG ReID settings. The code is available at https://github.com/liyuke65535/Part-Aware-Transformer.

Test-time task adaptation in few-shot learning aims to adapt a pre-trained task-agnostic model for capturing task-specific knowledge of the test task, rely only on few-labeled support samples. Previous approaches generally focus on developing advanced algorithms to achieve the goal, while neglecting the inherent problems of the given support samples. In fact, with only a handful of samples available, the adverse effect of either the image noise (a.k.a. X-noise) or the label noise (a.k.a. Y-noise) from support samples can be severely amplified. To address this challenge, in this work we propose DEnoised Task Adaptation (DETA), a first, unified image- and label-denoising framework orthogonal to existing task adaptation approaches. Without extra supervision, DETA filters out task-irrelevant, noisy representations by taking advantage of both global visual information and local region details of support samples. On the challenging Meta-Dataset, DETA consistently improves the performance of a broad spectrum of baseline methods applied on various pre-trained models. Notably, by tackling the overlooked image noise in Meta-Dataset, DETA establishes new state-of-the-art results. Code is released at https://github.com/JimZAI/DETA.

Existing solutions to lightweight human pose estimation typically adopt a depthwise separable strategy, i.e., a normal 2D convolution is factorized into channel aggregation and spatial aggregation. However, this strategy cannot well capture multi-scale Effective Receptive Field (ERF), which is essential to dense prediction tasks like human pose estimation. To address this issue, we propose a novel lightweight network for human pose estimation, namely effective aggregation net (EANet). In EANet, we introduce two lightweight computational units: effective channel aggregating (ECA) and effective spatial aggregating (ESA), which are respectively responsible for channel-wise feature aggregation and pixel-wise feature aggregation. Unlike typical channel-wise aggregation using pointwise (1 × 1) convolution, the ECA aggregates few feature points that are estimated as effective ones. Moreover, the ESA is designed with re-parameterizing techniques, and it aggregates effective spatial feature points with multi-scale shared convolutions. Comprehensive experiments are conducted on three challenging datasets, i.e., COCO, Crowd-Pose, Wholebody-COCO. Our EANet demonstrates superior results on human pose estimation over previous lightweight methods, reaching a new state-of-the-art performance with a good trade-off. Our code and models are publicly available1.

For black-box attacks, we utilize the transferability of adversarial examples to attack the unseen model successfully. However, existing attack algorithms are easily trapped into a sharp maximum, where a small perturbation changes its value significantly, leading to the failure of the attack. To tackle this issue, we propose a novel Sharpness-Aware Attack seeking the adversarial example with a flat maximum. Specifically, we sample several poor adversarial examples from the neighborhoods of the current point and alleviate the sharpness between them. We also sample anticipatory neighborhoods examples to make the attack algorithm converge quickly to an excellent starting point. Extensive experiments on the ImageNet dataset show the effectiveness of our method, combined with existing gradient-based attacks, our method yields an average attack success rate of 70.0% for nine defense models.

Few-shot classification consists of a training phase where a model is learned on a relatively large dataset and an adaptation phase where the learned model is adapted to previously-unseen tasks with limited labeled samples. In this paper, we empirically prove that the training algorithm and the adaptation algorithm can be completely disentangled, which allows algorithm analysis and design to be done individually for each phase. Our meta-analysis for each phase reveals several interesting insights that may help better understand key aspects of few-shot classification and connections with other fields such as visual representation learning and transfer learning. We hope the insights and research challenges revealed in this paper can inspire future work in related directions. Code and pre-trained models (in PyTorch) are available at https://github.com/Frankluox/CloserLookAgainFewShot.

The focus of this study is on Unsupervised Continual Learning (UCL), as it presents an alternative to Supervised Continual Learning which needs high-quality manual labeled data. The experiments under UCL paradigm indicate a phenomenon where the results on the first few tasks are suboptimal. This phenomenon can render the model inappropriate for practical applications. To address this issue, after analyzing the phenomenon and identifying the lack of diversity as a vital factor, we propose a method named Codebook for Unsupervised Continual Learning (CUCL) which promotes the model to learn discriminative features to complete the class boundary. Specifically, we first introduce a Product Quantization to inject diversity into the representation and apply a cross quantized contrastive loss between the original representation and the quantized one to capture discriminative information. Then, based on the quantizer, we propose a effective Codebook Rehearsal to address catastrophic forgetting. This study involves conducting extensive experiments on CIFAR100, TinyImageNet, and MiniImageNet benchmark datasets. Our method significantly boosts the performances of supervised and unsupervised methods. For instance, on TinyImageNet, our method led to a relative improvement of 12.76% and 7% when compared with Simsiam and BYOL, respectively. Codes are publicly available at https://github.com/zackschen/CUCL

Domain generalizable person Re-identification is a challenging and realistic task. It requires a model to train on multi-source domains and then generalizes well on unseen target domains. Existing approaches typically mix images from different domains in a mini-batch for training, but this can increase discrimination within a mini-batch due to the vast style differences among domains. As a result, the model may converge easily by mining domain-related information, while neglecting identity-discriminative information, especially for metric learning. To improve the difficulty of metric learning under multi-source training, we design a Style-aware Hard-negative Sampling (SHS) strategy. SHS effectively improves metric learning but reduces the style diversity within the batch. To enhance style diversity, we devise a Dynamic Style Mixing (DSM) which memorizes single-domain styles and synthesizes novel styles, which largely raises the diversity of source domains. Extensive experiments prove the effectiveness of our method. In both single-source and multi-source settings, our approach significantly outperforms the state-of-the-art (SOTA).

Understanding human interactions within diverse media contexts has emerged as a fundamental challenge. The explosive growth of multimedia data not only provides opportunities for human-centirc analysis but also increases the complexity of processing multimodal data. To address this pivotal challenge and explore its multifaceted dimensions, the Fourth International Workshop on Human-Centric Multimedia Analysis is concentrated on the tasks of human-centric analysis with multimedia and multimodal information. By delving into the nuances of human behavior within multimedia, this workshop aims to uncover novel insights, showcase innovative methodologies, and discuss future directions. With a spotlight on cutting-edge research and a focus on real-world applications, the workshop seeks to equip researchers and practitioners with the tools and knowledge to navigate the intricacies of human-centric multimedia analysis.

Compressing videos into binary codes can improve retrieval speed and reduce storage overhead. However, learning accurate hash codes for video retrieval can be challenging due to high local redundancy and complex global dependencies between video frames, especially in the absence of labels. Existing self-supervised video hashing methods have been effective in designing expressive temporal encoders, but have not fully utilized the temporal dynamics and spatial appearance of videos due to less challenging and unreliable learning tasks. To address these challenges, we begin by utilizing the contrastive learning task to capture global spatio-temporal information of videos for hashing. With the aid of our designed augmentation strategies, which focus on spatial and temporal variations to create positive pairs, the learning framework can generate hash codes that are invariant to motion, scale, and viewpoint. Furthermore, we incorporate two collaborative learning tasks, i.e., frame order verification and scene change regularization, to capture local spatio-temporal details within video frames, thereby enhancing the perception of temporal structure and the modeling of spatio-temporal relationships. Our proposed Contrastive Hashing with Global-Local Spatio-temporal Ibnformation (CHAIN) outperforms state-of-the-art self-supervised video hashing methods on four video benchmark datasets. Our codes will be released.

Deep hashing has been widely applied in large-scale image retrieval due to its powerful computational efficiency. Nevertheless, the vulnerability of deep hashing to adversarial examples has been revealed, particularly to targeted attacks with stronger manipulability. Existing targeted attack methods for deep hashing default to selecting target labels from random images, usually encompassing multiple classes for attack in multi-label datasets. However, they exhabit poor performance when facing a preciser single target label selection. In this work, we propose a novel Precise Target-Oriented Attack dubbed PTA, to enhance the precision of such targeted attacks. Specifically, we further categorize the general target label into preciser single target label for attack. By relaxing the non-differentiable indicator function, we directly adopt Average Precision (AP) as optimization objective to guide the generation of adversarial examples on a small subset of the entire database, thus achieving stronger precision. Extensive experiments demonstrate that the proposed PTA achieves state-of-the-art performance in both general and single target label selection, with superior transferability and universality.

Videos for mobile devices become the most popular access to share and acquire information recently. For the convenience of users' creation, in this paper, we present a system, namely MobileVidFactory, to automatically generate vertical mobile videos where users only need to give simple texts mainly. Our system consists of two parts: basic and customized generation. In the basic generation, we utilize the pretrained image diffusion model, and adapt it to a high-quality open-domain vertical video generator. As for the audio, by retrieving from our big database, our system matches a suitable background sound for the video. Additionally to produce customized content, our system allows users to add specified screen texts for enriching visual expression, and specify texts for automatic reading with optional voices as they like.

In this paper, we present MovieFactory, a powerful framework to generate cinematic-picture (3072x1280), film-style (multi-scene), and multi-modality (sounding) movies on the demand of natural languages. As the first fully automated movie generation model to the best of our knowledge, our approach empowers users to create captivating movies with smooth transitions using simple text inputs, surpassing existing methods that produce soundless videos limited to a single scene of modest quality. To facilitate this distinctive functionality, we leverage ChatGPT to expand user-provided text into detailed sequential scripts for movie generation. Then we bring scripts to life visually and acoustically through vision generation and audio retrieval. To generate videos, we extend the capabilities of a pretrained text-to-image diffusion model through a two-stage process. Firstly, we employ spatial finetuning to bridge the gap between the pretrained image model and the new video dataset. Subsequently, we introduce temporal learning to capture object motion. In terms of audio, we leverage sophisticated retrieval models to select and align audio elements that correspond to the plot and visual content of the movie.

Cross-modal Retrieval methods build similarity relations between vision and language modalities by jointly learning a common representation space. However, the predictions are often unreliable due to the Aleatoric uncertainty, which is induced by low-quality data, e.g., corrupt images, fast-paced videos, and non-detailed texts. In this paper, we propose a novel Prototype-based Aleatoric Uncertainty Quantification (PAU) framework to provide trustworthy predictions by quantifying the uncertainty arisen from the inherent data ambiguity. Concretely, we first construct a set of various learnable prototypes for each modality to represent the entire semantics subspace. Then Dempster-Shafer Theory and Subjective Logic Theory are utilized to build an evidential theoretical framework by associating evidence with Dirichlet Distribution parameters. The PAU model induces accurate uncertainty and reliable predictions for cross-modal retrieval. Extensive experiments are performed on four major benchmark datasets of MSR-VTT, MSVD, DiDeMo, and MS-COCO, demonstrating the effectiveness of our method. The code is accessible at https://github.com/leolee99/PAU.

Intention-oriented object detection aims to detect desired objects based on specific intentions or requirements. For instance, when we desire to "lie down and rest", we instinctively seek out a suitable option such as a "bed" or a "sofa" that can fulfill our needs. Previous work in this area is limited either by the number of intention descriptions or by the affordance vocabulary available for intention objects. These limitations make it challenging to handle intentions in open environments effectively. To facilitate this research, we construct a comprehensive dataset called Reasoning Intention-Oriented Objects (RIO). In particular, RIO is specifically designed to incorporate diverse real-world scenarios and a wide range of object categories. It offers the following key features: 1) intention descriptions in RIO are represented as natural sentences rather than a mere word or verb phrase, making them more practical and meaningful; 2) the intention descriptions are contextually relevant to the scene, enabling a broader range of potential functionalities associated with the objects; 3) the dataset comprises a total of 40,214 images and 130,585 intention-object pairs. With the proposed RIO, we evaluate the ability of some existing models to reason intention-oriented objects in open environments.

The performance of current Scene Graph Generation (SGG) models is severely hampered by hard-to-distinguish predicates, e.g., "woman-on/standing on/walking on-beach". As general SGG models tend to predict head predicates and re-balancing strategies prefer tail categories, none of them can appropriately handle hard-to-distinguish predicates. To tackle this issue, inspired by fine-grained image classification, which focuses on differentiating hard-to-distinguish objects, we propose an Adaptive Fine-Grained Predicates Learning (FGPL-A) which aims at differentiating hard-to-distinguish predicates for SGG. First, we introduce an Adaptive Predicate Lattice (PL-A) to figure out hard-to-distinguish predicates, which adaptively explores predicate correlations in keeping with model's dynamic learning pace. Practically, PL-A is initialized from SGG dataset, and gets refined by exploring model's predictions of current mini-batch. Utilizing PL-A, we propose an Adaptive Category Discriminating Loss (CDL-A) and an Adaptive Entity Discriminating Loss (EDL-A), which progressively regularize model's discriminating process with fine-grained supervision concerning model's dynamic learning status, ensuring balanced and efficient learning process. Extensive experimental results show that our proposed model-agnostic strategy significantly boosts performance of benchmark models on VG-SGG and GQA-SGG datasets by up to 175% and 76% on Mean Recall@100, achieving new state-of-the-art performance. Moreover, experiments on Sentence-to-Graph Retrieval and Image Captioning tasks further demonstrate practicability of our method.

Generating photo-realistic images from labels (e.g., semantic labels or sketch labels) is much more challenging than the general image-to-image translation task, mainly due to the large differences between extremely sparse labels and detail rich images. We propose a general framework Lab2Pix to tackle this issue from two aspects: 1) how to extract useful information from the input; and 2) how to efficiently bridge the gap between the labels and images. Specifically, we propose a Double-Guided Normalization (DG-Norm) to use the input label for semantically guiding activations in normalization layers, and use global features with large receptive fields for differentiating the activations within the same semantic region. To efficiently generate the images, we further propose Label Guided Spatial Co-Attention (LSCA) to encourage the learning of incremental visual information using limited model parameters while storing the well-synthesized part in lower-level features. Accordingly, Hierarchical Perceptual Discriminators with Foreground Enhancement Masks are proposed to toughly work against the generator thus encouraging realistic image generation and a sharp enhancement loss is further introduced for high-quality sharp image generation. We instantiate our Lab2Pix for the task of label-to-image in both unpaired (Lab2Pix-V1) and paired settings (Lab2Pix-V2). Extensive experiments conducted on various datasets demonstrate that our method significantly outperforms state-of-the-art methods quantitatively and qualitatively in both settings.

Deep metric learning has become a key component of cross-modal retrieval. By learning to pull the features of matched instances closer while pushing the features of mismatched instances farther away, one can learn highly robust multi-modal representations. Most existing cross-modal retrieval methods leverage vanilla triplet loss to train the network, which cannot adaptively penalize pairs with different hardness. Although various weighting strategies have been designed for unimodal matching tasks, few weighting strategies have been applied to cross-modal tasks due to the specificity of cross-modal tasks. While few weighting strategies are designed for cross-modal scenarios, they usually involve a lot of hyper-parameters, which require a lot of computational resources to fine-tune. In this paper, we introduce a new exponential loss, which can assign appropriate weights to individual positive and negative pairs according to their similarity so that it can adaptively penalize pairs with different hardness. Furthermore, the exponential loss has only two hyper-parameters, making it easier to find the optimal parameters to suit various data distributions in practice. Exponential loss can be universally applied to well-established cross-modal models and further boost their retrieval performance. We exhaustively ablate our method on Image-Text matching, Video-Text matching, as well as unimodal Image matching. Experimental results show that a standard model trained with exponential loss can achieve noticeable performance gains.

Visual dialog requires an agent to answer successive questions considering an image and dialog history, which is a classic vision-language task. Despite progress, there are still two key challenges: 1) parsing long or complex questions and answers and 2) dealing with the visual scene containing complicated interactions among entities. These challenges bring about the unsatisfactory consequence of current visual dialog methods. In this paper, we propose a novel Heterogeneous Knowledge Network (HKNet), which leverages textual sequence knowledge and graph knowledge to address the above issues. Specifically, the textual sequence knowledge is derived from the sentences that are retrieved from the image captions of the visual dialog dataset. The textual sequence knowledge can supplement essential common sense for parsing long or complex questions and answers. The graph knowledge is constructed via scene graph, which provides complete visual relationships for understanding the complicated interactions. These two kinds of heterogeneous knowledge complement each other and jointly improve the logical reasoning ability of the visual dialog. Extensive experimental results on two benchmark datasets: VisDial v0.9 and v1.0 demonstrate the superiority of the proposed HKNet. Ablation studies and visualization results further verify the effectiveness of our method.

In general, videos are powerful at recording physical patterns (e.g., spatial layout) while texts are great at describing abstract symbols (e.g., emotion). When video and text are used in multi-modal tasks, they are claimed to be complementary and their distinct information is crucial. However, when it comes to cross-modal tasks (e.g., retrieval), existing works usually use their common part in the form of common space learning while their distinct information is abandoned. In this paper, we argue that distinct information is also beneficial for cross-modal retrieval. To address this problem, we propose a divide-and-conquer learning approach, namely Complementarity-aware Space Learning (CSL), by recasting this challenge into learning of two spaces (i.e., latent and symbolic spaces) to simultaneously explore their common and distinct information by considering multi-modal complementary character. Specifically, we first propose to learn a symbolic space from video with a memory-based video encoder and a symbolic generator. In contrast, we also introduce learning a latent space from text with a text encoder and a memory-based latent feature selector. Finally, we propose a complementarity-aware loss by integrating two spaces to facilitate video-text retrieval tasks. Extensive experiments show that our approach outperforms existing state-of-the-art methods by 5.1%, 2.1% and 0.9% of R@10 for text-to-video retrieval on three benchmarks, respectively. Ablation study also verifies that the distinct information from video and text improves the retrieval performance. Trained models and source code have been released athttps://github.com/NovaMind-Z/CSL.

Part-level attribute parsing is a fundamental but challenging task, which requires the region-level visual understanding to provide explainable details of body parts. Most existing approaches address this problem by adding a regional convolutional neural network (RCNN) with an attribute prediction head to a two-stage detector, in which attributes of body parts are identified from localwise part boxes. However, localwise part boxes with limit visual clues (i.e., part appearance only) lead to unsatisfying parsing results, since attributes of body parts are highly dependent on comprehensive relations among them. In this article, we propose a knowledge-embedded RCNN (KE-RCNN) to identify attributes by leveraging rich knowledge, including implicit knowledge (e.g., the attribute “above-the-hip” for a shirt requires visual/geometry relations of shirt-hip) and explicit knowledge (e.g., the part of “shorts” cannot have the attribute of “hoodie” or “lining”). Specifically, the KE-RCNN consists of two novel components, that is: 1) implicit knowledge-based encoder (IK-En) and 2) explicit knowledge-based decoder (EK-De). The former is designed to enhance part-level representation by encoding part–part relational contexts into part boxes, and the latter one is proposed to decode attributes with a guidance of prior knowledge about part–attribute relations. In this way, the KE-RCNN is plug-and-play, which can be integrated into any two-stage detectors, for example, Attribute-RCNN, Cascade-RCNN, HRNet-based RCNN, and SwinTransformer-based RCNN. Extensive experiments conducted on two challenging benchmarks, for example, Fashionpedia and Kinetics-TPS, demonstrate the effectiveness and generalizability of the KE-RCNN. In particular, it achieves higher improvements over all existing methods, reaching around 3% of${\mathrm{ AP}}^{\mathrm{ all}}_{\rm IoU+F_{1}}$on Fashionpedia and around 4% of${\mathrm{ Acc}}_{p}$on Kinetics-TPS. Code and models are publicly available at:https://github.com/sota-joson/KE-RCNN.

How to avoid biased predictions is an important and active research question in scene graph generation (SGG). Current state-of-the-art methods employ debiasing techniques such as resampling and causality analysis. However, the role of intrinsic cues in the features causing biased training has remained under-explored. In this paper, for the first time, we make the surprising observation that object identity information, in the form of object label embeddings (e.g. GLOVE), is principally responsible for biased predictions. We empirically observe that, even without any visual features, a number of recent SGG models can produce comparable or even better results solely from object label embeddings. Motivated by this insight, we propose to leverage a conditional variational auto-encoder to decouple the entangled visual features into two meaningful components: the object's intrinsic identity features and the extrinsic, relation-dependent state feature. We further develop two compositional learning strategies on the relation and object levels to mitigate the data scarcity issue of rare relations. On the two benchmark datasets Visual Genome and GQA, we conduct extensive experiments on the three scenarios, i.e., conventional, few-shot and zero-shot SGG. Results consistently demonstrate that our proposed Decomposition and Composition (DeC) method effectively alleviates the biases in the relation prediction. Moreover, DeC is model-free, and it significantly improves the performance of recent SGG models, establishing new state-of-the-art performance.

Scene graph generation (SGG) and human-object interaction (HOI) detection are two important visual tasks aiming at localising and recognising relationships between objects, and interactions between humans and objects, respectively. Prevailing works treat these tasks as distinct tasks, leading to the development of task-specific models tailored to individual datasets. However, we posit that the presence of visual relationships can furnish crucial contextual and intricate relational cues that significantly augment the inference of human-object interactions. This motivates us to think if there is a natural intrinsic relationship between the two tasks, where scene graphs can serve as a source for inferring human-object interactions. In light of this, we introduce SG2HOI+, a unified one-step model based on the Transformer architecture. Our approach employs two interactive hierarchical Transformers to seamlessly unify the tasks of SGG and HOI detection. Concretely, we initiate a relation Transformer tasked with generating relation triples from a suite of visual features. Subsequently, we employ another transformer-based decoder to predict human-object interactions based on the generated relation triples. A comprehensive series of experiments conducted across established benchmark datasets including Visual Genome, V-COCO, and HICO-DET demonstrates the compelling performance of our SG2HOI+ model in comparison to prevalent one-stage SGG models. Remarkably, our approach achieves competitive performance when compared to state-of-the-art HOI methods. Additionally, we observe that our SG2HOI+ jointly trained on both SGG and HOI tasks in an end-to-end manner yields substantial improvements for both tasks compared to individualized training paradigms.

