In human-object interaction (HOI), physical contact between the body and objects is a primary determinant of realism and plausibility. Prior HOI methods typically encode relations via global joint-to-centroid or joint-to-boundary. Such strategies neglect contact anchors that are essential for defining joint-to-contact relations-where and how HOI occurs, thereby implicitly reducing the problem to nearest-distance optimization. Without explicit contact anchors and joint-to-contact dynamics, previous models drift toward artifacts: human-object penetration or unnatural object floating. We argue that modeling contact relationships by contact anchors is important for generating realistic HOIs, as it directly captures where and how humans physically interact with objects rather than merely minimizing spatial proximity. To address these limitations, we propose Contact-Aware HOI (ContA-HOI), a progressive framework that decomposes HOI generation into three synergistic stages: discovering where contact occurs, modeling how contact evolves, and guiding generation with contact constraints. First, a Contact Affordance Predictor (CAP) addresses the “where” by predicting precise object-surface contact anchors from text, human pose, and object geometry. Second, these anchors seed a Contact Relation Field (CRF) that captures “how” by modeling spatiotemporal dynamics of joint-to-contact relations throughout the interaction. Finally, a Contact Dynamics Model (CDM) learns a prior CRF evolution pattern and guides motion diffusion sampling by aligning the generated motion's CRF with this learned prior. On the FullBodyManipulation dataset, ContA-HOI yields more realistic and physically plausible HOIs, improving foot sliding and contact percentage over recent baselines.

Video-based multimodal large language models (V-MLLMs) have shown vulnerability to adversarial examples in video-text multimodal tasks. However, the transferability of adversarial videos to unseen models—a common and practical real-world scenario—remains unexplored. In this paper, we pioneer an investigation into the transferability of adversarial video samples across V-MLLMs. We find that existing adversarial attack methods face significant limitations when applied in black-box settings for V-MLLMs, which we attribute to the following shortcomings: (1) lacking generalization in perturbing video features, (2) focusing only on sparse key-frames, and (3) failing to integrate multimodal information. To address these limitations and deepen the understanding of V-MLLM vulnerabilities in black-box scenarios, we introduce the Image-to-Video MLLM (I2V-MLLM) attack. In I2V-MLLM, we utilize an image-based multimodal large language model (I-MLLM) as a surrogate model to craft adversarial video samples. Multimodal interactions and spatiotemporal information are integrated to disrupt video representations within the latent space, improving adversarial transferability. Additionally, a perturbation propagation technique is introduced to handle different unknown frame sampling strategies. Experimental results demonstrate that our method can generate adversarial examples that exhibit strong transferability across different V-MLLMs on multiple video-text multimodal tasks. Compared to white-box attacks on these models, our black-box attacks (using BLIP-2 as a surrogate model) achieve competitive performance, with average attack success rate (AASR) of 57.98% on MSVD-QA and 58.26% on MSRVTT-QA for Zero-Shot VideoQA tasks, respectively.

Recently, rapid advancements have been made in multimodal large language models (MLLMs), especially in video understanding tasks. However, current research focuses on simple video scenarios, failing to reflect the complex and diverse nature of real-world audio-visual events in videos. To bridge this gap, we firstly introduce R-AVST, a dataset for audio-visual reasoning featuring fine-grained spatio-temporal annotations. In constructing this, we design a pipeline consisting of LLM-based key object extraction, automatic spatial annotation and manual quality inspection, resulting in over 5K untrimmed videos with 27K objects across 100 types of audio-visual events. Building on this dataset, we define three core tasks for spatio-temporal reasoning in audio-visual scenes and generate more than 8K high-quality, evenly distributed question-answer pairs to effectively benchmark model performance. To further enhance reasoning, we propose AVST-Zero, a reinforcement learning-based model that avoids intermediate supervision, directly optimizing behavior via carefully designed multi-dimensional rewards. Extensive experiments validate the effectiveness of our R-AVST in advancing audio-visual spatio-temporal reasoning, upon which AVST-Zero demonstrates competitive performance compared to existing models. To the best of our knowledge, R-AVST is the first dataset designed for real-world audio-visual spatio-temporal reasoning, and AVST-Zero offers a novel perspective for tackling future challenges in this domain.