Lately, video-language pre-training and text-video retrieval have attracted significant attention with the explosion of multimedia data on the Internet. However, existing approaches for video-language pre-training typically limit the exploitation of the hierarchical semantic information in videos, such as frame semantic information and global video semantic information. In this work, we present an end-to-end pre-training network with Hierarchical Matching and Momentum Contrast named HMMC. The key idea is to explore the hierarchical semantic information in videos via multilevel semantic matching between videos and texts. This design is motivated by the observation that if a video semantically matches a text (can be a title, tag or caption), the frames in this video usually have semantic connections with the text and show higher similarity than frames in other videos. Hierarchical matching is mainly realized by two proxy tasks: Video-Text Matching (VTM) and Frame-Text Matching (FTM). Another proxy task: Frame Adjacency Matching (FAM) is proposed to enhance the single visual modality representations while training from scratch. Furthermore, momentum contrast framework was introduced into HMMC to form a multimodal momentum contrast framework, enabling HMMC to incorporate more negative samples for contrastive learning which contributes to the generalization of representations. We also collected a large-scale Chinese video-language dataset (over 763k unique videos) named CHVTT to explore the multilevel semantic connections between videos and texts. Experimental results on two major Text-video retrieval benchmark datasets demonstrate the advantages of our methods. We release our code at https://github.com/cheetah003/HMMC.

Existing supervised quantization methods usually learn the quantizers from pair-wise, triplet, or anchor-based losses, which only capture their relationship locally without aligning them globally. This may cause an inadequate use of the entire space and a severe intersection among different semantics, leading to inferior retrieval performance. Furthermore, to enable quantizers to learn in an end-to-end way, current practices usually relax the non-differentiable quantization operation by substituting it with softmax, which unfortunately is biased, leading to an unsatisfying suboptimal solution. To address the above issues, we present Spherical Centralized Quantization (SCQ), which contains a Priori Knowledge based Feature (PKFA) module for the global alignment of feature vectors, and an Annealing Regulation Semantic Quantization (ARSQ) module for low-biased optimization. Specifically, the PKFA module first applies Semantic Center Allocation (SCA) to obtain semantic centers based on prior knowledge, and then adopts Centralized Feature Alignment (CFA) to gather feature vectors based on corresponding semantic centers. The SCA and CFA globally optimize the inter-class separability and intra-class compactness, respectively. After that, the ARSQ module performs a partial-soft relaxation to tackle biases, and an Annealing Regulation Quantization loss for further addressing the local optimal solution. Experimental results show that our SCQ outperforms state-of-the-art algorithms by a large margin (2.1%, 3.6%, 5.5% mAP respectively) on CIFAR-10, NUS-WIDE, and ImageNet with a code length of 8 bits. Codes are publicly available:https://github.com/zzb111/Spherical-Centralized-Quantization.

Out-of-distribution (OOD) detection aims to detect "unknown" data whose labels have not been seen during the in-distribution (ID) training process. Recent progress in representation learning gives rise to distance-based OOD detection that recognizes inputs as ID/OOD according to their relative distances to the training data of ID classes. Previous approaches calculate pairwise distances relying only on global image representations, which can be sub-optimal as the inevitable background clutter and intra-class variation may drive image-level representations from the same ID class far apart in a given representation space. In this work, we overcome this challenge by proposing Multi-scale OOD DEtection (MODE), a first framework leveraging both global visual information and local region details of images to maximally benefit OOD detection. Specifically, we first find that existing models pretrained by off-the-shelf cross-entropy or contrastive losses are incompetent to capture valuable local representations for MODE, due to the scale-discrepancy between the ID training and OOD detection processes. To mitigate this issue and encourage locally discriminative representations in ID training, we propose Attention-based Local PropAgation (ALPA), a trainable objective that exploits a cross-attention mechanism to align and highlight the local regions of the target objects for pairwise examples. During test-time OOD detection, a Cross-Scale Decision (CSD) function is further devised on the most discriminative multi-scale representations to distinguish ID/OOD data more faithfully. We demonstrate the effectiveness and flexibility of MODE on several benchmarks - on average, MODE outperforms the previous state-of-the-art by up to 19.24% in FPR, 2.77% in AUROC. Code is available at https://github.com/JimZAI/MODE-OOD.

Multi-Codebook Quantization (MCQ) is a generalized version of existing codebook-based quantizations for Approximate Nearest Neighbor (ANN) search. Specifically, MCQ picks one codeword for each sub-codebook independently and takes the sum of picked codewords to approximate the original vector. The objective function involves no constraints, therefore, MCQ theoretically has the potential to achieve the best performance because solutions of other codebook-based quantization methods are all covered by MCQ's solution space under the same codebook size setting. However, finding the optimal solution to MCQ is proved to be NP-hard due to its encoding process, i.e., converting an input vector to a binary code. To tackle this, researchers apply constraints to it to find near-optimal solutions or employ heuristic algorithms that are still time-consuming for encoding. Different from previous approaches, this paper takes the first attempt to find a deep solution to MCQ. The encoding network is designed to be as simple as possible, so the very complex encoding problem becomes simply a feed-forward. Compared with other methods on three datasets, our method shows state-of-the-art performance. Notably, our method is 11× - 38× faster than heuristic algorithms for encoding, which makes it more practical for the real scenery of large-scale retrieval. Our code is publicly available: https://github.com/DeepMCQ/DeepQ.

Learning human 2D-3D correspondences aims to map all human 2D pixels to a 3D human template, namely human densepose estimation, involving surface patch recognition (i.e., Index-to-Patch (I)) and regression of patch-specific UV coordinates. Despite recent progress, it remains challenging especially under the condition of “in the wild”, where RGB images capture real-world scenes with backgrounds, occlusions, scale variations, and postural diversity. In this paper, we address three vital problems in this task: 1) how to perceive multi-scale visual information for instances “in the wild”; 2) how to design learning objectives to address the precise instance representation harassed by “multiple instances in one bounding box” phenomenon; and 3) how to boost the performance of index-to-patch prediction faced by limited supervision. To tackle problems above, we propose an end-to-end deep Adaptive Multi-path Aggregation network (AMA-net) for Human DensePose Estimation. First, we introduce an adaptive multi-path aggregation algorithm to extract varying-sized instance-level features, which capture multi-scale information of a bounding-box and are then utilized for parsing different instances. Second, we adopt an instance augmentation learning objective to further distinguish the target instance from other interference instances. Third, taking advantage of 2D human parsers that are trained from sufficient annotations, we introduce a task transformer that bridges the “gap” between 2D human parsing and densepose estimation, thus benefiting the performance of densepose estimator. Experimental results on the challenging DensePose-COCO dataset demonstrate that our approach sets a new record, and it significantly outperforms the state-of-the-art methods. Codes and models are publicly available.

Due to the usage of global similarity, the hashing methods based on predefined hash centers have achieved more accurate retrieval results than the pairwise/triplet-based methods. Nevertheless, the fixed hash centers lack the perception of data distribution and are limited by the pre-determined Hadamard matrix, which consider neither the label semantic information nor the object scale size, resulting in sub-optimal retrieval performance and weak generalization ability. In this paper, we (1) adopt the label semantic information to generate self-adaptive hash centers and (2) propose the label-affinity coefficient (lac) that considers the scale size of each label/object appearing in the given image to calculate the real hash centroid for this image. Based on this, we proposeLabel-affinity Self-adaptive Central Similarity Hashing (LSCSH)for image retrieval. LSCSH consists of a hash code generator module and a hash center adapter module. First, we obtain the label word vector (i.e., the word vector representation of each class label) via the Word2Vector technique to generate and update the hash centers that adapt to the distribution of both label word vectors and generated hash codes. Second, we learnlacto indicate the dominance of different labels corresponding to objects in each given image, which considers the unequal scales of each object (corresponding to a label) to calculate a more accurate hash centroid for each image. Last but not least, we design an asynchronous learning mechanism to enable each hash code and its corresponding hash centroid to adapt to each other dynamically. We conduct extensive experiments on 5 image datasets including CIFAR-10, ImageNet, VOC2012, MS-COCO and NUS-WIDE. The experimental results demonstrate that LSCSH can achieve the state-of-the-art visual retrieval performance on both single-label and multi-label image datasets. The code of this work is released at:https://github.com/lzHZWZ/LSCSH_sourcecode.git.

Fine-grained visual classification (FGVC) is challenging due to the interclass similarity and intraclass variation in datasets. In this work, we explore the great merit of complex values in introducing an imaginary part for modeling data uncertainty (e.g., different points on the complex plane can describe the same state) and graph convolutional networks (GCNs) in learning interdependently among classes to simultaneously tackle the above two major challenges. To the end, we propose a novel approach, termed text-assisted complex-valued fusion network (TA-CFN). Specifically, we expand each feature from 1-D real values to 2-D complex value by disassembling feature maps, thereby enabling the extension of traditional deep convolutional neural networks over the complex domain. Then, we fuse the real and imaginary parts of complex features through complex projection and modulus operation. Finally, we build an undirected graph over the object labels with the assistance of a text corpus, and a GCN is learned to map this graph into a set of classifiers. The benefits are in two folds: 1) complex features allow for a richer algebraic structure to better model the large variation within the same category and 2) leveraging the interclass dependencies brought by the GCN to capture key factors of the slight variation among different categories. We conduct extensive experiments to verify that our proposed model can achieve the state-of-the-art performance on two widely used FGVC datasets.

Learning accurate low-dimensional embeddings for a network is a crucial task as it facilitates many downstream network analytics tasks. For large networks, the trained embeddings often require a significant amount of space to store, making storage and processing a challenge. Building on our previous work on semisupervised network embedding, we develop d-SNEQ, a differentiable DNN-based quantization method for network embedding. d-SNEQ incorporates a rank loss to equip the learned quantization codes with rich high-order information and is able to substantially compress the size of trained embeddings, thus reducing storage footprint and accelerating retrieval speed. We also propose a new evaluation metric, path prediction, to fairly and more directly evaluate the model performance on the preservation of high-order information. Our evaluation on four real-world networks of diverse characteristics shows that d-SNEQ outperforms a number of state-of-the-art embedding methods in link prediction, path prediction, node classification, and node recommendation while being far more space- and time-efficient.

Previous work generally believes that improving the spatial invariance of convolutional networks is the key to object counting. However, after verifying several mainstream counting networks, we surprisingly found too strict pixel-level spatial invariance would cause overfit noise in the density map generation. In this paper, we try to use locally connected Gaussian kernels to replace the original convolution filter to estimate the spatial position in the density map. The purpose of this is to allow the feature extraction process to potentially stimulate the density map generation process to overcome the annotation noise. Inspired by previous work, we propose a low-rank approximation accompanied with translation invariance to favorably implement the approximation of massive Gaussian convolution. Our work points a new direction for follow-up research, which should investigate how to properly relax the overly strict pixel-level spatial invariance for object counting. We evaluate our methods on 4 mainstream object counting networks (i.e., MCNN, CSRNet, SANet, and ResNet-50). Extensive experiments were conducted on 7 popular benchmarks for 3 applications (i.e., crowd, vehicle, and plant counting). Experimental results show that our methods significantly outperform other state-of-the-art methods and achieve promising learning of the spatial position of objects11Code is at https://github.com/zhiqic/Rethinking-Counting.

Defense models against adversarial attacks have grown significantly, but the lack of practical evaluation methods has hindered progress. Evaluation can be defined as looking for defense models' lower bound of robustness given a budget number of iterations and a test dataset. A practical evaluation method should be convenient (i.e., parameter-free), efficient (i.e., fewer iterations) and reliable (i.e., approaching the lower bound of robustness). Towards this target, we propose a parameter-free Adaptive Auto Attack (A3) evaluation method which addresses the efficiency and reliability in a test-time-training fashion. Specifically, by observing that adversarial examples to a specific defense model follow some regularities in their starting points, we design an Adaptive Direction Initialization strategy to speed up the evaluation. Furthermore, to approach the lower bound of robustness under the budget number of iterations, we propose an online statistics-based discarding strategy that automatically identifies and abandons hard-to-attack images. Extensive experiments on nearly 50 widely-used defense models demonstrate the effectiveness of our A3. By consuming much fewer iterations than existing methods, i.e., 1/10 on average (10× speed up), we achieve lower robust accuracy in all cases. Notably, we won first place out of 1681 teams in CVPR 2021 White-box Adversarial Attacks on Defense Models competitions with this method. Code is available at: https://github.com/liuye6666/adaptive_auto_attack

The performance of current Scene Graph Generation models is severely hampered by some hard-to-distinguish predicates, e.g., “woman-on/standing on/walking on-beach” or “woman-near/looking at/in front of-child”. While general SGG models are prone to predict head predicates and existing re-balancing strategies prefer tail categories, none of them can appropriately handle these hard-to-distinguish predicates. To tackle this issue, inspired by fine-grained image classification, which focuses on differentiating among hard-to-distinguish object classes, we propose a method named Fine-Grained Predicates Learning (FGPL) which aims at differentiating among hard-to-distinguish predicates for Scene Graph Generation task. Specifically, we first introduce a Predicate Lattice that helps SGG models to figure out fine-grained predicate pairs. Then, utilizing the Predicate Lattice, we propose a Category Discriminating Loss and an Entity Discriminating Loss, which both contribute to distinguishing fine-grained predicates while maintaining learned discriminatory power over recognizable ones. The proposed model-agnostic strategy significantly boosts the performances of three benchmark models (Transformer, VCTree, and Motif) by 22.8%, 24.1% and 21.7% of Mean Recall (mR@100) on the Predicate Classification sub-task, respectively. Our model also outperforms state-of-the-art methods by a large margin (i.e., 6.1%, 4.6%, and 3.2% of Mean Recall (mR@100)) on the Visual Genome dataset. Codes are publicly available11https://github.com/XinyuLyu/FGPL.

Domain Generalizable (DG) person ReID is a challenging task which trains a model on source domains yet generalizes well on target domains. Existing methods use source domains to learn domain-invariant features, and assume those features are also irrelevant with target domains. However, they do not consider the target domain information which is unavailable in the training phrase of DG. To address this issue, we propose a novel Meta Distribution Alignment (MDA) method to enable them to share similar distribution in a test-time-training fashion. Specifically, since high-dimensional features are difficult to constrain with a known simple distribution, we first introduce an intermediate latent space constrained to a known prior distribution. The source domain data is mapped to this latent space and then reconstructed back. A meta-learning strategy is introduced to facilitate generalization and support fast adaption. To reduce their discrepancy, we further propose a test-time adaptive updating strategy based on the latent space which efficiently adapts model to unseen domains with a few samples. Extensive experimental results show that our model outperforms the state-of-the-art methods by up to 5.2% R-1 on average on the large-scale and 4.7% R-1 on the single-source domain generalization ReID benchmark. Source code is publicly available at https://github.com/haoni0812/MDA.git.

Modeling latent variables with priors and hyperpriors is an essential problem in variational image compression. Formally, trade-off between rate and distortion is handled well if priors and hyperpriors precisely describe latent variables. Current practices only adopt univariate priors and process each variable individually. However, we find inter-correlations and intra-correlations exist when observing latent variables in a vectorized perspective. These findings reveal visual redundancies to improve rate-distortion performance and parallel processing ability to speed up compression. This encourages us to propose a novel vectorized prior. Specifically, a multivariate Gaussian mixture is proposed with means and covariances to be estimated. Then, a novel probabilistic vector quantization is utilized to effectively approximate means, and remaining covariances are further induced to a unified mixture and solved by cascaded estimation without context models involved. Furthermore, code books involved in quantization are extended to multi-codebooks for complexity reduction, which formulates an efficient compression procedure. Extensive experiments on benchmark datasets against state-of-the-art indicate our model has better rate-distortion performance and an impressive 3.18x compression speed up, giving us the ability to perform real-time, high-quality variational image compression in practice. Our source code is publicly available at https://github.com/xiaosu-zhu/McQuic.

Visual dialog aims to answer several consecutive questions based on image and dialog history. Most works resolve all questions with ambiguous references (e.g., “she”) by dialog history, which generates redundant information and gets in-accurate results. Also, they regard this task as a classification task, which ignores the diversity of response answers and results in poor generalization capability. To tackle these problems, we propose a novel Context Gating with Multi-level Ranking Learning (CGMRL). Specifically, the proposed context gating considers both question and image to adaptively determine whether the history is needed for question answering, which reduces the redundant or even noisy information generated by history. To improve the generalization capability of the model, a new constrained multi-level ranking learning is proposed to encourage the model to consider the correct semantic options rather than only choose the ground truth answer. Experimental validations on the VisDial v1.0 show the superiority of the proposed method compared with other methods. Implementation code is published in anonymous Github: https://github.com/sy742/CGMRL_.

Scene graph provides a high-level scene understanding of the image, which has a wide range of applications in computer vision. Previous methods elaborately design many message passing strategies and uniformly treat instances in the image to capture contextual information. These methods, however, fail to grasp the salient objects and their relations, which are the basis of understanding the content of images. To capture the interaction among salient instances, we propose a novel Multi-Scale Graph Attention Network (MSGAT) that gradually shrinks the graph scale to retain salient instances, and then expands it to encode the multi-scale context. Our proposed MSGAT contains two sub-modules: Multi-Scale Message Passing (MSMP) and Relationship Filtering Module (RFM), which are designed to enhance features of salient instances and filter redundant relationships, respectively. Extensive experiments demonstrate that MSGAT outperforms previous methods and achieves state-of-the-art performances on Visual Genome.

Video captioning is a challenging task that necessitates a thorough comprehension of visual scenes. Existing methods follow a typical one-to-one mapping, which concentrates on a limited sample space while ignoring the intrinsic semantic associations between samples, resulting in rigid and uninformative expressions. To address this issue, we propose a novel and flexible framework, namely Support-set based Multi-modal Representation Enhancement (SMRE) model, to mine rich information in a semantic subspace shared between samples. Specifically, we propose a Support-set Construction (SC) module to construct a support-set to learn underlying connections between samples and obtain semantic-related visual elements. During this process, we design a Semantic Space Transformation (SST) module to constrain relative distance and administrate multi-modal inter-actions in a self-supervised way. Extensive experiments on MSVD and MSR-VTT datasets demonstrate that our SMRE achieves state-of-the-art performance. Our code is released at https://github.com/SMRE-CV/SMRE.

The graph convolutional networks (GCNs), which model human body skeletons as several spatial-temporal graphs, have been widely used and become a key to representative feature extraction. However, existing methods have limitations in recognizing action in the wild, where human body skeletons are captured from real-world scenes with diversified view-points, obvious motion blurs, complex interactions and fast varying resolutions of the human body. In this paper, we propose a Multi-modal Knowledge Embedded Graph Convolutional Network (MKE-GCN), which is a conceptually simple yet effective method for skeleton-based action recognition in the wild. In the proposed framework, we address two main problems: 1) how to design a simple yet effective pipeline for modeling multi-modal body skeletons; and 2) how to equip this pipeline with the ability of handling “in the wild”. To tackle these problems, in MKE-GCN, we first build an adaptive multi-modal aggregation (AMA) module and add it to traditional GCNs for multi-modal representation learning. Then, we further enhance the GCN model by a multi-modal knowledge distillation (MKD) strategy, where the proposed MKE-GCN mines action recognition knowledge from various multi-modal models. We discover that aside from the multi-modal representation, the MKD is of particular importance for improving the accuracy of skeleton-based action recognition “in the wild”. Notably, the proposed method is light-weight, which can be applied to any GCN based method. Furthermore, extensive experiments on three challenging benchmarks, e.g., UAV-Human, NTU-RGB+D 60 and NTU-RGB+D 120, demonstrate that our approach sets a new record for skeleton-based action recognition. Our anonymous code and models are also released1.

Scene Graph Generation (SGG) represents objects and their interactions with a graph structure. Recently, many works are devoted to solving the imbalanced problem in SGG. However, underestimating the head predicates in the whole training process, they wreck the features of head predicates that provide general features for tail ones. Besides, assigning excessive attention to the tail predicates leads to semantic deviation. Based on this, we propose a novel SGG framework, learning to generate scene graphs from Head to Tail (SGG-HT), containing Curriculum Re-weight Mechanism (CRM) and Semantic Context Module (SCM). CRM learns head/easy samples firstly for robust features of head predicates and then gradually focuses on tail/hard ones. SCM is proposed to relieve semantic deviation by ensuring the semantic consistency between the generated scene graph and the ground truth in global and local representations. Experiments show that SGG-HT significantly alleviates the biased problem and achieves state-of-the-art performances on Visual Genome.

High-resolution representation is necessary for human pose estimation to achieve high performance, and the ensuing problem is high computational complexity. In particular, predominant pose estimation methods estimate human joints by 2D single-peak heatmaps. Each 2D heatmap can be hori-zontally and vertically projected to and reconstructed by a pair of 1D heat vectors. Inspired by this observation, we introduce a lightweight and powerful alternative, Spatially Unidimensional Self-Attention (SUSA), to the pointwise (1 x 1) convolution that is the main computational bottleneck in the depthwise separable 3 x 3 convolution. Our SUSA reduces the computational complexity of the pointwise (1 x 1) convolution by 96% without sacrificing accuracy. Furthermore, we use the SUSA as the main module to build our lightweight pose estimation backbone X-HRNet, where$X$represents the estimated cross-shape attention vectors. Extensive experiments on the COCO benchmark demonstrate the superiority of our X-HRNet, and comprehensive ablation studies show the effectiveness of the SUSA modules. The code is publicly available at https://github.com/cool-xuan/x-hrnet.

Hashing learning for category-aware object retrieval in multi-label image is a challenging topic, in which the user is only interested in a certain object included in the query image rather than the entire image. Thus, it aims to find images which contain object similar to the interested one. However, previous hashing methods pre-select plenty of bounding box proposals or involve multiple independent steps to generate object-level representation, which may be suboptimal. In this paper, we propose a lightweight yet effective end-to-end deep category-aware hashing(DCAH) framework, which can generate individual hash code for each object included in the image by image-level label information, of which the key point is that it can directly localize object region with the assistance of category attention map. Extensive experiments on four benchmark datasets have demonstrated that our method achieves promising improvements on category-aware object retrieval results over the state-to-the-art methods.

Transformer-based architectures with grid features represent the state-of-the-art in visual and language reasoning tasks, such as visual question answering and image-text matching. However, directly applying them to image captioning may result in spatial and fine-grained semantic information loss. Their applicability to image captioning is still largely under-explored. Towards this goal, we propose a simple yet effective method, Spatial- and Scale-aware Transformer (S2 Transformer) for image captioning. Specifically, we firstly propose a Spatial-aware Pseudo-supervised (SP) module, which resorts to feature clustering to help preserve spatial information for grid features. Next, to maintain the model size and produce superior results, we build a simple weighted residual connection, named Scale-wise Reinforcement (SR) module, to simultaneously explore both low- and high-level encoded features with rich semantics. Extensive experiments on the MSCOCO benchmark demonstrate that our method achieves new state-of-art performance without bringing excessive parameters compared with the vanilla transformer. The source code is available at https://github.com/zchoi/S2-Transformer

Catastrophic forgetting is one of the most critical challenges in Continual Learning (CL). Recent approaches tackle this problem by projecting the gradient update orthogonal to the gradient subspace of existing tasks. While the results are remarkable, those approaches ignore the fact that these calculated gradients are not guaranteed to be orthogonal to the gradient subspace of each class due to the class deviation in tasks, e.g., distinguishing "Man" from "Sea" v.s. differentiating "Boy" from "Girl". Therefore, this strategy may still cause catastrophic forgetting for some classes. In this paper, we propose Class Gradient Projection (CGP), which calculates the gradient subspace from individual classes rather than tasks. Gradient update orthogonal to the gradient subspace of existing classes can be effectively utilized to minimize interference from other classes. To improve the generalization and efficiency, we further design a Base Refining (BR) algorithm to combine similar classes and refine class bases dynamically. Moreover, we leverage a contrastive learning method to improve the model's ability to handle unseen tasks. Extensive experiments on benchmark datasets demonstrate the effectiveness of our proposed approach. It improves the previous methods by 2.0% on the CIFAR-100 dataset. The code is available at https://github.com/zackschen/CGP.

The Weakly-Supervised Audio-Visual Video Parsing (AVVP) task aims to parse a video into temporal segments and predict their event categories in terms of modalities, labeling them as either audible, visible, or both. Since the temporal boundaries and modalities annotations are not provided, only video-level event labels are available, this task is more challenging than conventional video understanding tasks.Most previous works attempt to analyze videos by jointly modeling the audio and video data and then learning information from the segment-level features with fixed lengths. However, such a design exist two defects: 1) The various semantic information hidden in temporal lengths is neglected, which may lead the models to learn incorrect information; 2) Due to the joint context modeling, the unique features of different modalities are not fully explored. In this paper, we propose a novel AVVP framework termedDual Hierarchical Hybrid Network (DHHN) to tackle the above two problems. Our DHHN method consists of three components: 1) A hierarchical context modeling network for extracting different semantics in multiple temporal lengths; 2) A modality-wise guiding network for learning unique information from different modalities; 3) A dual-stream framework generating audio and visual predictions separately. It maintains the best adaptions on different modalities, further boosting the video parsing performance. Extensive quantitative and qualitative experiments demonstrate that our proposed method establishes the new state-of-the-art performance on the AVVP task.

Skeleton-based action recognition aims to project skeleton sequences to action categories, where skeleton sequences are derived from multiple forms of pre-detected points. Compared with earlier methods that focus on exploring single-form skeletons via Graph Convolutional Networks (GCNs), existing methods tend to improve GCNs by leveraging multi-form skeletons due to their complementary cues. However, these methods (either adapting structure of GCNs or model ensemble) require the co-existence of all skeleton forms during both training and inference stages, while a typical situation in real life is the existence of only partial forms for inference. To tackle this, we present Adaptive Cross-Form Learning (ACFL), which empowers well-designed GCNs to generate complementary representation from single-form skeletons without changing model capacity. Specifically, each GCN model in ACFL not only learns action representation from the single-form skeletons, but also adaptively mimics useful representations derived from other forms of skeletons. In this way, each GCN can learn how to strengthen what has been learned, thus exploiting model potential and facilitating action recognition as well. Extensive experiments conducted on three challenging benchmarks, i.e., NTU-RGB+D 120, NTU-RGB+D 60 and UAV-Human, demonstrate the effectiveness and generalizability of our method. Specifically, the ACFL significantly improves various GCN models (i.e., CTR-GCN, MS-G3D, and Shift-GCN), achieving a new record for skeleton-based action recognition.

Real-world videos are composed of complex actions with inherent temporal continuity (eg "person-touching-bottle" is usually followed by "person-holding-bottle"). In this work, we propose a novel method to mine such temporal continuity for dynamic scene graph generation (DSGG), namely Temporal Prior Inference (TPI). As opposed to current DSGG methods, which individually capture the temporal dependence of each video by refining representations, we make the first attempt to explore the temporal continuity by extracting the entire co-occurrence patterns of action categories from a variety of videos in Action Genome (AG) dataset. Then, these inherent patterns are organized as Temporal Prior Knowledge (TPK) which serves as prior knowledge for models' learning and inference. Furthermore, given the prior knowledge, human-object relationships in current frames can be effectively inferred from adjacent frames via the robust Temporal Prior Inference algorithm with tiny computation cost. Specifically, to efficiently guide the generating of temporal-consistent dynamic scene graphs, we incorporate the temporal prior inference into a DSGG framework by introducing frame enhancement, continuity loss, and fast inference. The proposed model-agnostic strategies significantly boost the performances of existing state-of-the-art models on the Action Genome dataset, achieving 69.7 and 72.6 for [email protected] and [email protected] on PredCLS. In addition, the inference speed can be significantly reduced by 41% with an acceptable drop on [email protected] (69.7 to 66.8) by utilizing fast inference.

Multi-modal tracking gains attention due to its ability to be more accurate and robust in complex scenarios compared to traditional RGB-based tracking. Its key lies in how to fuse multi-modal data and reduce the gap between modalities. However, multi-modal tracking still severely suffers from data deficiency, thus resulting in the insufficient learning of fusion modules. Instead of building such a fusion module, in this paper, we provide a new perspective on multi-modal tracking by attaching importance to the multi-modal visual prompts. We design a novel multi-modal prompt tracker (ProTrack), which can transfer the multi-modal inputs to a single modality by the prompt paradigm. By best employing the tracking ability of pre-trained RGB trackers learning at scale, our ProTrack can achieve high-performance multi-modal tracking by only altering the inputs, even without any extra training on multi-modal data. Extensive experiments on 5 benchmark datasets demonstrate the effectiveness of the proposed ProTrack.

Studies of image captioning are shifting towards a trend of a fully end-to-end paradigm by leveraging powerful visual pre-trained models and transformer-based generation architecture for more flexible model training and faster inference speed. State-of-the-art approaches simply extract isolated concepts or attributes to assist description generation. However, such approaches do not consider the hierarchical semantic structure in the textual domain, which leads to an unpredictable mapping between visual representations and concept words. To this end, we propose a novel Progressive Tree-Structured prototype Network (dubbed PTSN), which is the first attempt to narrow down the scope of prediction words with appropriate semantics by modeling the hierarchical textual semantics. Specifically, we design a novel embedding method called tree-structured prototype, producing a set of hierarchical representative embeddings which capture the hierarchical semantic structure in textual space. To utilize such tree-structured prototypes into visual cognition, we also propose a progressive aggregation module to exploit semantic relationships within the image and prototypes. By applying our PTSN to the end-to-end captioning framework, extensive experiments conducted on MSCOCO dataset show that our method achieves a new state-of-the-art performance with 144.2% (single model) and 146.5% (ensemble of 4 models) CIDEr scores on 'Karpathy' split and 141.4% (c5) and 143.9% (c40) CIDEr scores on the official online test server. Trained models and source code have been released at: https://github.com/NovaMind-Z/PTSN.

The Third International Workshop on Human-Centric Multimedia Analysis concentrates on the tasks of human-centric analysis with multimedia and multimodal information. It involves multiple tasks such as face detection and recognition, human body pattern analysis, person re-identification, human action detection, etc. Today, multiple multimedia sensing technologies and large-scale computing infrastructures are emerging at a rapid velocity a wide variety of big multi-modality data for human-centric analysis, which provides rich knowledge to help tackle these challenges. Researchers have strived to push the limits of human-centric multimedia analysis in a wide variety of applications, such as intelligent surveillance, retailing, fashion design, and services. Therefore, this workshop aims to provide a platform to bridge the gap between the communities of human analysis and multimedia.

Cross-Domain Few-Shot Learning (CDFSL) aims for training an adaptable model that can learn out-of-domain classes with a handful of samples. Compared to the well-studied few-shot learning problem, the difficulty for CDFSL lies in that the available training data from test tasks is not only extremely limited but also presents severe class differences from training tasks. To tackle this challenge, we propose Style-aware Episodic Training with Robust Contrastive Learning (SET-RCL), which is motivated by the key observation that a remarkable style-shift between tasks from source and target domains plays a negative role in cross-domain generalization. SET-RCL addresses the style-shift from two perspectives: 1) simulating the style distributions of unknown target domains (data perspective); and 2) learning a style-invariant representation (model perspective). Specifically, Style-aware Episodic Training (SET) focuses on manipulating the styl distribution of training tasks in the source domain, such that the learned model can achieve better adaption on test tasks with domain-specific styles. To further improve cross-domain generalization under style-shift, we develop Robust Contrastive Learning (RCL) to capture style-invariant and discriminative representations from the manipulated tasks. Notably,our SET-RCL is orthogonal to existing FSL approaches, thus can be adopted as a "free-lunch" for boosting their CDFSL performance. Extensive experiments on nine benchmark datasets and six baseline methods demonstrate the effectiveness of our method.

Cross-modal retrieval aims to build correspondence between multiple modalities by learning a common representation space. Typically, an image can match multiple texts semantically and vice versa, which significantly increases the difficulty of this task. To address this problem, probabilistic embedding is proposed to quantify these many-to-many relationships. However, existing datasets (e.g., MS-COCO) and metrics (e.g., Recall@K) cannot fully represent these diversity correspondences due to non-exhaustive annotations. Based on this observation, we utilize semantic correlation computed by CIDEr to find the potential correspondences. Then we present an effective metric, named Average Semantic Precision (ASP), which can measure the ranking precision of semantic correlation for retrieval sets. Additionally, we introduce a novel and concise objective, coined Differentiable ASP Approximation (DAA). Concretely, DAA can optimize ASP directly by making the ranking function of ASP differentiable through a sigmoid function. To verify the effectiveness of our approach, extensive experiments are conducted on MS-COCO, CUB Captions, and Flickr30K, which are commonly used in cross-modal retrieval. The results show that our approach obtains superior performance over the state-of-the-art approaches on all metrics. The code and trained models are released at https://github.com/leolee99/2022-NeurIPS-DAA.

Unrestricted color attacks, which manipulate semantically meaningful color of an image, have shown their stealthiness and success in fooling both human eyes and deep neural networks. However, current works usually sacrifice the flexibility of the uncontrolled setting to ensure the naturalness of adversarial examples. As a result, the black-box attack performance of these methods is limited. To boost transferability of adversarial examples without damaging image quality, we propose a novel Natural Color Fool (NCF) which is guided by realistic color distributions sampled from a publicly available dataset and optimized by our neighborhood search and initialization reset. By conducting extensive experiments and visualizations, we convincingly demonstrate the effectiveness of our proposed method. Notably, on average, results show that our NCF can outperform state-of-the-art approaches by 15.0%$\sim$32.9% for fooling normally trained models and 10.0%$\sim$25.3% for evading defense methods. Our code is available at https://github.com/VL-Group/Natural-Color-Fool.

As a crucial approach for compact representation learning, hashing has achieved great success in effectiveness and efficiency. Numerous heuristic Hamming space metric learning objectives are designed to obtain high-quality hash codes. Nevertheless, a theoretical analysis of criteria for learning good hash codes remains largely unexploited. In this paper, we prove that inter-class distinctiveness and intra-class compactness among hash codes determine the lower bound of hash codes' performance. Promoting these two characteristics could lift the bound and improve hash learning. We then propose a surrogate model to fully exploit the above objective by estimating the posterior of hash codes and controlling it, which results in a low-bias optimization. Extensive experiments reveal the effectiveness of the proposed method. By testing on a series of hash-models, we obtain performance improvements among all of them, with an up to $26.5\%$ increase in mean Average Precision and an up to $20.5\%$ increase in accuracy. Our code is publicly available at https://github.com/VL-Group/LBHash.

Human densepose estimation, aiming at establishing dense correspondences between 2D pixels of human body and 3D human body template, is a key technique in enabling machines to have an understanding of people in images. It still poses several challenges due to practical scenarios where real-world scenes are complex and only partial annotations are available, leading to incompelete or false estimations. In this work, we present a novel framework to detect the densepose of multiple people in an image. The proposed method, which we refer to Knowledge Transfer Network (KTN), tackles two main problems: 1) how to refine image representation for alleviating incomplete estimations, and 2) how to reduce false estimation caused by the low-quality training labels (i.e., limited annotations and class-imbalance labels). Unlike existing works directly propagating the pyramidal features of regions for densepose estimation, the KTN uses a refinement of pyramidal representation, where it simultaneously maintains feature resolution and suppresses background pixels, and this strategy results in a substantial increase in accuracy. Moreover, the KTN enhances the ability of 3D based body parsing with external knowledges, where it casts 2D based body parsers trained from sufficient annotations as a 3D based body parser through a structural body knowledge graph. In this way, it significantly reduces the adverse effects caused by the low-quality annotations. The effectiveness of KTN is demonstrated by its superior performance to the state-of-the-art methods on DensePose-COCO dataset. Extensive ablation studies and experimental results on representative tasks (e.g., human body segmentation, human part segmentation and keypoints detection) and two popular densepose estimation pipelines (i.e., RCNN and fully-convolutional frameworks), further indicate the generalizability of the proposed method.

Meta-learning offers an effective solution to learn new concepts under scarce supervision through an episodic-training scheme: a series of target-like tasks sampled from base classes are sequentially fed into a meta-learner to extract cross-task knowledge, which can facilitate the quick acquisition of task-specific knowledge of the target task with few samples. Despite its noticeable improvements, the episodic-training strategy samples tasks randomly and uniformly, without considering their hardness and quality, which may not progressively improve the meta-leaner’s generalization. In this paper, we propose Progressive Meta-learning using tasks from easy to hard. First, based on a predefined curriculum, we develop a Curriculum-Based Meta-learning (CubMeta) method. CubMeta is in a stepwise manner, and in each step, we design a BrotherNet module to establish harder tasks and an effective learning scheme for obtaining an ensemble of stronger meta-learners. Then we move a step further to propose an end-to-end Self-Paced Meta-learning (SepMeta) method. The curriculum in SepMeta is effectively integrated as a regularization term into the objective so that the meta-learner can measure the hardness of tasks adaptively, according to what the model has already learned. Extensive experiments on benchmark datasets demonstrate the effectiveness of the proposed methods. Our code is available athttps://github.com/nobody-777.

Scene graph generation (SGG) is built on top of detected objects to predict object pairwise visual relations for describing the image content abstraction. Existing works have revealed that if the links between objects are given as prior knowledge, the performance of SGG is significantly improved. Inspired by this observation, in this article, we propose a relation regularized network (R2-Net), which can predict whether there is a relationship between two objects and encode this relation into object feature refinement and better SGG. Specifically, we first construct an affinity matrix among detected objects to represent the probability of a relationship between two objects. Graph convolution networks (GCNs) over this relation affinity matrix are then used as object encoders, producing relation-regularized representations of objects. With these relation-regularized features, our R2-Net can effectively refine object labels and generate scene graphs. Extensive experiments are conducted on the visual genome dataset for three SGG tasks (i.e., predicate classification, scene graph classification, and scene graph detection), demonstrating the effectiveness of our proposed method. Ablation studies also verify the key roles of our proposed components in performance improvement.

Recently, integrating vision and language for in-depth video understanding e.g., video captioning and video question answering, has become a promising direction for artificial intelligence. However, due to the complexity of video information, it is challenging to extract a video feature that can well represent multiple levels of concepts i.e., objects, actions and events. Meanwhile, content completeness and syntactic consistency play an important role in high-quality language-related video understanding. Motivated by these, we propose a novel framework, named Hierarchical Representation Network with Auxiliary Tasks (HRNAT), for learning multi-level representations and obtaining syntax-aware video captions. Specifically, the Cross-modality Matching Task enables the learning of hierarchical representation of videos, guided by the three-level representation of languages. The Syntax-guiding Task and the Vision-assist Task contribute to generating descriptions which are not only globally similar to the video content, but also syntax-consistent to the ground-truth description. The key components of our model are general and they can be readily applied to both video captioning and video question answering tasks. Performances for the above tasks on several benchmark datasets validate the effectiveness and superiority of our proposed method compared with the state-of-the-art methods. Codes and models are also released https://github.com/riesling00/HRNAT.

Referring Expression Comprehension (REC) aims to localize an image region of a given object described by a natural-language expression. While promising performance has been demonstrated, existing REC algorithms make a strong assumption that training data feeding into a model are given upfront, which degrades its practicality for real-world scenarios. In this paper, we propose Continual Referring Expression Comprehension (CREC), a new setting for REC, where a model is learning on a stream of incoming tasks. In order to continuously improve the model on sequential tasks without forgetting prior learned knowledge and without repeatedly re-training from a scratch, we propose an effective baseline method named Dual Modular Memorization (DMM), which alleviates the problem of catastrophic forgetting by two memorization modules: Implicit-Memory and Explicit-Memory. Specifically, the former module aims to constrain drastic changes to important parameters learned on old tasks when learning a new task; while the latter module maintains a buffer pool to dynamically select and store representative samples of each seen task for future rehearsal. We create three benchmarks for the new CREC setting, by respectively re-splitting three widely-used REC datasets RefCOCO, RefCOCO+ and RefCOCOg into sequential tasks. Extensive experiments on the constructed benchmarks demonstrate that our DMM method significantly outperforms other alternatives, based on two popular REC backbones. We make the source code and benchmarks publicly available to foster future progress in this field: https://github.com/zackschen/DMM.

Video Question Answering (VideoQA), which explores spatial-temporal visual information of videos given a linguistic query, has received unprecedented attention over recent years. One of the main challenges lies in locating relevant visual and linguistic information, and therefore various attention-based approaches are proposed. Despite the impressive progress, two aspects are not fully explored by current methods to get proper attention. Firstly, prior knowledge, which in the human cognitive process plays an important role in assisting the reasoning process of VideoQA, is not fully utilized. Secondly, structured visual information (e.g., object) instead of the raw video is underestimated. To address the above two issues, we propose a Prior Knowledge and Object-sensitive Learning (PKOL) by exploring the effect of prior knowledge and learning object-sensitive representations to boost the VideoQA task. Specifically, we first propose a Prior Knowledge Exploring (PKE) module that aims to acquire and integrate prior knowledge into a question feature for feature enriching, where an information retriever is constructed to retrieve related sentences as prior knowledge from the massive corpus. In addition, we propose an Object-sensitive Representation Learning (ORL) module to generate object-sensitive features by interacting object-level features with frame and clip-level features. Our proposed PKOL achieves consistent improvements on three competitive benchmarks (i.e., MSVD-QA, MSRVTT-QA, and TGIF-QA) and gains state-of-the-art performance. The source code is available at https://github.com/zchoi/PKOL.

The type of neural networks widely used in artificial intelligence applications mixes its computation and memory modules in neuron weights and activities. The previously learned information are stored in network weights. When dealing with complex data, e.g., those possessing diverse content or containing long-sequences, some information stored in the weights can be altered drastically or wiped as the training goes, but they are not necessarily unimportant. External memory is a recent technique proposed to prevent from forgetting significant previously learned information. In this work, we aim at taking advantage of this recent technique to advance the similarity learning task that is critical in many real-world artificial intelligence applications. We propose suitable external memory design supported by extended attention mechanism. Two different kinds of memory modules are proposed so that the similarity learning process can dynamically shift focus over a wide range of diverse content contained by the training data. Effectiveness of the proposed method is demonstrated through evaluations based on different image retrieval tasks and compared against various state-of-the-art algorithms in the field.