Viewpoint missing of objects is common in scene reconstruction, as camera paths typically prioritize capturing the overall scene structure rather than individual objects. This makes it highly challenging to achieve high-fidelity object-level modeling while maintaining accurate scene-level representation. Addressing this issue is critical for advancing downstream tasks requiring high-fidelity object reconstruction. In this paper, we introduce Scene-Consistent Object Refinement via Proxy Generation and Tuning (SCORP), a novel 3D enhancement framework that leverages 3D generative priors to recover fine-grained object geometry and appearance under missing views. Starting with proxy generation by substituting degraded objects using a 3D generation model, SCORP then progressively refines geometry and texture by aligning each proxy to its degraded counter-part in 7-DoF pose, followed by correcting spatial and appearance inconsistencies through registration-constrained enhancement. This two-stage proxy tuning ensures the high-fidelity geometry and appearance of the original object in unseen views while maintaining consistency in spatial positioning, observed geometry, and appearance. Across challenging benchmarks, SCORP achieves consistent gains over recent state-of-the-art baselines on both novel view synthesis and geometry completion tasks. SCORP is available at https://github.com/PolySummit/SCORP.

With the rapid growth of online video platforms and the escalating volume of video content, the need for proficient video understanding tools has increased significantly. Given the remarkable capabilities of large language models (LLMs) in language and multimodal tasks, this survey provides a detailed overview of recent advances in video understanding that harness the power of LLMs (Vid-LLMs). The emergent capabilities of Vid-LLMs are surprisingly advanced, particularly their ability for open-ended multi-granularity (abstract, temporal, and spatiotemporal) reasoning combined with common-sense knowledge, suggesting a promising path for future video understanding. We examine the unique characteristics and capabilities of Vid-LLMs, categorizing the approaches into three main types:Video Analyzer × LLM, Video Embedder × LLM, and (Analyzer + Embedder) × LLM. We identify five subtypes based on the functions of LLMs in Vid-LLMs:LLMas Summarizer,LLMas Manager,LLMas Text Decoder,LLMas Regressor, andLLMas Hidden Layer. This survey also presents a comprehensive study of the tasks, datasets, benchmarks, and evaluation methods for Vid-LLMs. Additionally, it explores the extensive applications of Vid-LLMs in various domains, highlighting their remarkable scalability and versatility in real-world video understanding challenges. Additionally, it summarizes the limitations of existing Vid-LLMs and outlines directions for future research. For more information, readers are encouraged to visit the repository at https://github.com/yunlong10/Awesome-LLMs-for-Video-Understanding.

Despite impressive advancements in video understanding, most efforts remain limited to coarse-grained or visual-only video tasks. However, real-world videos encompass omni-modal information (vision, audio, and speech) with a series of events forming a cohesive storyline. The lack of multi-modal video data with fine-grained event annotations and the high cost of manual labeling are major obstacles to comprehensive omni-modality video perception. To address this gap, we propose an automatic pipeline consisting of high-quality multi-modal video filtering, semantically coherent omni-modal event boundary detection, and cross-modal correlation-aware event captioning. In this way, we present LongVALE, the first- ever Vision-Audio-Language Event understanding benchmark comprising 105K omni-modal events with precise temporal boundaries and detailed relation-aware captions within 8.4K high-quality long videos. Further, we build a baseline that leverages LongVALE to enable video large language models (LLMs) for omni-modality fine-grained temporal video understanding for the first time. Extensive experiments demonstrate the effectiveness and great potential of LongVALE in advancing comprehensive multi-modal video understanding. The dataset and code are available at https://ttgeng233.github.io/LongVALE/.

Recent advances in large video-language models have revolutionized video understanding tasks.However, their efficiency is greatly constrained by processing high volumes of visual tokens.Existing token compression strategies apply a fixed compression ratio, ignoring varying semantic density across video clips.Consequently, this leads to inadequate representation of information-rich clips due to insufficient tokens and unnecessary computation on static or content-poor ones.To address this, we propose LangDC, a Language-aware Dynamic Token Compressor.LangDC leverages a lightweight language model to describe video clips, converting them into soft caption tokens as visual representations.Trained with our proposed semantic density-aware supervision, LangDC aims to 1) cover key visual cues necessary for downstream task reasoning and 2) dynamically adjust compression ratios based on scene richness, reflected by description length.Our design mimics how humans dynamically express what they see: complex scenes (seeing more) elicit more detailed language to convey nuances (saying more), whereas simpler scenes are described with fewer words.Experimental results show that our method reduces FLOPs by 49% compared to VideoGPT+ while maintaining competitive performance.Furthermore, qualitative results demonstrate our approach adaptively adjusts the token compression ratio based on video segment richness.Codes are available at https://github.com/NIneeeeeem/LangDC.