Targeted attack aims to mislead the classification model to a specific class, and it can be further divided into black-box and white-box targeted attack depending on whether the classification model is known. A growing number of approaches rely on disrupting the image representations to craft adversarial examples. However, this type of methods often suffer from either lowwhite-box targetedattack success rate or poorblack-box targetedattack transferability. To address these problems, we propose a Transferable Attentive Attack (TAA) method which adds perturbation to clean images based on the attended regions and features. This is motivated by one important observation that deep-learning based classification models (or even shallow-learning based models like SIFT) make the prediction mainly based on the informative and discriminative regions of an image. Specifically, the corresponding features of the informative regions are firstly extracted, and theanchorimage’s features are iteratively “pushed” away from the source class and simultaneously “pulled” closer to the target class along with attacking. Moreover, we introduce a new strategy that the attack selects the centroids of source and target class cluster as the input of triplet loss to achieve high transferability. Experimental results demonstrate that our method improves the transferability of adversarial example, while maintaining higher success rate forwhite-box targetedattacks compared with the state-of-the-arts. In particular, TAA attacks on image-representation based task like VQA also result in a significant performance drop in terms of accuracy.

Face aging and rejuvenation is applied to predict what a person looks like at different ages. While prior work brought about a significant progress in this topic, there are two central problems remaining to be solved : 1) most prior works require sequential data during training, while it is very rare in existing datasets; and 2) how to render an aging face and preserve personality at the same time. To deal with these problems, we develop a novel dual conditional GANs mechanism, thus aging faces can be trained with multiple sets of unlabeled facial images of different ages. Our basic architecture is AgeGAN, in which the primal conditional GAN converts input faces to other ages based on relevant age conditions, and the dual conditional GAN learns to invert the task. We further improve our networks, termed AgeGAN++, in which we share the weights between the primal part and the dual part to to streamline the model. Moreover, in order to get more sensible results, a representation disentanglement component is integrated with the latent facial representation, and an enhanced discriminator is applied on the generated process. In addition, we firstly perform an interpolation experiment to demonstrate that our generators are powerful and effective for face aging and rejuvenation. Experimental results on four public datasets demonstrate the appealing performance of the proposed methods by comparing with the state-of-the-art methods. Our code and a demo are released athttps://github.com/Sherry-JQ/AgeGAN.

Fully mining visual cues to aid in content understanding is crucial for video captioning. However, most state-of-the-art video captioning methods are limited to generating captions purely based on straightforward information while ignoring the scenario and context information. To fill the gap, we propose a novel, simple but effective scenario-aware recurrent transformer (SART) model to execute video captioning. Our model contains a “scenario understanding” module to obtain a global perspective across multiple frames, providing a specific scenario to guarantee a goal-directed description. Moreover, for the sake of achieving narrative continuity in the generated paragraph, a unified recurrent transformer is adopted. To demonstrate the effectiveness of our proposed SART, we have conducted comprehensive experiments on various large-scale video description datasets, including ActivityNet, YouCookII, and VideoStory. Additionally, we extend a story-oriented evaluation framework for assessing the quality of the generated caption more precisely. The superior performance has shown that SART has a strong ability to generate correct, deliberative, and narrative coherent video descriptions.

Despite of the recent great progress on multi-person pose estimation, existing solutions still remain challenging under the condition of "crowded scenes'', where RGB images capture complex real-world scenes with highly-overlapped people, severe occlusions and diverse postures. In this work, we focus on two main problems: 1) how to design an effective pipeline for crowded scenes pose estimation; and 2) how to equip this pipeline with the ability of relation modeling for interference resolving. To tackle these problems, we propose a new pipeline named Relation based Skeleton Graph Network (RSGNet). Unlike existing works that directly predict joints-of-target by labeling joints-of-interference as false positive, we first encourage all joints to be predicted. And then, a Target-aware Relation Parser (TRP) is designed to model the relation over all predicted joints, resulting in a target-aware encoding. This new pipeline will largely relieve the confusion of the joints estimation model when seeing identical joints with totally distinct labels (e.g., the identical hand exists in two bounding boxes). Furthermore, we introduce a Skeleton Graph Machine (SGM) to model the skeleton-based commonsense knowledge, aiming to estimate the target pose with the constraint of human body structure. Such skeleton-based constraint can help to deal with the challenges in crowded scenes from a reasoning perspective. Solid experiments on pose estimation benchmarks demonstrate that our method outperforms existing state-of-the-art methods.

The scene graph generation (SGG) task aims to detect visual relationship triplets, i.e., subject, predicate, object, in an image, providing a structural vision layout for scene understanding. However, current models are stuck in common predicates, e.g., "on" and "at", rather than informative ones, e.g., "standing on" and "looking at", resulting in the loss of precise information and overall performance. If a model only uses "stone on road" rather than "blocking" to describe an image, it is easy to misunderstand the scene. We argue that this phenomenon is caused by two key imbalances between informative predicates and common ones, i.e., semantic space level imbalance and training sample level imbalance. To tackle this problem, we propose BA-SGG, a simple yet effective SGG framework based on balance adjustment but not the conventional distribution fitting. It integrates two components: Semantic Adjustment (SA) and Balanced Predicate Learning (BPL), respectively for adjusting these imbalances. Benefited from the model-agnostic process, our method is easily applied to the state-of-the-art SGG models and significantly improves the SGG performance. Our method achieves 14.3%, 8.0%, and 6.1% higher Mean Recall (mR) than that of the Transformer model at three scene graph generation sub-tasks on Visual Genome, respectively. Codes are publicly available1.

Human-Object Interaction (HOI) detection is a fundamental visual task aiming at localizing and recognizing interactions between humans and objects. Existing works focus on the visual and linguistic features of the humans and objects. However, they do not capitalise on the high-level and semantic relationships present in the image, which provides crucial contextual and detailed relational knowledge for HOI inference. We propose a novel method to exploit this information, through the scene graph, for the Human-Object Interaction (SG2HOI) detection task. Our method, SG2HOI, incorporates the SG information in two ways: (1) we embed a scene graph into a global context clue, serving as the scene-specific environmental context; and (2) we build a relation-aware message-passing module to gather relationships from objects' neighborhood and transfer them into interactions. Empirical evaluation shows that our SG2HOI method outperforms the state-of-the-art methods on two benchmark HOI datasets: V-COCO and HICO-DET. Code will be available at https://github.com/ht014/SG2HOI.

Video captioning is to understand a video in depth and generate high-quality descriptions. However, due to the complexity of videos, it is challenging to extract a video feature that can well represent multiple levels of concepts i.e., events, objects and actions. Meanwhile, content completeness and syntactic consistency play an important role in high-quality video captioning. Motivated by these, we propose a novel framework, named Hierarchical Representation Network with Auxiliary Tasks (HRNAT), for learning multi-level representations, and generating syntax-aware video captioning. Specifically, the Cross-modality Matching Task enables the learning of hierarchical representation of videos, guided by the three-level representation of languages. The Syntax-guiding Task and Vision-assist Task contribute to generating descriptions to be not only globally similar to the video, but also syntax-consistent to the ground-truth description. Finally, performances on several benchmark datasets validate the effectiveness and superiority of our method compared with state-of-the-art methods.

Visual dialog aims to generate an answer to each question based on an image and dialog history. Despite recent progress, existing methods still undergo degradation on the condition of complex scenarios. Handling these scenarios depends on logical reasoning that requires common sense priors. In this paper, we propose a novel visual dialog pipeline, named Structured Knowledge-Aware Network (SKANet), consisting of a Multi-Modality Fusion Module, an Image Knowledge-Aware Module, and a Caption Knowledge-Aware Module. The Multi-Modality Fusion Module explores the textual context about the dialog history and visual content. To deal with the complex scenarios, the Image and Caption Knowledge-Aware Modules construct common sense knowledge graphs from ConceptNet. Experimental results on the VisDial v1.0 dataset show that our proposed method effectively outperforms comparative methods.

By adding human-imperceptible perturbations to images, DNNs can be easily fooled. As one of the mainstream methods, feature space targeted attacks perturb images by modulating their intermediate feature maps, for the discrepancy between the intermediate source and target features is minimized. However, the current choice of pixel-wise Euclidean Distance to measure the discrepancy is questionable because it unreasonably imposes a spatial-consistency constraint on the source and target features. Intuitively, an image can be categorized as "cat'' no matter the cat is on the left or right of the image. To address this issue, we propose to measure this discrepancy using statistic alignment. Specifically, we design two novel approaches called Pair-wise Alignment Attack and Global-wise Alignment Attack, which attempt to measure similarities between feature maps by high-order statistics with translation invariance. Furthermore, we systematically analyze the layer-wise transferability with varied difficulties to obtain highly reliable attacks. Extensive experiments verify the effectiveness of our proposed method, and it outperforms the state-of-the-art algorithms by a large margin. Our code is publicly available at https://github.com/yaya-cheng/PAA-GAA.

Replacing objects in images is a practical functionality of Photoshop, e.g., clothes changing. This task is defined as Unsupervised Deformable-Instances Image-to-Image Translation (UDIT), which maps multiple foreground instances of a source domain to a target domain, involving significant changes in shape. In this paper, we propose an effective pipeline named Mask-Guided Deformable-instances GAN (MGD-GAN) which first generates target masks in batch and then utilizes them to synthesize corresponding instances on the background image, with all instances efficiently translated and background well preserved. To promote the quality of synthesized images and stabilize the training, we design an elegant training procedure which transforms the unsupervised mask-to-instance process into a supervised way by creating paired examples. To objectively evaluate the performance of UDIT task, we design new evaluation metrics which are based on the object detection. Extensive experiments on four datasets demonstrate the significant advantages of our MGD-GAN over existing methods both quantitatively and qualitatively. Furthermore, our training time consumption is hugely reduced compared to the state-of-the-art. The code could be available at https://github.com/sitongsu/MGD_GAN.

Visual dialog is a fundamental vision-language task where an AI agent holds a meaningful dialogue about visual content with humans in nature. However, this task remains challenging, since there is still no consensus way to capture rich visual contextual information contained in the environment rather than only focusing on visual objects. Furthermore, conventional methods suffer from the single-answer learning strategy, where it only accepts one correct answer without considering the diverse expressions of the language (i.e., one identical meaning but multiple expressions via rephrasing or adopting synonyms etc). In this paper, we introduce Contextual-Aware Representation and linguistic-diverse Expression (CARE), a novel plug-and-play framework with contextual-based graph embedding and curriculum contrastive learning to solve the above two issues. Specifically, the contextual-based graph embedding (CGE) module aims to integrate the environmental context information with visual objects to improve the answer quality. In addition, we propose a curriculum contrastive learning (CCL) paradigm to imitate the learning habits of humans when facing a question with multiple correct answers sharing the same meaning but with diverse expressions. To support CCL, a CCL loss is designed to progressively strengthen the model's ability in identifying the answers with correct semantics. Extensive experiments are conducted on two benchmark datasets, and our proposed method outperforms the state-of-the-arts by a considerable margin on VisDial V1.0 (4.63% NDCG) and VisDial V0.9 (1.27% MRR, 1.74% [email protected], 0.87% [email protected], 1.28% [email protected], 0.26 Mean.

The Second International Workshop on Human-centric Multimedia Analysis is focused on human-centric analysis using multimedia information. The human-centric multimedia analysis is one of the fundamental and challenging problems of multimedia understanding. It involves various human-centric analysis tasks like face recognition, human pose estimation, person re-identification, human action recognition, person tracking, human-computer interaction, etc. Nowadays, various multimedia sensing devices and large-scale computing infrastructures are generating a wide variety of multi-modality data at a rapid velocity, which supplies rich knowledge to tackle these challenges for human-centric analysis. Researchers and engineers have strived to push the limits of human-centric multimedia analysis in a wide variety of applications, such as smart city, retailing, intelligent manufacturing, and public services. To this end, our workshop aims to provide a platform to promote exchanges and integration for the fields of human analysis and multimedia.

Despite the success of single-domain person re-identification (ReID), current supervised models degrade dramatically when deployed to unseen domains, mainly due to the discrepancy across cameras. To tackle this issue, we propose an Adversarial Disentangling Learning (ADL) framework to decouple camera-related and ID-related features, which can be readily used for camera-agnostic person ReID. ADL adopts a discriminative way instead of the mainstream generative styles in disentangling methods, eg., GAN or VAE based, because for person ReID task only the information to discriminate IDs is needed, and more information to generate images are redundant and may be noisy. Specifically, our model involves a feature separation module that encodes images into two separate feature spaces and a disentangled feature learning module that performs adversarial training to minimize mutual information. We design an effective solution to approximate and minimize mutual information by transforming it into a discrimination problem. The two modules are co-designed to obtain strong generalization ability by only using source dataset. Extensive experiments on three public benchmarks show that our method outperforms the state-of-the-art generalizable person ReID model by a large margin. Our code is publicly available at https://github.com/luckyaci/ADL_ReID.

Recently, performing semantic editing of an image by modifying a scene graph has been proposed to support high-level image manipulation, and plays an important role for image generation. However, existing methods are all based on bounding boxes, and they suffer from the bounding box constraint. First, a bounding box often involves other instances (e.g, objects or environments) which do not need to be modified, but existing methods manipulate all the contents included in the bounding box. Secondly, prior methods fail to support adding instances when the bounding box of the target instance cannot be provided. To address the two issues above, we propose a novel bounding box free approach, which consists of two parts: a Local Bounding Box Free (Local-BBox-Free) Mask Generation and a Global Bounding Box Free (Global-BBox-Free) Instance Generation. The first part relieves the model of reliance on bounding boxes by generating the mask of the target instance to be manipulated without using the target instance bounding box. This enables our method to be the first to support fully functional image manipulation using scene graphs, including adding, removing, replacing and repositing instances. The second part is designed to synthesize the target instance directly from the generated mask and then paste it back to the inpainted original image using the generated mask, which preserves the unchanged part to the largest extent and precisely controls the target instance generation. Extensive experiments on Visual Genome and COCO-Stuff demonstrate that our model significantly surpasses the state-of-the-art both quantitatively and qualitatively.

Crowded scenes human pose estimation remains challenging, which requires joint comprehension of multi-persons and their keypoints in a highly complex scenario. The top-down mechanism, which is a detect-then-estimate pipeline, has become the mainstream solution for general pose estimation and obtained impressive progress. However, simply applying this mechanism to crowded scenes pose estimation results in unsatisfactory performance due to several issues, in particular involving missing keypoints in crowds and ambiguously labeling during training. To tackle above two issues, we introduce a novel method named Semantic-aware Transfer with Instance-adaptive Parsing (STIP). Specifically, our STIP first enhances the discriminative power of pixel-level representations with a semantic-aware mechanism, where it smartly decides which pixels to enhance and what semantic embeddings to add. In this way, the missing keypoints detection can be alleviated.Secondly, instead of adopting a standard regressor with fixed parameters, we propose a new instance-adaptive parsing method, where it dynamically generates instance-specific parameters for reducing adverse effects caused by ambiguously labeling. Notably, STIP is designed in a plugin fashion and it can be integrated into any top-down models, such as HRNet. Extensive experiments on two challenging benchmarks, i.e., CrowdPose and MS-COCO, demonstrate the superiority and generalizability of our approach.

Montreal Cognitive Assessment (MoCA) test is an auxiliary medical screening method for Alzheimer's disease (AD). During the traditional process, a testee is required to conduct several test items on the paper questionnaire following the guidance of a medical staff. It is inefficient and dependents largely on the doctor's subjective judgment and experience level. Therefore, we propose an Interactive and Intelligent AD Auxiliary Screening (IAS) system consisting of speech-based Interactive Unit Testing Module (IUTM) and truth-based Intelligent Analysis Module (IAM), both of which are developed by deep learning techniques. Following the guidance of voice commands, the testee could achieve the MoCA test independently in IUTM just by a mobile device, and then the testing data is analyzed accurately and objectively by IAM. Moreover, the electronic system is beneficial to collect and analyze clinical data for further research compared to the traditional method. And the system is deployed in the Department of Neurology, Sichuan Provincial People's Hospital in June 2021 and has been used in the clinical screening of Alzheimer's disease.

Image-Text Matching (ITM) is a fundamental and emerging task, which plays a key role in cross-modal understanding. It remains a challenge because prior works mainly focus on learning fine-grained (i.e. coarse and/or phrase) correspondence, without considering the syntactical correspondence. In theory, a sentence is not only a set of words or phrases but also a syntactic structure, consisting of a set of basic syntactic tuples (i.e.(attribute) object - predicate - (attribute) subject). Inspired by this, we propose a Conceptual and Syntactical Cross-modal Alignment with Cross-level Consistency (CSCC) for Image-text Matching by simultaneously exploring the multiple-level cross-modal alignments across the concept and syntactic with a consistency constraint. Specifically, a conceptual-level cross-modal alignment is introduced for exploring the fine-grained correspondence, while a syntactical-level cross-modal alignment is proposed to explicitly learn a high-level syntactic similarity function. Moreover, an empirical cross-level consistent attention loss is introduced to maintain the consistency between cross-modal attentions obtained from the above two cross-modal alignments. To justify our method, comprehensive experiments are conducted on two public benchmark datasets, i.e. MS-COCO (1K and 5K) and Flickr30K, which show that our CSCC outperforms state-of-the-art methods with fairly competitive improvements.

Meta-learning offers an effective solution to learn new concepts with scarce supervision through an episodic training scheme: a series of target-like tasks sampled from base classes are sequentially fed into a meta-learner to extract common knowledge across tasks, which can facilitate the quick acquisition of task-specific knowledge of the target task with few samples. Despite its noticeable improvements, the episodic training strategy samples tasks randomly and uniformly, without considering their hardness and quality, which may not progressively improve the meta-leaner's generalization ability. In this paper, we present a Curriculum-Based Meta-learning (CubMeta) method to train the meta-learner using tasks from easy to hard. Specifically, the framework of CubMeta is in a progressive way, and in each step, we design a module named BrotherNet to establish harder tasks and an effective learning scheme for obtaining an ensemble of stronger meta-learners. In this way, the meta-learner's generalization ability can be progressively improved, and better performance can be obtained even with fewer training tasks. We evaluate our method for few-shot classification on two benchmarks - mini-ImageNet and tiered-ImageNet, where it achieves consistent performance improvements on various meta-learning paradigms.

Fine-grained visual recognition tasks typically require training data with reliable acquisition and annotation processes. Acquiring such datasets with precise fine-grained annotations is very expensive and time-consuming. Conversely, a vast amount of web data is relatively easy to obtain with nearly no human effort. Nevertheless, the presence of label noise in web images becomes a huge obstacle for training robust fine-grained recognition models. In this work, we investigate the noisy label problem and propose a method that can specifically distinguish in- and out-of-distribution noisy samples. It can purify the web training data by discarding out-of-distribution noisy images and relabeling in-distribution ones. After purification, we can train the model on a less noisy web training set to achieve better robustness and performance. Extensive experiments on three real-world web datasets for fine-grained visual recognition demonstrate the superiority of our approach.

Abstract Person re‐identification (Re‐ID) is in significant demand for intelligent security and single or multiple‐target tracking. However, there are issues in the person Re‐ID tasks, such as sharp decline in cross‐data sets detection accuracy, poor generalization and cross‐domain ability of the model. This work mainly studies the generalization and adaptation of cross‐domain person Re‐ID models. Different from most existing methods for cross‐domain Re‐ID tasks, the authors use diversified spatial semantic feature in pixel‐level learning in the target domain to improve the generality and adaptability of the model. In the case that no information of the target domain is used during the model training, the trained model is directly tested on the data set of the target domain. It has proven effective to add the attention cascade module into the backbone network combining with the part‐level branch. The authors conducted extensive experiments based on the three data sets of Market‐1501, DukeMTMC‐ReID and MSMT17, resulting in both single‐domain and cross‐domain tests with an average improvement of Rank1 and mAP values of about 10% compared with Baseline through the authors' proposed method named Part‐Level Attention Network.

Traditional operations, e.g. graph edit distance (GED), are no longer suitable for processing the massive quantities of graph-structured data now available, due to their irregular structures and high computational complexities. With the advent of graph neural networks (GNNs), the problems of graph representation and graph similarity search have drawn particular attention in the field of computer vision. However, GNNs have been less studied for efficient and fast retrieval after graph representation. To represent graph-based data, and maintain fast retrieval while doing so, we introduce an efficient hash model with graph neural networks (HGNN) for a newly designed task (i.e. fast graph-based data retrieval). Due to its flexibility, HGNN can be implemented in both an unsupervised and supervised manner. Specifically, by adopting a graph neural network and hash learning algorithms, HGNN can effectively learn a similarity-preserving graph representation and compute pair-wise similarity or provide classification via low-dimensional compact hash codes. To the best of our knowledge, our model is the first to address graph hashing representation in the Hamming space. Our experimental results reach comparable prediction accuracy to full-precision methods and can even outperform traditional models in some cases. In real-world applications, using hash codes can greatly benefit systems with smaller memory capacities and accelerate the retrieval speed of graph-structured data. Hence, we believe the proposed HGNN has great potential in further research.

Supervised cross-modal hashing has attracted much attention. However, there are still some challenges, e.g., how to effectively embed the label information into binary codes, how to avoid using a large similarity matrix and make a model scalable to large-scale datasets, how to efficiently solve the binary optimization problem. To address these challenges, in this paper, we present a novel supervised cross-modal hashing method, i.e., scalaBle Asymmetric discreTe Cross-modal Hashing, BATCH for short. It leverages collective matrix factorization to learn a common latent space for the labels and different modalities, and embeds the labels into binary codes by minimizing a distance-distance difference problem. Furthermore, it builds a connection between the common latent space and the hash codes by an asymmetric strategy. In the light of this, it can perform cross-modal retrieval and embed more similarity information into the binary codes. In addition, it introduces a quantization minimization term and orthogonal constraints into the optimization problem, and generates the binary codes discretely. Therefore, the quantization error and redundancy may be much reduced. Moreover, it is a two-step method, making the optimization simple and scalable to large-scale datasets. Extensive experimental results on three benchmark datasets demonstrate that BATCH outperforms some state-of-the-art cross-modal hashing methods in terms of accuracy and efficiency.

Visual question answering (VQA) that involves understanding an image and paired questions develops very quickly with the boost of deep learning in relevant research fields, such as natural language processing and computer vision. Existing works highly rely on the knowledge of the data set. However, some questions require more professional cues other than the data set knowledge to answer questions correctly. To address such an issue, we propose a novel framework named a knowledge-based augmentation network (KAN) for VQA. We introduce object-related open-domain knowledge to assist the question answering. Concretely, we extract more visual information from images and introduce a knowledge graph to provide the necessary common sense or experience for the reasoning process. For these two augmented inputs, we design an attention module that can adjust itself according to the specific questions, such that the importance of external knowledge against detected objects can be balanced adaptively. Extensive experiments show that our KAN achieves state-of-the-art performance on three challenging VQA data sets, i.e., VQA v2, VQA-CP v2, and FVQA. In addition, our open-domain knowledge is also beneficial to VQA baselines. Code is available at https://github.com/yyyanglz/KAN.

Learning accurate low-dimensional embeddings for a network is a crucial task as it facilitates many network analytics tasks. Moreover, the trained embeddings often require a significant amount of space to store, making storage and processing a challenge, especially as large-scale networks become more prevalent. In this paper, we present a novel semi-supervised network embedding and compression method, SNEQ, that is competitive with state-of-art embedding methods while being far more space- and time-efficient. SNEQ incorporates a novel quantisation method based on a self-attention layer that is trained in an end-to-end fashion, which is able to dramatically compress the size of the trained embeddings, thus reduces storage footprint and accelerates retrieval speed. Our evaluation on four real-world networks of diverse characteristics shows that SNEQ outperforms a number of state-of-the-art embedding methods in link prediction, node classification and node recommendation. Moreover, the quantised embedding shows a great advantage in terms of storage and time compared with continuous embeddings as well as hashing methods.

The recent advances in 3D Convolutional Neural Networks (3D CNNs) have shown promising performance for untrimmed video action detection, employing the popular detection framework that heavily relies on the temporal action proposal generations as the input of the action detector and localization regressor. In practice the proposals usually contain strong intra and inter relations among them, mainly stemming from the temporal and spatial variations in the video actions. However, most of existing 3D CNNs ignore the relations and thus suffer from the redundant proposals degenerating the detection performance and efficiency. To address this problem, we propose graph attention based proposal 3D ConvNets (AGCN-P-3DCNNs) for video action detection. Specifically, our proposed graph attention is composed of intra attention based GCN and inter attention based GCN. We use intra attention to learn the intra long-range dependencies inside each action proposal and update node matrix of Intra Attention based GCN, and use inter attention to learn the inter dependencies between different action proposals as adjacency matrix of Inter Attention based GCN. Afterwards, we fuse intra and inter attention to model intra long-range dependencies and inter dependencies simultaneously. Another contribution is that we propose a simple and effective framewise classifier, which enhances the feature presentation capabilities of backbone model. Experiments on two proposal 3D ConvNets based models (P-C3D and P-ResNet) and two popular action detection benchmarks (THUMOS 2014, ActivityNet v1.3) demonstrate the state-of-the-art performance achieved by our method. Particularly, P-C3D embedded with our module achieves average mAP 3.7% improvement on THUMOS 2014 dataset compared to original model.

Employing attention mechanisms to model both global and local features as a final pedestrian representation has become a trend for person re-identification (Re-ID) algorithms. A potential limitation of these methods is that they focus on the most salient features, but the re-identification of a person may rely on diverse clues masked by the most salient features in different situations, e.g., body, clothes or even shoes. To handle this limitation, we propose a novel Salience-guided Cascaded Suppression Network (SCSN) which enables the model to mine diverse salient features and integrate these features into the final representation by a cascaded manner. Our work makes the following contributions: (i) We observe that the previously learned salient features may hinder the network from learning other important information. To tackle this limitation, we introduce a cascaded suppression strategy, which enables the network to mine diverse potential useful features that be masked by the other salient features stage-by-stage and each stage integrates different feature embedding for the last discriminative pedestrian representation. (ii) We propose a Salient Feature Extraction (SFE) unit, which can suppress the salient features learned in the previous cascaded stage and then adaptively extracts other potential salient feature to obtain different clues of pedestrians. (iii) We develop an efficient feature aggregation strategy that fully increases the network’s capacity for all potential salience features. Finally, experimental results demonstrate that our proposed method outperforms the state-of-the-art methods on four large-scale datasets. Especially, our approach exceeds the current best method by over 7% on the CUHK03 dataset.

Weight and activation binarization is an effective approach to deep neural network compression and can accelerate the inference by leveraging bitwise operations. Although many binarization methods have improved the accuracy of the model by minimizing the quantization error in forward propagation, there remains a noticeable performance gap between the binarized model and the full-precision one. Our empirical study indicates that the quantization brings information loss in both forward and backward propagation, which is the bottleneck of training accurate binary neural networks. To address these issues, we propose an Information Retention Network (IR-Net) to retain the information that consists in the forward activations and backward gradients. IR-Net mainly relies on two technical contributions: (1) Libra Parameter Binarization (Libra-PB): simultaneously minimizing both quantization error and information loss of parameters by balanced and standardized weights in forward propagation; (2) Error Decay Estimator (EDE): minimizing the information loss of gradients by gradually approximating the sign function in backward propagation, jointly considering the updating ability and accurate gradients. We are the first to investigate both forward and backward processes of binary networks from the unified information perspective, which provides new insight into the mechanism of network binarization. Comprehensive experiments with various network structures on CIFAR-10 and ImageNet datasets manifest that the proposed IR-Net can consistently outperform state-of-the-art quantization methods.

It has always been a tricky task to generate image hashing function via deep learning without labels and allocate the relative distance between data through their features. Existing methods can complete this task and prevent the overfitting problem using shallow graph embedding technique. However, they only capture the first-order proximity. To address this problem, we design DSTGeH, a deep self-taught graph embedding hashing framework which learns hash function without labels for image retrieval. DSTGeH introduces deep graph embedding means to capture more complex topological relationships (the second-order proximity) on the graph and maps these relationships into pseudo labels, which enables an end-to-end hash model and helps recognize the samples outside the graph. We present the ablation studies and compare DSTGeH with the state-of-the-art label-free hashing algorithms. Extensive experiments show DSTGeH can achieve the best performances and produce an overwhelming advantage on multi-object datasets.

Image edge detection is considered as a cornerstone task in computer vision. Due to the nature of hierarchical representations learned in CNN, it is intuitive to design side networks utilizing the richer convolutional features to improve the edge detection. However, there is no consensus way to integrate the hierarchical information. In this paper, we propose an effective and end-to-end framework, named Bidirectional Additive Net (BAN), for image edge detection. In the proposed framework, we focus on two main problems: 1) how to design a universal network for incorporating hierarchical information sufficiently; and 2) how to achieve effective information flow between different stages and gradually improve the edge map stage by stage. To tackle these problems, we design a consecutive bottom-up and top-down architecture, where a bottom-up branch can gradually remove detailed or sharp boundaries to enable accurate edge detection and a top-down branch offers a chance of error-correcting by revisiting the low-level features that contain rich textual and spatial information. And attended additive module (AAM) is designed to cumulatively refine edges by selecting pivotal features in each stage. Experimental results show that our proposed methods can improve the edge detection performance to new records and achieve state-of-the-art results on two public benchmarks: BSDS500 and NYUDv2.

Despite the huge progress in scene graph generation in recent years, its long-tail distribution in object relationships remains a challenging and pestering issue. Existing methods largely rely on either external knowledge or statistical bias information to alleviate this problem. In this paper, we tackle this issue from another two aspects: (1) scene-object interaction aiming at learning specific knowledge from a scene via an additive attention mechanism; and (2) long-tail knowledge transfer which tries to transfer the rich knowledge learned from the head into the tail. Extensive experiments on the benchmark dataset Visual Genome on three tasks demonstrate that our method outperforms current state-of-the-art competitors. Our source code is available at https://github.com/htlsn/issg.

Lab2Pix refers to the task of generating photo-realistic images from labels, e.g., semantic labels or sketch labels. Despite inheriting from image-to-image translation, Lab2Pix develops its own characteristics due to the differences between labels and general images. This prevents Lab2Pix task from simply applying general image-to-image translation models. Therefore, we propose an unsupervised framework named Lab2Pix to adaptively synthesize images from labels by elegantly considering the particular properties of label to image synthesis task. Specifically, since the labels contain much less information than the images, we design our generator in a cumulative style which gradually renders synthesized images by fusing features in different levels. Accordingly, the verification process feeds the generated images to a segmentation component and compares the results to the original input label. Furthermore, we propose a sharp enhancement loss, an image consistency loss and a foreground enhancement mask to encourage the network to synthesize photo-realistic images. Experiments conducted on Cityscapes, Facades, Edge2shoes and Edge2handbags datasets demonstrate that our Lab2Pix significantly outperforms existing state-of-the-art unsupervised methods and is even comparable to supervised methods. The source code is available at https://github.com/RoseRollZhu/Lab2Pix.

As a structured representation of the image content, the visual scene graph (visual relationship) acts as a bridge between computer vision and natural language processing. Existing models on the scene graph generation task notoriously require tens or hundreds of labeled samples. By contrast, human beings can learn visual relationships from a few or even one example. Inspired by this, we design a task named One-Shot Scene Graph Generation, where each relationship triplet (e.g., "dog-has-head'') comes from only one labeled example. The key insight is that rather than learning from scratch, one can utilize rich prior knowledge. In this paper, we propose Multiple Structured Knowledge (Relational Knowledge and Commonsense Knowledge) for the one-shot scene graph generation task. Specifically, the Relational Knowledge represents the prior knowledge of relationships between entities extracted from the visual content, e.g., the visual relationships "standing in'', "sitting in'', and "lying in'' may exist between "dog'' and "yard'', while the Commonsense Knowledge encodes "sense-making'' knowledge like "dog can guard yard''. By organizing these two kinds of knowledge in a graph structure, Graph Convolution Networks (GCNs) are used to extract knowledge-embedded semantic features of the entities. Besides, instead of extracting isolated visual features from each entity generated by Faster R-CNN, we utilize an Instance Relation Transformer encoder to fully explore their context information. Based on a constructed one-shot dataset, the experimental results show that our method significantly outperforms existing state-of-the-art methods by a large margin. Ablation studies also verify the effectiveness of the Instance Relation Transformer encoder and the Multiple Structured Knowledge.

The First International Workshop on Human-Centric MultimediaAnalysis is concentrated on the tasks of human-centric analysis with multimedia and multimodal information. It is one of the fundamental and challenging problems of multimedia understanding. The human-centric multimedia analysis involves multiple tasks such as face detection and recognition, human body pattern analysis, person re-identification, human action detection, person tracking,human-object interaction, and so on. Today, multiple multimedia sensing technologies and large-scale computing infrastructures are producing at a rapid velocity a wide variety of big multi-modality data for human-centric analysis, which provides rich knowledge to help tackle these challenges. Researchers have strived to push the limits of human-centric multimedia analysis in a wide variety of applications, such as intelligent surveillance, retailing, fashion design, and services. Therefore, this workshop aims to provide a platform to bridge the gap between the communities of human analysis and multimedia.

In this paper, we address the multi-person densepose estimation problem, which aims at learning dense correspondences between 2D pixels of human body and 3D surface. It still poses several challenges due to real-world scenes with scale variations, occlusion and insufficient annotations. In particular, we address two main problems: 1) how to design a simple yet effective pipeline for densepose estimation; and 2) how to equip this pipeline with the ability of handling the issues of limited annotations and class-imbalanced labels. To tackle these problems, we develop a novel densepose estimation framework based on a two-stage pipeline, called Knowledge Transfer Network (KTN). Unlike existing works which directly propagate the pyramidal base features of regions, we enhance their representation power by a multi-instance decoder (MID). MID can well distinguish the target instance from other interference instances and background. Then, we introduce a knowledge transfer machine (KTM), which improves densepose estimation by utilizing the external commonsense knowledge. Notably, with the help of our knowledge transfer machine (KTM), current densepose estimation systems (either based on RCNN or fully-convolutional frameworks) can be improved in terms of the accuracy of human densepose estimation. Solid experiments on densepose estimation benchmarks demonstrate the superiority and generalizability of our approach. Our code and models will be publicly available.

In biology, evolution is the gradual change in the characteristics of a species over several generations. It has two properties: 1) The change is gradual, and 2) long-term changes are relied on short-term changes. Face aging/rejuvenation, which renders younger or elder facial images, follows the principles of evolution. Inspired by this, we propose an Evolutionary GANs (EvoGAN) for face aging/rejuvenation by making each age transformation smooth and decomposing a long-term transformation into several short-terms. Specifically, since short-term facial changes are gradual and relatively easy to render, we first divide the ages into several groups (i.e., chronologically from child, adult to elder). Then, for each pair of adjacent groups, we design two age transforms for face aging and rejuvenation, which are supposed to preserve personal identify information and predict age-specific characteristics. Compared with the mainstream for face aging/rejuvenation, i.e., conditional

Unsupervised video quantization is to compress the original videos to compact binary codes so that video retrieval can be conducted in an efficient way. In this paper, we make a first attempt to combine quantization method with video retrieval called 3D-UVQ, which obtains high retrieval accuracy with low storage cost. In the proposed framework, we address two main problems: 1) how to design an effective pipeline to perceive video contextual information for video features extraction; and 2) how to quantize these features for efficient retrieval. To tackle these problems, we propose a 3D self-attention module to exploit the spatial and temporal contextual information, where each pixel is influenced by its surrounding pixels. By taking a further recurrent operation, each pixel can finally capture the global context from all pixels. Then, we propose gradient-based residual quantization which consists of several quantization blocks to approximate the features gradually. Extensive experimental results on three benchmark datasets demonstrate that our method significantly outperforms the state-of-the-arts. Ablation study shows that both the 3D self-attention module and the gradient-based residual quantization can improve the performance of retrieval. Our model is publicly available at https://github.com/brownwolf/3D-UVQ.

Recent progress has been made in using attention based encoder-decoder framework for image and video captioning. Most existing decoders apply the attention mechanism to every generated word including both visual words (e.g., "gun" and "shooting") and non-visual words (e.g., "the", "a"). However, these non-visual words can be easily predicted using natural language model without considering visual signals or attention. Imposing attention mechanism on non-visual words could mislead and decrease the overall performance of visual captioning. Furthermore, the hierarchy of LSTMs enables more complex representation of visual data, capturing information at different scales. Considering these issues, we propose a hierarchical LSTM with adaptive attention (hLSTMat) approach for image and video captioning. Specifically, the proposed framework utilizes the spatial or temporal attention for selecting specific regions or frames to predict the related words, while the adaptive attention is for deciding whether to depend on the visual information or the language context information. Also, a hierarchical LSTMs is designed to simultaneously consider both low-level visual information and high-level language context information to support the caption generation. We design the hLSTMat model as a general framework, and we first instantiate it for the task of video captioning. Then, we further instantiate our hLSTMarefine it and apply it to the imioning task. To demonstrate the effectiveness of our proposed framework, we test our method on both video and image captioning tasks. Experimental results show that our approach achieves the state-of-the-art performance for most of the evaluation metrics on both tasks. The effect of important components is also well exploited in the ablation study.

Given a query instance from one modality (e.g., image), cross-modal retrieval aims to find semantically similar instances from another modality (e.g., text). To perform cross-modal retrieval, existing approaches typically learn a common semantic space from a labeled source set and directly produce common representations in the learned space for the instances in a target set. These methods commonly require that the instances of both two sets share the same classes. Intuitively, they may not generalize well on a more practical scenario of zero-shot cross-modal retrieval, that is, the instances of the target set contain unseen classes that have inconsistent semantics with the seen classes in the source set. Inspired by zero-shot learning, we propose a novel model called ternary adversarial networks with self-supervision (TANSS) in this paper, to overcome the limitation of the existing methods on this challenging task. Our TANSS approach consists of three paralleled subnetworks: 1) two semantic feature learning subnetworks that capture the intrinsic data structures of different modalities and preserve the modality relationships via semantic features in the common semantic space; 2) a self-supervised semantic subnetwork that leverages the word vectors of both seen and unseen labels as guidance to supervise the semantic feature learning and enhances the knowledge transfer to unseen labels; and 3) we also utilize the adversarial learning scheme in our TANSS to maximize the consistency and correlation of the semantic features between different modalities. The three subnetworks are integrated in our TANSS to formulate an end-to-end network architecture which enables efficient iterative parameter optimization. Comprehensive experiments on three cross-modal datasets show the effectiveness of our TANSS approach compared with the state-of-the-art methods for zero-shot cross-modal retrieval.

Recently, 3D Convolutional Neural Network (3D CNN) models have been widely studied for video sequences and achieved satisfying performance in action recognition and detection tasks. However, most of the existing 3D CNNs treat all input video frames equally, thus ignoring the spatial and temporal differences across the video frames. To address the problem, we propose a spatio-temporal attention (STA) network that is able to learn the discriminative feature representation for actions, by respectively characterizing the beneficial information at both the frame level and the channel level. By simultaneously exploiting the differences in spatial and temporal dimensions, our STA module enhances the learning capability of the 3D convolutions when handling the complex videos. The proposed STA method can be wrapped as a generic module easily plugged into the state-of-the-art 3D CNN architectures for video action detection and recognition. We extensively evaluate our method on action recognition and detection tasks over three popular datasets (UCF-101, HMDB-51 and THUMOS 2014), and the experimental results demonstrate that adding our STA network module can obtain the state-of-the-art performance on UCF-101 and HMDB-51, which has the top-1 accuracies of 98.4% and 81.4% respectively, and achieve significant improvement on THUMOS 2014 dataset compared against original models.

Generating photo-realistic images conditioned on semantic text descriptions is a challenging task in computer vision field. Due to the nature of hierarchical representations learned in CNN, it is intuitive to utilize richer convolutional features to improve text-to-image synthesis. In this paper, we propose Perceptual Pyramid Adversarial Network (PPAN) to directly synthesize multi-scale images conditioned on texts in an adversarial way. Specifically, we design one pyramid generator and three independent discriminators to synthesize and regularize multi-scale photo-realistic images in one feed-forward process. At each pyramid level, our method takes coarse-resolution features as input, synthesizes highresolution images, and uses convolutions for up-sampling to finer level. Furthermore, the generator adopts the perceptual loss to enforce semantic similarity between the synthesized image and the ground truth, while a multi-purpose discriminator encourages semantic consistency, image fidelity and class invariance. Experimental results show that our PPAN sets new records for text-to-image synthesis on two benchmark datasets: CUB (i.e., 4.38 Inception Score and .290 Visual-semantic Similarity) and Oxford-102 (i.e., 3.52 Inception Score and .297 Visual-semantic Similarity).

In daily life, deliberation is a common behavior for human to improve or refine their work (e.g., writing, reading and drawing). To date, encoder-decoder framework with attention mechanisms has achieved great progress for image captioning. However, such framework is in essential an one-pass forward process while encoding to hidden states and attending to visual features, but lacks of the deliberation action. The learned hidden states and visual attention are directly used to predict the final captions without further polishing. In this paper, we present a novel Deliberate Residual Attention Network, namely DA, for image captioning. The first-pass residual-based attention layer prepares the hidden states and visual attention for generating a preliminary version of the captions, while the second-pass deliberate residual-based attention layer refines them. Since the second-pass is based on the rough global features captured by the hidden layer and visual attention in the first-pass, our DA has the potential to generate better sentences. We further equip our DA with discriminative loss and reinforcement learning to disambiguate image/caption pairs and reduce exposure bias. Our model improves the state-of-the-arts on the MSCOCO dataset and reaches 37.5% BELU-4, 28.5% METEOR and 125.6% CIDEr. It also outperforms the-state-ofthe-arts from 25.1% BLEU-4, 20.4% METEOR and 53.1% CIDEr to 29.4% BLEU-4, 23.0% METEOR and 66.6% on the Flickr30K dataset.

To date, visual question answering (VQA) (i.e., image QA and video QA) is still a holy grail in vision and language understanding, especially for video QA. Compared with image QA that focuses primarily on understanding the associations between image region-level details and corresponding questions, video QA requires a model to jointly reason across both spatial and long-range temporal structures of a video as well as text to provide an accurate answer. In this paper, we specifically tackle the problem of video QA by proposing a Structured Two-stream Attention network, namely STA, to answer a free-form or open-ended natural language question about the content of a given video. First, we infer rich longrange temporal structures in videos using our structured segment component and encode text features. Then, our structured two-stream attention component simultaneously localizes important visual instance, reduces the influence of background video and focuses on the relevant text. Finally, the structured two-stream fusion component incorporates different segments of query and video aware context representation and infers the answers. Experiments on the large-scale video QA dataset TGIF-QA show that our proposed method significantly surpasses the best counterpart (i.e., with one representation for the video input) by 13.0%, 13.5%, 11.0% and 0.3 for Action, Trans., TrameQA and Count tasks. It also outperforms the best competitor (i.e., with two representations) on the Action, Trans., TrameQA tasks by 4.1%, 4.7%, and 5.1%.

Most of the recent progresses on visual question answering are based on recurrent neural networks (RNNs) with attention. Despite the success, these models are often timeconsuming and having difficulties in modeling long range dependencies due to the sequential nature of RNNs. We propose a new architecture, Positional Self-Attention with Coattention (PSAC), which does not require RNNs for video question answering. Specifically, inspired by the success of self-attention in machine translation task, we propose a Positional Self-Attention to calculate the response at each position by attending to all positions within the same sequence, and then add representations of absolute positions. Therefore, PSAC can exploit the global dependencies of question and temporal information in the video, and make the process of question and video encoding executed in parallel. Furthermore, in addition to attending to the video features relevant to the given questions (i.e., video attention), we utilize the co-attention mechanism by simultaneously modeling “what words to listen to” (question attention). To the best of our knowledge, this is the first work of replacing RNNs with selfattention for the task of visual question answering. Experimental results of four tasks on the benchmark dataset show that our model significantly outperforms the state-of-the-art on three tasks and attains comparable result on the Count task. Our model requires less computation time and achieves better performance compared with the RNNs-based methods. Additional ablation study demonstrates the effect of each component of our proposed model.

Product Quantization (PQ) has long been a mainstream for generating an exponentially large codebook at very low memory/time cost. Despite its success, PQ is still tricky for the decomposition of high-dimensional vector space, and the retraining of model is usually unavoidable when the code length changes. In this work, we propose a deep progressive quantization (DPQ) model, as an alternative to PQ, for large scale image retrieval. DPQ learns the quantization codes sequentially and approximates the original feature space progressively. Therefore, we can train the quantization codes with different code lengths simultaneously. Specifically, we first utilize the label information for guiding the learning of visual features, and then apply several quantization blocks to progressively approach the visual features. Each quantization block is designed to be a layer of a convolutional neural network, and the whole framework can be trained in an end-to-end manner. Experimental results on the benchmark datasets show that our model significantly outperforms the state-of-the-art for image retrieval. Our model is trained once for different code lengths and therefore requires less computation time. Additional ablation study demonstrates the effect of each component of our proposed model. Our code is released at https://github.com/cfm-uestc/DPQ.

With the recent explosive increase of digital data, image recognition and retrieval become a critical practical application. Hashing is an effective solution to this problem, due to its low storage requirement and high query speed. However, most of past works focus on hashing in a single (source) domain. Thus, the learned hash function may not adapt well in a new (target) domain that has a large distributional difference with the source domain. In this paper, we explore an end-to-end domain adaptive learning framework that simultaneously and precisely generates discriminative hash codes and classifies target domain images. Our method encodes two domains images into a semantic common space, followed by two independent generative adversarial networks arming at crosswise reconstructing two domains’ images, reducing domain disparity and improving alignment in the shared space. We evaluate our framework on four public benchmark datasets, all of which show that our method is superior to the other state-of-the-art methods on the tasks of object recognition and image retrieval.

Quantization has been an effective technology in ANN (approximate nearest neighbour) search due to its high accuracy and fast search speed. To meet the requirement of different applications, there is always a trade-off between retrieval accuracy and speed, reflected by variable code lengths. However, to encode the dataset into different code lengths, existing methods need to train several models, where each model can only produce a specific code length. This incurs a considerable training time cost, and largely reduces the flexibility of quantization methods to be deployed in real applications. To address this issue, we propose a Deep Recurrent Quantization (DRQ) architecture which can generate sequential binary codes. To the end, when the model is trained, a sequence of binary codes can be generated and the code length can be easily controlled by adjusting the number of recurrent iterations. A shared codebook and a scalar factor is designed to be the learnable weights in the deep recurrent quantization block, and the whole framework can be trained in an end-to-end manner. As far as we know, this is the first quantization method that can be trained once and generate sequential binary codes. Experimental results on the benchmark datasets show that our model achieves comparable or even better performance compared with the state-of-the-art for image retrieval. But it requires significantly less number of parameters and training times. Our code is published online: https://github.com/cfm-uestc/DRQ.

Action localization in untrimmed videos is an important topic in the field of video understanding. However, existing action localization methods are restricted to a pre-defined set of actions and cannot localize unseen activities. Thus, we consider a new task to localize unseen activities in videos via image queries, named Image-Based Activity Localization. This task faces three inherent challenges: (1) how to eliminate the influence of semantically inessential contents in image queries; (2) how to deal with the fuzzy localization of inaccurate image queries; (3) how to determine the precise boundaries of target segments. We then propose a novel self-attention interaction localizer to retrieve unseen activities in an end-to-end fashion. Specifically, we first devise a region self-attention method with relative position encoding to learn fine-grained image region representations. Then, we employ a local transformer encoder to build multi-step fusion and reasoning of image and video contents. We next adopt an order-sensitive localizer to directly retrieve the target segment. Furthermore, we construct a new dataset ActivityIBAL by reorganizing the ActivityNet dataset. The extensive experiments show the effectiveness of our method.

Open-ended video question answering aims to automatically generate the natural-language answer from referenced video contents according to the given question. Currently, most existing approaches focus on short-form video question answering with multi-modal recurrent encoder-decoder networks. Although these works have achieved promising performance, they may still be ineffectively applied to long-form video question answering due to the lack of long-range dependency modeling and the suffering from the heavy computational cost. To tackle these problems, we propose a fast hierarchical convolutional self-attention encoder-decoder network. Concretely, we first develop a hierarchical convolutional self-attention encoder to efficiently model long-form video contents, which builds the hierarchical structure for video sequences and captures question-aware long-range dependencies from video context. We then devise a multi-scale attentive decoder to incorporate multi-layer video representations for answer generation, which avoids the information missing of the top encoder layer. The extensive experiments show the effectiveness and efficiency of our method.

Dense human pose "in the wild'' task aims to map all 2D pixels of the detected human body to a 3D surface by establishing surface correspondences, i.e., surface patch index and part-specific UV coordinates. It remains challenging especially under the condition of "in the wild'', where RGB images capture complex, real-world scenes with background, occlusions, scale variations, and postural diversity. In this paper, we propose an end-to-end deep Adaptive Multi-path Aggregation network (AMA-net) for Dense Human Pose Estimation. In the proposed framework, we address two main problems: 1) how to design a simple yet effective pipeline for supporting distinct sub-tasks (e.g., instance segmentation, body part segmentation, and UV estimation); and 2) how to equip this pipeline with the ability of handling "in the wild''. To solve these problems, we first extend FPN by adding a branch for mapping 2D pixels to a 3D surface in parallel with the existing branch for bounding box detection. Then, in AMA-net, we extract variable-sized object-level feature maps (e.g., 7×7, 14×14, and 28×28), named multi-path, from multi-layer feature maps, which capture rich information of objects and are then adaptively utilized in different tasks. AMA-net is simple to train and adds only a small overhead to FPN. We discover that aside from the deep feature map, Adaptive Multi-path Aggregation is of particular importance for improving the accuracy of dense human pose estimation "in the wild''. The experimental results on the challenging Dense-COCO dataset demonstrate that our approach sets a new record for Dense Human Pose Estimation task, and it significantly outperforms the state-of-the-art methods. Our code: \urlhttps://github.com/nobody-g/AMA-net.

Video visual question answering (V-VQA) remains challenging at the intersection of vision and language, where it requires joint comprehension of video and natural language question. Image-Question co-attention mechanism, which aims at generating a spatial map highlighting image regions relevant to answering the question and vice versa, has obtained impressive results. Despite the success, simply applying co-attention to video visual question answering results in unsatisfactory performance due to the complexity and temporal nature of videos. In this paper, we proposed a novel architecture, namely Learnable Aggregating Net with Diversity learning (LAD-Net), for V-VQA. In the proposed method, we address two central problems: 1) how to deploy co-attention to V-VQA task considering the complex and diverse content of videos; and 2) how to aggregate the frame-level features without destroying the feature distributions and temporal information. To solve these problems, our LAD-Net first extends single-path based co-attention mechanism to a multi-path pyramid co-attention structure with a novel diversity learning to explicitly encourage attention diversity. For video-level (or question-level) descriptor, instead of taking a simple temporal pooling (i.e., average pooling), we propose a new learnable aggregation method with a set of evidence gates. It automatically aggregates adaptively-weighted frame-level features (or word-level features) to extract rich video (or question) context semantic information by imitating Bags-of-Words (BoW) quantization. With evidence gates, it then further chooses the most related signals representing the evidence information to predict the answer.Extensive validations on the two challenging video visual question answering datasets TGIF-QA and TVQA show that LAD-Net achieves the state-of-the-art performance under various settings and metrics. Our proposed strategies are of particular importance for improving the performance of the baseline co-attention V-VQA.

This paper focuses on fine-grained human parsing in images. This is a very challenging task due to the diverse person appearance, semantic ambiguity of different body parts and clothing, and extremely small parsing targets. Although existing approaches can achieve significant improvement by pyramid feature learning, multi-level supervision, and joint learning with pose estimation, human parsing is still far from being solved. Different from existing approaches, we propose a Braiding Network, named as BraidNet, to learn complementary semantics and details for fine-grained human parsing. The BraidNet contains a two-stream braid-like architecture. The first stream is a semantic abstracting net with a deep yet narrow structure which can learn semantic knowledge by a hierarchy of fully convolution layers to overcome the challenges of diverse person appearance. To capture low-level details of small targets, the detail-preserving net is designed to exploit a shallow yet wide network without down-sampling, which can retain sufficient local structures for small objects. Moreover, we design a group of braiding modules across the two sub-nets, by which complementary information can be exchanged during end-to-end training. Besides, in the end of BraidNet, a Pairwise Hard Region Embedding strategy is propose to eliminate the semantic ambiguity of different body parts and clothing. Extensive experiments show that the proposed BraidNet achieves better performance than the state-of-the-art methods for fine-grained human parsing.

A major challenge in matching images and text is that they have intrinsically different data distributions and feature representations. Most existing approaches are based either on embedding or classification, the first one mapping image and text instances into a common embedding space for distance measuring, and the second one regarding image-text matching as a binary classification problem. Neither of these approaches can, however, balance the matching accuracy and model complexity well. We propose a novel framework that achieves remarkable matching performance with acceptable model complexity. Specifically, in the training stage, we propose a novel Multi-modal Tensor Fusion Network (MTFN) to explicitly learn an accurate image-text similarity function with rank-based tensor fusion rather than seeking a common embedding space for each image-text instance. Then, during testing, we deploy a generic Cross-modal Re-ranking (RR) scheme for refinement without requiring additional training procedure. Extensive experiments on two datasets demonstrate that our MTFN-RR consistently achieves the state-of-the-art matching performance with much less time complexity.

Positioning data and other sensor measurements, such as camera orientation, have become important contextual features generated by mobile devices during video recording, which proved to be increasingly beneficial to video search. To enable access to videos based on their metadata (e.g., geo-properties produced by GPS and digital compass), a model representing camera field of view (FOV) is needed. Vector model of previous work, which simplifies FOV by ignoring the viewable angle for search efficiency, has become popular in georeferenced video search. However, when the viewable angle is large, many false positives and false negatives occur, which are undesirable for filtering of georeferenced video search. This paper proposes a new model, which can appropriately represent the actual FOV as a filtering step, without any false positive or false negative. Based on this model, we investigate how to process five types of overlap queries for searching videos as spatio-temporal objects. To verify the effectiveness of our model and the corresponding query processing algorithms, experiments on a real data set we collected and a large synthetic data set are conducted. The results show that the proposed model can perform much better compared with the existing vector model, and the accuracy of its search results remains almost steady, even when the angle changes.

Hashing algorithm has been widely used to speed up image retrieval due to its compact binary code and fast distance calculation. The combination with deep learning boosts the performance of hashing by learning accurate representations and complicated hashing functions. So far, the most striking success in deep hashing have mostly involved discriminative models, which require labels. To apply deep hashing on datasets without labels, we propose a deep self-taught hashing algorithm (DSTH), which generates a set of pseudo labels by analyzing the data itself, and then learns the hash functions for novel data using discriminative deep models. Furthermore, we generalize DSTH to support both supervised and unsupervised cases by adaptively incorporating label information. We use two different deep learning framework to train the hash functions to deal with out-of-sample problem and reduce the time complexity without loss of accuracy. We have conducted extensive experiments to investigate different settings of DSTH, and compared it with state-of-the-art counterparts in six publicly available datasets. The experimental results show that DSTH outperforms the others in all datasets.

Action recognition has been extensively researched in computer vision due to its potential applications in a broad range of areas. The key to action recognition lies in modeling actions and measuring their similarity, which however poses great challenges. In this paper, we propose learning match kernels between actions on Grassmann manifold for action recognition. Specifically, we propose modeling actions as a linear subspace on the Grassmann manifold; the subspace is a set of convolutional neural network (CNN) feature vectors pooled temporally over frames in semantic video clips, which simultaneously captures local discriminant patterns and temporal dynamics of motion. To measure the similarity between actions, we propose Grassmann match kernels (GMK) based on canonical correlations of linear subspaces to directly match videos for action recognition; GMK is learned in a supervised way via kernel target alignment, which is endowed with a great discriminative ability to distinguish actions from different classes. The proposed approach leverages the strengths of CNNs for feature extraction and kernels for measuring similarity, which accomplishes a general learning framework of match kernels for action recognition. We have conducted extensive experiments on five challenging realistic data sets including Youtube, UCF50, UCF101, Penn action, and HMDB51. The proposed approach achieves high performance and substantially surpasses the state-of-the-art algorithms by large margins, which demonstrates the great effectiveness of proposed approach for action recognition.

Video captioning, in essential, is a complex natural process, which is affected by various uncertainties stemming from video content, subjective judgment, and so on. In this paper, we build on the recent progress in using encoder-decoder framework for video captioning and address what we find to be a critical deficiency of the existing methods that most of the decoders propagate deterministic hidden states. Such complex uncertainty cannot be modeled efficiently by the deterministic models. In this paper, we propose a generative approach, referred to as multimodal stochastic recurrent neural networks (MS-RNNs), which models the uncertainty observed in the data using latent stochastic variables. Therefore, MS-RNN can improve the performance of video captioning and generate multiple sentences to describe a video considering different random factors. Specifically, a multimodal long short-term memory (LSTM) is first proposed to interact with both visual and textual features to capture a high-level representation. Then, a backward stochastic LSTM is proposed to support uncertainty propagation by introducing latent variables. Experimental results on the challenging data sets, microsoft video description and microsoft research video-to-text, show that our proposed MS-RNN approach outperforms the state-of-the-art video captioning benchmarks.

The most striking successes in image retrieval using deep hashing have mostly involved discriminative models, which require labels. In this paper, we use binary generative adversarial networks (BGAN) to embed images to binary codes in an unsupervised way. By restricting the input noise variable of generative adversarial networks (GAN) to be binary and conditioned on the features of each input image, BGAN can simultaneously learn a binary representation per image, and generate an image plausibly similar to the original one. In the proposed framework, we address two main problems: 1) how to directly generate binary codes without relaxation? 2) how to equip the binary representation with the ability of accurate image retrieval? We resolve these problems by proposing new sign-activation strategy and a loss function steering the learning process, which consists of new models for adversarial loss, a content loss, and a neighborhood structure loss. Experimental results on standard datasets (CIFAR-10, NUSWIDE, and Flickr) demonstrate that our BGAN significantly outperforms existing hashing methods by up to 107% in terms of mAP (See Table 2).

Instance Search (INS) is a fundamental problem for many applications, while it is more challenging comparing to traditional image search since the relevancy is defined at the instance level. Existing works have demonstrated the success of many complex ensemble systems that are typically conducted by firstly generating object proposals, and then extracting handcrafted and/or CNN features of each proposal for matching. However, object bounding box proposals and feature extraction are often conducted in two separated steps, thus the effectiveness of these methods collapses. Also, due to the large amount of generated proposals, matching speed becomes the bottleneck that limits its application to large-scale datasets. To tackle these issues, in this paper we propose an effective and efficient Deep Region Hashing (DRH) approach for large-scale INS using an image patch as the query. Specifically, DRH is an end-to-end deep neural network which consists of object proposal, feature extraction, and hash code generation. DRH shares full-image convolutional feature map with the region proposal network, thus enabling nearly cost-free region proposals. Also, each high-dimensional, real-valued region features are mapped onto a low-dimensional, compact binary codes for the efficient object region level matching on large-scale dataset. Experimental results on four datasets show that our DRH can achieve even better performance than the state-of-the-arts in terms of mAP, while the efficiency is improved by nearly 100 times.

Designing an automatic solver for math word problems has been considered as a crucial step towards general AI, with the ability of natural language understanding and logical inference. The state-of-the-art performance was achieved by enumerating all the possible expressions from the quantities in the text and customizing a scoring function to identify the one with the maximum probability. However, it incurs exponential search space with the number of quantities and beam search has to be applied to trade accuracy for efficiency. In this paper, we make the first attempt of applying deep reinforcement learning to solve arithmetic word problems. The motivation is that deep Q-network has witnessed success in solving various problems with big search space and achieves promising performance in terms of both accuracy and running time. To fit the math problem scenario, we propose our MathDQN that is customized from the general deep reinforcement learning framework. Technically, we design the states, actions, reward function, together with a feed-forward neural network as the deep Q-network. Extensive experimental results validate our superiority over state-of-the-art methods. Our MathDQN yields remarkable improvement on most of datasets and boosts the average precision among all the benchmark datasets by 15\%.

Recently, automatic answering of visually related questions (VQA) has gained a lot of attention in computer vision community. However, there is little work on automatically generating questions for images (VQG). Actually, VQG itself closes the loop to question-answering and diverse questions, which is useful to the research on VQA. Motivated by the assumption that learning to answer questions may boost the question generation, in this paper, we introduce the VQA task as the complementary of our primary VQG task, and propose a novel model that uses dual learning framework to jointly learn the dual tasks. In the framework, we devise an agent for VQG and VQA with pre-trained models respectively, and the learning tasks of the two agents form a closed loop, whose objectives are optimized together to guide each other via a reinforcement learning process. Specific rewards for each task are designed to update the models of the agents with policy gradient method. The relation of these two tasks can be exploited to further improve the performance of the primary VQG task. Extensive experiments conducted on two large-scale datasets show that the proposed method is capable to generate grounded visual questions of sufficient coverage and outperforms previous VQG methods on standard measures.

Building multiple hash tables has been proven a successful technique for indexing massive databases, which can guarantee a desired level of overall performance. However, existing hash based multi-indexing methods suffer from the heavy redundancy, without strong table complementarity and effective hash code learning. To address the problems, this paper proposes a complementary binary quantization (CBQ) method to jointly learning multiple hash tables. It exploits the power of incomplete binary coding based on prototypes to align the original space and the Hamming space, and further utilizes the nature of multi-indexing search to jointly reduce the quantization loss based on the prototype based hash function. Our alternating optimization adaptively discovers the complementary prototype sets and the corresponding code sets of a varying size in an efficient way, which together robustly approximate the data relations. Our method can be naturally generalized to the product space for long hash codes. Extensive experiments carried out on two popular large-scale tasks including Euclidean and semantic nearest neighbor search demonstrate that the proposed CBQ method enjoys the strong table complementarity and significantly outperforms the state-of-the-art, with up to 57.76\% performance gains relatively.

Image co-segmentation is the problem of automatically discovering the common objects co-occurring in a set of relevant images and segmenting them as foreground simultaneously. Although a bunch of approaches have been proposed to address this problem, many of them still suffer from certain limitations, e.g., supervised feature learning and complex models, which hinder their capability in the real-world scenarios. To alleviate these limitations, we propose a novel coarse-to-fine co-segmentation (CFC) framework, which utilizes the coarse foreground and background proposals to learn a robust similarity measure of the features in an unsupervised way, and then devises a simple objective function based on the definition of image co-segmentation. Specifically, we first generate superpixels for all the images and extract their features. Instead of using existing distance metrics, we utilize object proposal methods to generate coarse foreground and background to learn a similarity measure of superpixels to construct a robust feature similarity graph. Then we design an intuitive objective function to learn a segmentation similarity graph which should be consistent with feature similarity graph and also be able to co-segment the superpixels in the images into either foreground and background. This objective function can be further reformulated as a graph learning problem with intra and inter rank constraints. Experiments on two commonly used image datasets (iCoseg and MSRC) demonstrate that CFC outperforms other state-of-the-art methods. Notably, this performance is achieved by using only HSV feature.

Face aging and rejuvenation is to predict the face of a person at different ages. While tremendous progress have been made in this topic, there are two central problems remaining largely unsolved: 1) the majority of prior works requires sequential training data, which is very rare in real scenarios, and 2) how to simultaneously render aging face and preserve personality. To tackle these issues, in this paper, we develop a novel dual conditional GAN (DCGAN) mechanism, which enables face aging and rejuvenation to be trained from multiple sets of unlabeled face images with different ages. In our architecture, the primal conditional GAN transforms a face image to other ages based on the age condition, while the dual conditional GAN learns to invert the task. Hence a loss function that accounts for the reconstruction error of images can preserve the personal identity, while the discriminators on the generated images learn the transition patterns (e.g., the shape and texture changes between age groups) and guide the generation of age-specific photo-realistic faces. Experimental results on two publicly dataset demonstrate the appealing performance of the proposed framework by comparing with the state-of-the-art methods.

Recently, attention-based Visual Question Answering (VQA) has achieved great success by utilizing question to selectively target different visual areas that are related to the answer. Existing visual attention models are generally planar, i.e., different channels of the last conv-layer feature map of an image share the same weight. This conflicts with the attention mechanism because CNN features are naturally spatial and channel-wise. Also, visual attention models are usually conducted on pixel-level, which may cause region discontinuous problem. In this paper we propose a Cubic Visual Attention (CVA) model by successfully applying a novel channel and spatial attention on object regions to improve VQA task. Specifically, instead of attending to pixels, we first take advantage of the object proposal networks to generate a set of object candidates and extract their associated conv features. Then, we utilize the question to guide channel attention and spatial attention calculation based on the con-layer feature map. Finally, the attended visual features and the question are combined to infer the answer. We assess the performance of our proposed CVA on three public image QA datasets, including COCO-QA, VQA and Visual7W. Experimental results show that our proposed method significantly outperforms the state-of-the-arts.

We realize a system that utilizes WiFi to facilitate the image-based localization system, which avoids the confusion caused by the similar decoration inside the buildings. While WiFi-based localization thread obtains the rough location information, the image-based localization thread retrieves the best matching images and clusters the camera poses associated with the images into different location candidates. The image cluster closest to the WiFi localization outcome is selected for the exact camera pose estimation. The usage of WiFi significantly reduces the search scope, avoiding the extensive search of millions of descriptors in a 3D model. In the image-based localization stage, we also propose a novel 2D-to-2D-to-3D localization framework which follows a coarse-to-fine strategy to quickly locate the query image in several location candidates and performs the local feature matching and camera pose estimation after choosing the correct image location by WiFi positioning. The entire system demonstrates significant benefits in combining both images and WiFi signals in localization tasks and great potential to be deployed in real applications.

Cross-modal retrieval, e.g., using an image query to search related text and vice-versa, has become a highlighted research topic, to provide flexible retrieval experience across multi-modal data. Existing approaches usually consider the so-called non-extendable cross-modal retrieval task. In this task, they learn a common latent subspace from a source set containing labeled instances of image-text pairs and then generate common representation for the instances in a target set to perform cross-modal matching. However, these method may not generalize well when the instances of the target set contains unseen classes since the instances of both the source and target set are assumed to share the same range of classes in the non-extensive cross-modal retrieval task. In this paper, we consider a more practical issue of extendable cross-modal retrieval task where instances in source and target set have disjoint classes. We propose a novel framework, termed Modal-adversarial Semantic Learning Network (MASLN), to tackle the limitation of existing methods on this practical task. Specifically, the proposed MASLN consists two subnetworks of cross-modal reconstruction and modal-adversarial semantic learning. The former minimizes the cross-modal distribution discrepancy by reconstructing each modality data mutually, with the guidelines of class embeddings as side information in the reconstruction procedure. The latter generates semantic representation to be indiscriminative for modalities, while to distinguish the modalities from the common representation via an adversarial learning mechanism. The two subnetworks are jointly trained to enhance the cross-modal semantic consistency in the learned common subspace and the knowledge transfer to instances in the target set. Comprehensive experiment on three widely-used multi-modal datasets show its effectiveness and robustness on both non-extendable and extendable cross-modal retrieval task.

Multiple-choice (MC) Visual Question Answering (VQA) is a similar but essentially different task to open-ended VQA because the answer options are provided. Most of existing works tackle them in a unified pipeline by solving a multi-class problem to infer the best answer from a predefined answer set. The option that matches the best answer is selected for MC VQA. Nevertheless, this violates human thinking logics. Normally, people examine the questions, answer options and the reference image before inferring a MC VQA. For MC VQA, human either rely on the question and answer options to directly deduce a correct answer if the question is not image-related, or read the question and answer options and then purposefully search for answers in a reference image. Therefore, we propose a novel approach, namely Multi-task Learning with Adaptive-attention (MTA), to simulate human logics for MC VQA. Specifically, we first fuse the answer options and question features, and then adaptively attend to the visual features for inferring a MC VQA. Furthermore, we design our model as a multi-task learning architecture by integrating the open-ended VQA task to further boost the performance of MC VQA. We evaluate our approach on two standard benchmark datasets: VQA and Visual7W and our approach sets new records on both datasets for MC VQA task, reaching 73.5% and 65.9% average accuracy respectively.

Zero-shot learning (ZSL) aims to recognize unseen classes that are excluded from training classes. ZSL suffers from 1) Zero-shot bias (Z-Bias) --- model is biased towards seen classes because unseen data is inaccessible for training; 2) Zero-shot variance (Z-Variance) --- associating different images to same semantic embedding yields large associating error. To reduce Z-Bias, we propose a pseudo transfer mechanism, where we first synthesize the distribution of unseen data using semantic embeddings, then we minimize the mismatch between the seen distribution and the synthesized unseen distribution. To reduce Z-Variance, we implicitly corrupted one semantic embedding multiple times to generate image-wise semantic vectors, with which our model learn robust classifiers. Lastly, we integrate our Z-Bias and Z-variance reduction techniques with a linear ZSL model to show its usefulness. Our proposed model successfully overcomes the Z-bias and Z-variance problems. Extensive experiments on five benchmark datasets including ImageNet-1K demonstrate that our model outperforms the state-of-the-art methods with fast training.

Lots of recent progress have been made by using Convolutional Neural Networks (CNN) for edge detection. Due to the nature of hierarchical representations learned in CNN, it is intuitive to design side networks utilizing the richer convolutional features to improve the edge detection. However, different side networks are isolated, and the final results are usually weighted sum of the side outputs with uneven qualities. To tackle these issues, we propose a Cumulative Network (C-Net), which learns the side network cumulatively based on current visual features and low-level side outputs, to gradually remove detailed or sharp boundaries to enable high-resolution and accurate edge detection. Therefore, the lower-level edge information is cumulatively inherited while the superfluous details are progressively abandoned. In fact, recursively Learningwhere to remove superfluous details from the current edge map with the supervision of a higher-level visual feature is challenging. Furthermore, we employ atrous convolution (AC) and atrous convolution pyramid pooling (ASPP) to robustly detect object boundaries at multiple scales and aspect ratios. Also, cumulatively refining edges using high-level visual information and lower-lever edge maps is achieved by our designed cumulative residual attention (CRA) block. Experimental results show that our C-Net sets new records for edge detection on both two benchmark datasets: BSDS500 (i.e., .819 ODS, .835 OIS and .862 AP) and NYUDV2 (i.e., .762 ODS, .781 OIS, .797 AP). C-Net has great potential to be applied to other deep learning based applications, e.g., image classification and segmentation.

Nearest neighbor search is a problem of finding the data points from the database such that the distances from them to the query point are the smallest. Learning to hash is one of the major solutions to this problem and has been widely studied recently. In this paper, we present a comprehensive survey of the learning to hash algorithms, categorize them according to the manners of preserving the similarities into: pairwise similarity preserving, multiwise similarity preserving, implicit similarity preserving, as well as quantization, and discuss their relations. We separate quantization from pairwise similarity preserving as the objective function is very different though quantization, as we show, can be derived from preserving the pairwise similarities. In addition, we present the evaluation protocols, and the general performance analysis, and point out that the quantization algorithms perform superiorly in terms of search accuracy, search time cost, and space cost. Finally, we introduce a few emerging topics.

Existing video hash functions are built on three isolated stages: frame pooling, relaxed learning, and binarization, which have not adequately explored the temporal order of video frames in a joint binary optimization model, resulting in severe information loss. In this paper, we propose a novel unsupervised video hashing framework dubbed self-supervised video hashing (SSVH), which is able to capture the temporal nature of videos in an end-to-end learning to hash fashion. We specifically address two central problems: 1) how to design an encoder-decoder architecture to generate binary codes for videos and 2) how to equip the binary codes with the ability of accurate video retrieval. We design a hierarchical binary auto-encoder to model the temporal dependencies in videos with multiple granularities, and embed the videos into binary codes with less computations than the stacked architecture. Then, we encourage the binary codes to simultaneously reconstruct the visual content and neighborhood structure of the videos. Experiments on two real-world data sets show that our SSVH method can significantly outperform the state-of-the-art methods and achieve the current best performance on the task of unsupervised video retrieval.

In this paper, we address the problem of learning robust cross-domain representations for sketch-based image retrieval (SBIR). While, most SBIR approaches focus on extracting low- and mid-level descriptors for direct feature matching, recent works have shown the benefit of learning coupled feature representations to describe data from two related sources. However, cross-domain representation learning methods are typically cast into non-convex minimization problems that are difficult to optimize, leading to unsatisfactory performance. Inspired by self-paced learning (SPL), a learning methodology designed to overcome convergence issues related to local optima by exploiting the samples in a meaningful order (i.e., easy to hard), we introduce the cross-paced partial curriculum learning (CPPCL) framework. Compared with existing SPL methods which only consider a single modality and cannot deal with prior knowledge, CPPCL is specifically designed to assess the learning pace by jointly handling data from dual sources and modality-specific prior information provided in the form of partial curricula. In addition, thanks to the learned dictionaries, we demonstrate that the proposed CPPCL embeds robust coupled representations for SBIR. Our approach is extensively evaluated on four publicly available datasets (i.e., CUFS, Flickr15K, QueenMary SBIR, and TU-Berlin Extension datasets), showing superior performance over competing SBIR methods.

Item-to-item collaborative filtering (aka.item-based CF) has been long used for building recommender systems in industrial settings, owing to its interpretability and efficiency in real-time personalization. It builds a user's profile as her historically interacted items, recommending new items that are similar to the user's profile. As such, the key to an item-based CF method is in the estimation of item similarities. Early approaches use statistical measures such as cosine similarity and Pearson coefficient to estimate item similarities, which are less accurate since they lack tailored optimization for the recommendation task. In recent years, several works attempt to learn item similarities from data, by expressing the similarity as an underlying model and estimating model parameters by optimizing a recommendation-aware objective function. While extensive efforts have been made to use shallow linear models for learning item similarities, there has been relatively less work exploring nonlinear neural network models for item-based CF. In this work, we propose a neural network model named Neural Attentive Item Similarity model (NAIS) for item-based CF. The key to our design of NAIS is an attention network, which is capable of distinguishing which historical items in a user profile are more important for a prediction. Compared to the state-of-the-art item-based CF method Factored Item Similarity Model (FISM) [1] , our NAIS has stronger representation power with only a few additional parameters brought by the attention network. Extensive experiments on two public benchmarks demonstrate the effectiveness of NAIS. This work is the first attempt that designs neural network models for item-based CF, opening up new research possibilities for future developments of neural recommender systems.

This paper proposes a new unsupervised spectral feature selection method to preserve both the local and global structure of the features as well as the samples. Specifically, our method uses the self-expressiveness of the features to represent each feature by other features for preserving the local structure of features, and a low-rank constraint on the weight matrix to preserve the global structure among samples as well as features. Our method also proposes to learn the graph matrix measuring the similarity of samples for preserving the local structure among samples. Furthermore, we propose a new optimization algorithm to the resulting objective function, which iteratively updates the graph matrix and the intrinsic space so that collaboratively improving each of them. Experimental analysis on 12 benchmark datasets showed that the proposed method outperformed the state-of-the-art feature selection methods in terms of classification performance.

The explosive growth of video content on the Web has been revolutionizing the way people share, exchange and perceive information, such as events. While an individual video usually concerns a specific aspect of an event, the videos that are uploaded by different users at different locations and times can embody different emphasis and compensate each other in describing the event. Combining these videos from different sources together can unveil a more complete picture of the event. Simply concatenating videos together is an intuitive solution, but it may degrade user experience since it is time-consuming and tedious to view those highly redundant, noisy and disorganized content. Therefore, we develop a novel approach, termed event video mashup (EVM), to automatically generate a unified short video from a collection of Web videos to describe the storyline of an event. We propose a submodular based content selection model that embodies both importance and diversity to depict the event from comprehensive aspects in an efficient way. Importantly, the video content is organized temporally and semantically conforming to the event evolution. We evaluate our approach on a real-world YouTube event dataset collected by ourselves. The extensive experimental results demonstrate the effectiveness of the proposed framework.

Zero-shot learning (ZSL) aims to recognize objects of unseen classes with available training data from another set of seen classes. Existing solutions are focused on exploring knowledge transfer via an intermediate semantic embedding (e.g., attributes) shared between seen and unseen classes. In this paper, we propose a novel projection framework based on matrix tri-factorization with manifold regularizations. Specifically, we learn the semantic embedding projection by decomposing the visual feature matrix under the guidance of semantic embedding and class label matrices. By additionally introducing manifold regularizations on visual data and semantic embeddings, the learned projection can effectively captures the geometrical manifold structure residing in both visual and semantic spaces. To avoid the projection domain shift problem, we devise an effective prediction scheme by exploiting the test-time manifold structure. Extensive experiments on four benchmark datasets show that our approach significantly outperforms the state-of-the-arts, yielding an average improvement ratio by 7.4% and 31.9% for the recognition and retrieval task, respectively.

In this paper, we propose a new synchronization-inspired co-clustering algorithm by dynamic simulation, called CoSync, which aims to discover biologically relevant subgroups embedding in a given gene expression data matrix. The basic idea is to view a gene expression data matrix as a dynamical system, and the weighted two-sided interactions are imposed on each element of the matrix from both aspects of genes and conditions, resulting in the values of all element in a co-cluster synchronizing together. Experiments show that our algorithm allows uncovering high-quality co-clusterings embedded in gene expression data sets and has its superiority over many state-of-the-art algorithms.

Recent progress has been made in using attention based encoder-decoder framework for video captioning. However, most existing decoders apply the attention mechanism to every generated words including both visual words (e.g., “gun” and "shooting“) and non-visual words (e.g. "the“, "a”).However, these non-visual words can be easily predicted using natural language model without considering visual signals or attention.Imposing attention mechanism on non-visual words could mislead and decrease the overall performance of video captioning.To address this issue, we propose a hierarchical LSTM with adjusted temporal attention (hLSTMat) approach for video captioning. Specifically, the proposed framework utilizes the temporal attention for selecting specific frames to predict related words, while the adjusted temporal attention is for deciding whether to depend on the visual information or the language context information. Also, a hierarchical LSTMs is designed to simultaneously consider both low-level visual information and deep semantic information to support the video caption generation. To demonstrate the effectiveness of our proposed framework, we test our method on two prevalent datasets: MSVD and MSR-VTT, and experimental results show that our approach outperforms the state-of-the-art methods on both two datasets.

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.

This paper proposes a generic formulation that significantly expedites the training and deployment of image classification models, particularly under the scenarios of many image categories and high feature dimensions. As the core idea, our method represents both the images and learned classifiers using binary hash codes, which are simultaneously learned from the training data. Classifying an image thereby reduces to retrieving its nearest class codes in the Hamming space. Specifically, we formulate multiclass image classification as an optimization problem over binary variables. The optimization alternatingly proceeds over the binary classifiers and image hash codes. Profiting from the special property of binary codes, we show that the sub-problems can be efficiently solved through either a binary quadratic program (BQP) or a linear program. In particular, for attacking the BQP problem, we propose a novel bit-flipping procedure which enjoys high efficacy and a local optimality guarantee. Our formulation supports a large family of empirical loss functions and is, in specific, instantiated by exponential and linear losses. Comprehensive evaluations are conducted on several representative image benchmarks. The experiments consistently exhibit reduced computational and memory complexities of model training and deployment, without sacrificing classification accuracy.

Human activity recognition in videos with convolutional neural network (CNN) features has received increasing attention in multimedia understanding. Taking videos as a sequence of frames, a new record was recently set on several benchmark datasets by feeding frame-level CNN sequence features to long short-term memory (LSTM) model for video activity recognition. This recurrent model-based visual recognition pipeline is a natural choice for perceptual problems with time-varying visual input or sequential outputs. However, the above-mentioned pipeline takes frame-level CNN sequence features as input for LSTM, which may fail to capture the rich motion information from adjacent frames or maybe multiple clips. Furthermore, an activity is conducted by a subject or multiple subjects. It is important to consider attention that allows for salient features, instead of mapping an entire frame into a static representation. To tackle these issues, we propose a novel pipeline, saliency-aware three-dimensional (3-D) CNN with LSTM, for video action recognition by integrating LSTM with salient-aware deep 3-D CNN features on videos shots. Specifically, we first apply saliency-aware methods to generate saliency-aware videos. Then, we design an end-to-end pipeline by integrating 3-D CNN with LSTM, followed by a time series pooling layer and a softmax layer to predict the activities. Noticeably, we set a new record on two benchmark datasets, i.e., UCF101 with 13 320 videos and HMDB-51 with 6766 videos. Our method outperforms the state-of-the-art end-to-end methods of action recognition by 3.8% and 3.2%, respectively on above two datasets.

Product quantization (PQ) has been recognized as a useful technique to encode visual feature vectors into compact codes to reduce both the storage and computation cost. Recent advances in retrieval and vision tasks indicate that high-dimensional descriptors are critical to ensuring high accuracy on large-scale data sets. However, optimizing PQ codes with high-dimensional data is extremely time-consuming and memory-consuming. To solve this problem, in this paper, we present a novel PQ method based on bilinear projection, which can well exploit the natural data structure and reduce the computational complexity. Specifically, we learn a global bilinear projection for PQ, where we provide both non-parametric and parametric solutions. The non-parametric solution does not need any data distribution assumption. The parametric solution can avoid the problem of local optima caused by random initialization, and enjoys a theoretical error bound. Besides, we further extend this approach by learning locally bilinear projections to fit underlying data distributions. We show by extensive experiments that our proposed method, dubbed bilinear optimization product quantization, achieves competitive retrieval and classification accuracies while having significant lower time and space complexities.

The papers in this special section focus on multimedia data retrieval and classification via large-scale systems. Today, large collections of multimedia data are explosively created in different fields and have attracted increasing interest in the multimedia research area. Large-scale multimedia data provide great unprecedented opportunities to address many challenging research problems, e.g., enabling generic visual classification to bridge the well-known semantic gap by exploring large-scale data, offering a promising possibility for in-depth multimedia understanding, as well as discerning patterns and making better decisions by analyzing the large pool of data. Therefore, the techniques for large-scale multimedia retrieval, classification, and understanding are highly desired. Simultaneously, the explosion of multimedia data puts urgent needs for more sophisticated and robust models and algorithms to retrieve, classify, and understand these data. Another interesting challenge is, how can the traditional machine learning algorithms be scaled up to millions and even billions of items with thousands of dimensionalities? This motivated the community to design parallel and distributed machine learning platforms, exploiting GPUs as well as developing practical algorithms. Besides, it is also important to exploit the commonalities and differences between different tasks, e.g., image retrieval and classification have much in common while different indexing methods evolve in a mutually supporting way.

Graph-based image segmentation organizes the image elements into graphs and partitions an image based on the graph. It has been widely used and many promising results are obtained. Since the segmentation performance highly depends on the graph, most of existing methods focus on obtaining a precise similarity graph or on designing efficient cutting/merging strategies. However, these two components are often conducted in two separated steps, and thus the obtained graph similarity may not be the optimal one for segmentation and this may lead to suboptimal results. In this paper, we propose a novel framework, Graph-Without-Cut (GWC), for learning the similarity graph and image segmentations simultaneously. GWC learns the similarity graph by assigning adaptive and optimal neighbors to each vertex based on the spatial and visual information. Meanwhile, the new rank constraint is imposed to the Laplacian matrix of the similarity graph, such that the connected components in the resulted similarity graph are exactly equal to the region number. Extensive empirical results on three public data sets (i.e, BSDS300, BSDS500 and MSRC) show that our unsupervised GWC achieves state-of-the-art performance compared with supervised and unsupervised image segmentation approaches.

Several applications benefit from learning coupled representations able to describe data from multiple sources. For instance, cross-domain dictionary learning methods demonstrated to be particularly effective. In this paper we introduce Multi-Paced Dictionary Learning (MPDL) and propose an instantiation of it under the framework of cross-domain dictionary learning. MPDL is inspired by previous works on self-paced learning, a framework able to enhance the accuracy of conventional learning models by presenting the training data in a meaningful order, i.e. easy samples are provided first. However, most of existing self-paced learning methods only consider a single modality, while MPDL is specifically designed to assess the learning pace when data from multiple sources are available. We present the model and propose an efficient algorithm to learn the dictionaries and codes. The approach is validated via experiments on two different tasks, namely cross-media retrieval and sketch-to-photo face recognition, using publicly available datasets.

Recent progress in using Long Short-Term Memory (LSTM) for image description has motivated the exploration of their applications for automatically describing video content with natural language sentences. By taking a video as a sequence of features, LSTM model is trained on video-sentence pairs to learn association of a video to a sentence. However, most existing methods compress an entire video shot or frame into a static representation, without considering attention which allows for salient features. Furthermore, most existing approaches model the translating error, but ignore the correlations between sentence semantics and visual content.

Video segmentation has become an important and active research area with a large diversity of proposed approaches. Graph-based methods, enabling top performance on recent benchmarks, usually focus on either obtaining a precise similarity graph or designing efficient graph cutting strategies. However, these two components are often conducted in two separated steps, and thus the obtained similarity graph may not be the optimal one for segmentation and this may lead to suboptimal results. In this paper, we propose a novel framework, joint graph learning and video segmentation (JGLVS)}, which learns the similarity graph and video segmentation simultaneously. JGLVS learns the similarity graph by assigning adaptive neighbors for each vertex based on multiple cues (appearance, motion, boundary and spatial information). Meanwhile, the new rank constraint is imposed to the Laplacian matrix of the similarity graph, such that the connected components in the resulted similarity graph are exactly equal to the number of segmentations. Furthermore, JGLVS can automatically weigh multiple cues and calibrate the pairwise distance of superpixels based on their topology structures. Most noticeably, empirical results on the challenging dataset VSB100 show that JGLVS achieves promising performance on the benchmark dataset which outperforms the state-of-the-art by up to 11% for the BPR metric.

In the last few years, the query-by-visual-example paradigm gained popularity, specially for content based retrieval systems. As sketches represent a natural way of expressing a synthetic query, recent research efforts focused on developing algorithmic solutions to address the sketch-based image retrieval (SBIR) problem. Within this context, we propose a novel approach for SBIR that, unlike previous methods, is able to exploit the visual complexity inherently present in sketches and images. We introduce academic learning, a paradigm in which the sample learning order is constructed both from the data, as in self-paced learning, and from partial curricula. We propose an instantiation of this paradigm within the framework of coupled dictionary learning to address the SBIR task. We also present an efficient algorithm to learn the dictionaries and the codes, and to pace the learning combining the reconstruction error, the prior knowledge suggested by the partial curricula and the cross-domain code coherence. In order to evaluate the proposed approach, we report an extensive experimental validation showing that the proposed method outperforms the state-of-the-art in coupled dictionary learning and in SBIR on three different publicly available datasets.

Cross-modal retrieval has been attracting increasing attention because of the explosion of multi-modal data, e.g., texts and images. Most supervised cross-modal retrieval methods learn discriminant common subspaces minimizing the heterogeneity of different modalities by exploiting the label information. However, these methods neglect the fact that, in practice, the given labels of training data might be incomplete (i.e., some of their labels are missing). The low-quality labels result in less effective subspace and consequent unsatisfactory retrieval performance. To tackle this, we propose a novel model that simultaneously performs label completion and cross-modal retrieval. Specifically, we assume the to-be-learned common subspace can be jointly derived through two aspects: 1) linear projection from modality-specific features and 2) enriching mapping from the incomplete labels. We thus formulate the subspace learning problem as a co-regularized learning framework based on multi-modal features and incomplete labels. Extensive experiments on two large-scale multi-modal datasets demonstrate the superiority of our model for both label completion and cross-modal retrieval over the state-of-the-arts.

Hashing or binary code learning has been recognized to accomplish efficient near neighbor search, and has thus attracted broad interests in recent retrieval, vision, and learning studies. One main challenge of learning to hash arises from the involvement of discrete variables in binary code optimization. While the widely used continuous relaxation may achieve high learning efficiency, the pursued codes are typically less effective due to accumulated quantization error. In this paper, we propose a novel binary code optimization method, dubbed discrete proximal linearized minimization (DPLM), which directly handles the discrete constraints during the learning process. Specifically, the discrete (thus nonsmooth nonconvex) problem is reformulated as minimizing the sum of a smooth loss term with a nonsmooth indicator function. The obtained problem is then efficiently solved by an iterative procedure with each iteration admitting an analytical discrete solution, which is thus shown to converge very fast. In addition, the proposed method supports a large family of empirical loss functions, which is particularly instantiated in this paper by both a supervised and an unsupervised hashing losses, together with the bits uncorrelation and balance constraints. In particular, the proposed DPLM with a supervised ℓ2loss encodes the whole NUS-WIDE database into 64-b binary codes within 10 s on a standard desktop computer. The proposed approach is extensively evaluated on several large-scale data sets and the generated binary codes are shown to achieve very promising results on both retrieval and classification tasks.

In multimedia annotation, due to the time constraints and the tediousness of manual tagging, it is quite common to utilize both tagged and untagged data to improve the performance of supervised learning when only limited tagged training data are available. This is often done by adding a geometry-based regularization term in the objective function of a supervised learning model. In this case, a similarity graph is indispensable to exploit the geometrical relationships among the training data points, and the graph construction scheme essentially determines the performance of these graph-based learning algorithms. However, most of the existing works construct the graph empirically and are usually based on a single feature without using the label information. In this paper, we propose a semi-supervised annotation approach by learning an optimized graph (OGL) from multi-cues (i.e., partial tags and multiple features), which can more accurately embed the relationships among the data points. Since OGL is a transductive method and cannot deal with novel data points, we further extend our model to address the out-of-sample issue. Extensive experiments on image and video annotation show the consistent superiority of OGL over the state-of-the-art methods.

In recent years, the task of event recognition from videos has attracted increasing interest in multimedia area. While most of the existing research was mainly focused on exploring visual cues to handle relatively small-granular events, it is difficult to directly analyze video content without any prior knowledge. Therefore, synthesizing both the visual and semantic analysis is a natural way for video event understanding. In this paper, we study the problem of Web video event recognition, where Web videos often describe large-granular events and carry limited textual information. Key challenges include how to accurately represent event semantics from incomplete textual information and how to effectively explore the correlation between visual and textual cues for video event understanding. We propose a novel framework to perform complex event recognition from Web videos. In order to compensate the insufficient expressive power of visual cues, we construct an event knowledge base by deeply mining semantic information from ubiquitous Web documents. This event knowledge base is capable of describing each event with comprehensive semantics. By utilizing this base, the textual cues for a video can be significantly enriched. Furthermore, we introduce a two-view adaptive regression model, which explores the intrinsic correlation between the visual and textual cues of the videos to learn reliable classifiers. Extensive experiments on two real-world video data sets show the effectiveness of our proposed framework and prove that the event knowledge base indeed helps improve the performance of Web video event recognition.

Recently, binary codes have been widely used in many multimedia applications to approximate high-dimensional multimedia features for practical similarity search due to the highly compact data representation and efficient distance computation. While the majority of the hashing methods aim at learning more accurate hash codes, only a few of them focus on indexing methods to accelerate the search for binary code databases. Among these indexing methods, most of them suffer from extremely high memory cost or extensive Hamming distance computations. In this paper, we propose a new Hamming distance search scheme for large scale binary code databases, which is free of Hamming distance computations to return the exact results. Without the necessity to compare database binary codes with queries, the search performance can be improved and databases can be externally maintained. More specifically, we adopt the inverted multi-index data structure to index binary codes. Importantly, the Hamming distance information embedded in the structure is utilized in the designed search scheme such that the verification of exact results no longer relies on Hamming distance computations. As a step further, we optimize the performance of the inverted multi-index structure by taking the code distributions among different bits into account for index construction. Empirical results on large-scale binary code databases demonstrate the superiority of our method over existing approaches in terms of both memory usage and search efficiency.

We present a novel unsupervised deep learning framework for anomalous event detection in complex video scenes.While most existing works merely use hand-crafted appearance and motion features, we propose Appearance and Motion DeepNet (AMDN) which utilizes deep neural networks to automatically learn feature representations.To exploit the complementary information of both appearance and motion patterns, we introduce a novel double fusion framework, combining both the benefits of traditional early fusion and late fusion strategies.Specifically, stacked denoising autoencoders are proposed to separately learn both appearance and motion features as well as a joint representation (early fusion).Based on the learned representations, multiple one-class SVM models are used to predict the anomaly scores of each input, which are then integrated with a late fusion strategy for final anomaly detection.We evaluate the proposed method on two publicly available video surveillance datasets, showing competitive performance with respect to state of the art approaches.

In multimedia annotation, due to the time constraints and the tediousness of manual tagging, it is quite common to utilize both tagged and untagged data to improve the performance of supervised learning when only limited tagged training data are available. This is often done by adding a geometrically based regularization term in the objective function of a supervised learning model. In this case, a similarity graph is indispensable to exploit the geometrical relationships among the training data points, and the graph construction scheme essentially determines the performance of these graph-based learning algorithms. However, most of the existing works construct the graph empirically and are usually based on a single feature without using the label information. In this paper, we propose a semi-supervised annotation approach by learning an optimal graph (OGL) from multi-cues (i.e., partial tags and multiple features) which can more accurately embed the relationships among the data points. We further extend our model to address out-of-sample and noisy label issues. Extensive experiments on four public datasets show the consistent superiority of OGL over state-of-the-art methods by up to 12% in terms of mean average precision.

Image-based localization is an essential complement to GPS localization. Current image-based localization methods are based on either 2D-to-3D or 3D-to-2D to find the correspondences, which ignore the real scene geometric attributes. The main contribution of our paper is that we use a 3D model reconstructed by a short video as the query to realize 3D-to-3D localization under a multi-task point retrieval framework. Firstly, the use of a 3D model as the query enables us to efficiently select location candidates. Furthermore, the reconstruction of 3D model exploits the correlations among different images, based on the fact that images captured from different views for SfM share information through matching features. By exploring shared information (matching features) across multiple related tasks (images of the same scene captured from different views), the visual feature's view-invariance property can be improved in order to get to a higher point retrieval accuracy. More specifically, we use multi-task point retrieval framework to explore the relationship between descriptors and the 3D points, which extracts the discriminant points for more accurate 3D-to-3D correspondences retrieval. We further apply multi-task learning (MTL) retrieval approach on thermal images to prove that our MTL retrieval framework also provides superior performance for the thermal domain. This application is exceptionally helpful to cope with the localization problem in an environment with limited light sources.

The problem of image categorization from zero or only a few training examples, called zero-shot learning, occurs frequently, but it has hardly been studied in computer vision research. To tackle this problem, mid-level semantic attributes are introduced to identify image categories. For example, one can construct a classifier for the giant panda category by enumerating its attributes (e.g., black, white and four-footed) even without providing giant panda training images. Recently, several studies have investigated to learn attribute classifiers, based on which new classes can be detected. However, an often-encountered problem is the limited number of training data due to the time-consuming manual annotation of the attributes. Also, using single feature is hard to detect some attributes, e.g., the HSV feature is not robust enough to predict 'tusk' or 'flies' attributes. In this paper, we propose a unified semi-supervised learning (SSL) framework that learns the attribute classifiers by utilizing multiple feature and exploring the correlations between images. Specifically, we learn an optimal graph which embeds the relationships among the data points more accurately. Then, this graph is used to generate a geometrical regularizers for a semi-supervised learning model to learn the attribute classifier by utilizing both labeled and unlabeled images. Afterward, new classes can be detected based on their attribute representation. The use of SSL can boost the performances of attribute classifiers with very few training examples, and the adoption of multiple features makes the attribute prediction more robust. Experimental results on a series of real benchmark data sets suggest that semi-supervised learning do enhance the performances of attribute prediction and zero-shot categorization, compared with state-of-the-art methods.

Learning-based hashing methods are becoming the mainstream for approximate scalable multimedia retrieval. They consist of two main components: hash codes learning for training data and hash functions learning for new data points. Tremendous efforts have been devoted to designing novel methods for these two components, i.e., supervised and unsupervised methods for learning hash codes, and different models for inferring hashing functions. However, there is little work integrating supervised and unsupervised hash codes learning into a single framework. Moreover, the hash function learning component is usually based on hand-crafted visual features extracted from the training images. The performance of a content-based image retrieval system crucially depends on the feature representation and such hand-crafted visual features may degrade the accuracy of the hash functions. In this paper, we propose a semi-supervised deep learning hashing (DLH) method for fast multimedia retrieval. More specifically, in the first component, we utilize both visual and label information to learn an relative similarity graph that can more precisely reflect the relationship among training data, and then generate the hash codes based on the graph. In the second stage, we apply a deep convolutional neural network (CNN) to simultaneously learn a good multimedia representation and hash functions. Extensive experiments on three popular datasets demonstrate the superiority of our DLH over both supervised and unsupervised hashing methods.

There is an increasing interest in using hash codes for efficient multimedia retrieval and data storage. The hash functions are learned in such a way that the hash codes can preserve essential properties of the original space or the label information. Then the Hamming distance of the hash codes can approximate the data similarity. Existing works have demonstrated the success of many supervised hashing models. However, labeling data is time and labor consuming, especially for scalable datasets. In order to utilize the supervised hashing models to improve the discriminative power of hash codes, we propose a Supervised Hashing with Pseudo Labels (SHPL) which uses the cluster centers of the training data to generate pseudo labels, based on which the hash codes can be generated using the criteria of supervised hashing. More specifically, we utilize linear discriminant analysis (LDA) with trace ratio criterion as a showcase for hash functions learning and during the optimization, we prove that the pseudo labels and the hash codes can be jointly learned and iteratively updated in an unified framework. The learned hash functions can harness the discriminant power of trace ratio criterion, and thus can achieve better performance. Experimental results on three large-scale unlabeled datasets (i.e., SIFT1M, GIST1M, and SIFT1B) demonstrate the superior performance of our SHPL over existing hashing methods.

Hashing algorithm has been widely used to speed up image retrieval due to its compact binary code and fast distance calculation. The combination with deep learning boosts the performance of hashing by learning accurate representations and complicated hashing functions. So far, the most striking success in deep hashing have mostly involved discriminative models, which require labels. To apply deep hashing on datasets without labels, we propose a deep self-taught hashing algorithm (DSTH), which generates a set of pseudo labels by analyzing the data itself, and then learns the hash functions for novel data using discriminative deep models. Furthermore, we generalize DSTH to support both supervised and unsupervised cases by adaptively incorporating label information. We use two different deep learning framework to train the hash functions to deal with out-of-sample problem and reduce the time complexity without loss of accuracy. We have conducted extensive experiments to investigate different settings of DSTH, and compared it with state-of-the-art counterparts in six publicly available datasets. The experimental results show that DSTH outperforms the others in all datasets.

Product quantization-based approaches are effective to encode high-dimensional data points for approximate nearest neighbor search. The space is decomposed into a Cartesian product of low-dimensional subspaces, each of which generates a sub codebook. Data points are encoded as compact binary codes using these sub codebooks, and the distance between two data points can be approximated efficiently from their codes by the precomputed lookup tables. Traditionally, to encode a subvector of a data point in a subspace, only one sub codeword in the corresponding sub codebook is selected, which may impose strict restrictions on the search accuracy. In this paper, we propose a novel approach, named optimized cartesian K-means (ock-means), to better encode the data points for more accurate approximate nearest neighbor search. In ock-means, multiple sub codewords are used to encode the subvector of a data point in a subspace. Each sub codeword stems from different sub codebooks in each subspace, which are optimally generated with regards to the minimization of the distortion errors. The high-dimensional data point is then encoded as the concatenation of the indices of multiple sub codewords from all the subspaces. This can provide more flexibility and lower distortion errors than traditional methods. Experimental results on the standard real-life data sets demonstrate the superiority over state-of-the-art approaches for approximate nearest neighbor search.

Image fingerprinting is regarded as an alternative approach to watermarking in terms of near-duplicate detection application. It consists of feature extraction and feature indexing. Generally, the former is mainly related to discrimination, robustness , and security while the latter closely focuses on the efficiency of fingerprints search. To enable fast fingerprints searching over a very large database, we propose a new kernelized multiple feature hashing method to convert the real-value fingerprints into compact binary-value fingerprints. During the process of converting, the proposed hashing method jointly utilizes the kernel trick and multiple feature fusion strategy to map the image represented by multiple features into a compact binary code. With the help of the kernel function, the hashing method can be applied to any format (such as string, graph, set, and so on) as long as there is an associated kernel function available for similarity measurement. In addition, taking multiple features into account aims at improving the discriminability since these multiple evidences are complementary to each other. The extensive experimental results show that the proposed algorithm outperforms state-of-the-art kernelized hashing methods by up to 10 percent.

Sparse coding was shown to be able to find succinct representations of stimuli. Recently, it has been successfully applied to a variety of problems in image processing analysis. Sparse coding models data vectors as a linear combination of a few elements from a dictionary. However, most existing sparse coding methods are applied for a single task on a single dataset. The learned dictionary is then possibly biased towards the specific dataset and lacks of generalization abilities. In light of this, in this paper we propose a multitask sparse coding approach by uncovering a shared subspace among heterogeneous datasets. The proposed multi-task coding strategy leverages the commonality benefit from different datasets. Moreover, our multi-task coding framework is capable of direct classification by incorporating label information. Experimental results show that the dictionary learned by our approach has more generalization abilities and our model performs better classification compared to the model learned from only one dataset or the model learned from simply pooling different datasets together.

Similarity search plays an important role in many applications involving high-dimensional data. Due to the known dimensionality curse, the performance of most existing indexing structures degrades quickly as the feature dimensionality increases. Hashing methods, such as locality sensitive hashing (LSH) and its variants, have been widely used to achieve fast approximate similarity search by trading search quality for efficiency. However, most existing hashing methods make use of randomized algorithms to generate hash codes without considering the specific structural information in the data. In this paper, we propose a novel hashing method, namely, robust hashing with local models (RHLM), which learns a set of robust hash functions to map the high-dimensional data points into binary hash codes by effectively utilizing local structural information. In RHLM, for each individual data point in the training dataset, a local hashing model is learned and used to predict the hash codes of its neighboring data points. The local models from all the data points are globally aligned so that an optimal hash code can be assigned to each data point. After obtaining the hash codes of all the training data points, we design a robust method by employing l2,1 -norm minimization on the loss function to learn effective hash functions, which are then used to map each database point into its hash code. Given a query data point, the search process first maps it into the query hash code by the hash functions and then explores the buckets, which have similar hash codes to the query hash code. Extensive experimental results conducted on real-life datasets show that the proposed RHLM outperforms the state-of-the-art methods in terms of search quality and efficiency.

In this paper, we present a new multimedia retrieval paradigm to innovate large-scale search of heterogenous multimedia data. It is able to return results of different media types from heterogeneous data sources, e.g., using a query image to retrieve relevant text documents or images from different data sources. This utilizes the widely available data from different sources and caters for the current users' demand of receiving a result list simultaneously containing multiple types of data to obtain a comprehensive understanding of the query's results. To enable large-scale inter-media retrieval, we propose a novel inter-media hashing (IMH) model to explore the correlations among multiple media types from different data sources and tackle the scalability issue. To this end, multimedia data from heterogeneous data sources are transformed into a common Hamming space, in which fast search can be easily implemented by XOR and bit-count operations. Furthermore, we integrate a linear regression model to learn hashing functions so that the hash codes for new data points can be efficiently generated. Experiments conducted on real-world large-scale multimedia datasets demonstrate the superiority of our proposed method compared with state-of-the-art techniques.

Near-duplicate video retrieval (NDVR) has recently attracted much research attention due to the exponential growth of online videos. It has many applications, such as copyright protection, automatic video tagging and online video monitoring. Many existing approaches use only a single feature to represent a video for NDVR. However, a single feature is often insufficient to characterize the video content. Moreover, while the accuracy is the main concern in previous literatures, the scalability of NDVR algorithms for large scale video datasets has been rarely addressed. In this paper, we present a novel approach-Multiple Feature Hashing (MFH) to tackle both the accuracy and the scalability issues of NDVR. MFH preserves the local structural information of each individual feature and also globally considers the local structures for all the features to learn a group of hash functions to map the video keyframes into the Hamming space and generate a series of binary codes to represent the video dataset. We evaluate our approach on a public video dataset and a large scale video dataset consisting of 132,647 videos collected from YouTube by ourselves. This dataset has been released (http://itee.uq.edu.au/shenht/UQ_VIDEO/). The experimental results show that the proposed method outperforms the state-of-the-art techniques in both accuracy and efficiency.

Multimedia data are usually represented by multiple features. In this paper, we propose a new algorithm, namely Multi-feature Learning via Hierarchical Regression for multimedia semantics understanding, where two issues are considered. First, labeling large amount of training data is labor-intensive. It is meaningful to effectively leverage unlabeled data to facilitate multimedia semantics understanding. Second, given that multimedia data can be represented by multiple features, it is advantageous to develop an algorithm which combines evidence obtained from different features to infer reliable multimedia semantic concept classifiers. We design a hierarchical regression model to exploit the information derived from each type of feature, which is then collaboratively fused to obtain a multimedia semantic concept classifier. Both label information and data distribution of different features representing multimedia data are considered. The algorithm can be applied to a wide range of multimedia applications and experiments are conducted on video data for video concept annotation and action recognition. Using Trecvid and CareMedia video datasets, the experimental results show that it is beneficial to combine multiple features. The performance of the proposed algorithm is remarkable when only a small amount of labeled training data are available.

Near-duplicate video retrieval (NDVR) has recently attracted lots of research attention due to the exponential growth of online videos. It helps in many areas, such as copyright protection, video tagging, online video usage monitoring, etc. Most of existing approaches use only a single feature to represent a video for NDVR. However, a single feature is often insufficient to characterize the video content. Besides, while the accuracy is the main concern in previous literatures, the scalability of NDVR algorithms for large scale video datasets has been rarely addressed. In this paper, we present a novel approach - Multiple Feature Hashing (MFH) to tackle both the accuracy and the scalability issues of NDVR. MFH preserves the local structure information of each individual feature and also globally consider the local structures for all the features to learn a group of hash functions which map the video keyframes into the Hamming space and generate a series of binary codes to represent the video dataset. We evaluate our approach on a public video dataset and a large scale video dataset consisting of 132,647 videos, which was collected from YouTube by ourselves. The experiment results show that the proposed method outperforms the state-of-the-art techniques in both accuracy and efficiency.