In the field of industrial inspection, Multimodal Large Language Models (MLLMs) have a high potential to renew the paradigms in practical applications due to their robust language capabilities and generalization abilities. However, despite their impressive problem-solving skills in many domains, MLLMs' ability in industrial anomaly detection has not been systematically studied. To bridge this gap, we present MMAD, a full-spectrum MLLM benchmark in industrial Anomaly Detection. We defined seven key subtasks of MLLMs in industrial inspection and designed a novel pipeline to generate the MMAD dataset with 39,672 questions for 8,366 industrial images. With MMAD, we have conducted a comprehensive, quantitative evaluation of various state-of-the-art MLLMs. The commercial models performed the best, with the average accuracy of GPT-4o models reaching 74.9\%. However, this result falls far short of industrial requirements. Our analysis reveals that current MLLMs still have significant room for improvement in answering questions related to industrial anomalies and defects. We further explore two training-free performance enhancement strategies to help models improve in industrial scenarios, highlighting their promising potential for future research. The code and data are available at https://github.com/jam-cc/MMAD.

Multimodal Large Language Models (MLLMs) exhibit promising advancements across various tasks, yet they still encounter significant trustworthiness issues. Prior studies apply Split Conformal Prediction (SCP) in language modeling to construct prediction sets with statistical guarantees. However, these methods typically rely on internal model logits or are restricted to multiple-choice settings, which hampers their generalizability and adaptability in dynamic, open-ended environments. In this paper, we introduce *TRON*, a **t**wo-step framework for **r**isk c**o**ntrol and assessme**n**t, applicable to any MLLM that supports sampling in both open-ended and closed-ended scenarios. *TRON* comprises two main components: (1) a novel conformal score to **sample** response sets of minimum size, and (2) a nonconformity score to **identify** high-quality responses based on self-consistency theory, controlling the error rates by two specific risk levels. Furthermore, we investigate semantic redundancy in prediction sets within open-ended contexts for the first time, leading to a promising evaluation metric for MLLMs based on average set size. Our comprehensive experiments across four Video Question-Answering (VideoQA) datasets utilizing eight MLLMs show that *TRON* achieves desired error rates bounded by two user-specified risk levels. Additionally, deduplicated prediction sets maintain adaptiveness while being more efficient and stable for risk assessment under different risk levels.

Large language models (LLMs) have demonstrated remarkable potential in handling natural language processing (NLP) tasks and beyond. LLMs usually can be categorized as transformer decoder-only models (DOMs), utilizing Next-Token-Prediction (NTP) as their pre-training methodology. Despite their tremendous empirical successes, the theoretical understanding of how NTP pre-training affects the model’s generalization behavior is lacking. To fill this gap, we establish the fine-grained generalization analysis for NTP pre-training based on Rademacher complexity, where the dependence between tokens is also addressed. Technically, a novel decomposition of Rademacher complexity is developed to study DOMs from the representation learner and the token predictor, respectively. Furthermore, the upper bounds of covering number are established for multi-layer and multi-head transformer-decoder models under the Frobenius norm, which theoretically pioneers the incorporation of mask matrix within the self-attention mechanism. Our results reveal that the generalization ability of NTP pre-training is affected quantitively by the number of token sequences $N$, the maximum length of sequence $m$, and the count of parameters in the transformer model $\Theta$. Additionally, experiments on public datasets verify our theoretical findings.

Adverse conditions such as intense illumination and inclement weather pose challenges to object detection tasks. Current methodologies aim to enhance detector performance by improving image quality through various means. In low-visibility agricultural scene object detection, improving detection accuracy is insufficient with image quality enhancement alone. Existing detectors designed for low-visibility conditions do not exhibit strong performance in agricultural scenes. In this paper, we introduce a novel benchmark called Low-visibility Crop Detection (LVCD), extending the low-visibility task to agricultural scenes. Furthermore, we propose a foundational framework, Point cloud Guided Segmentation Network (PGSNet), which learns additional point cloud cues to compensate for the missing details of targets caused by low-visibility in images, extending the model’s representational capacity to two modalities. To facilitate research, we gather a multi-modal dataset, LVScene4K, comprising images and corresponding point clouds of various crop types. In order to address the challenges posed by low-visibility, we specifically designed corresponding modules. The encoder component encodes features at multiple scales and constructs multi-scale receptive fields to enable the model to simultaneously extract more detailed features from both images and point clouds. The decoder analyzes both local and global details as well as texture features of the target, while adaptively capturing characteristics under various adverse conditions to improve the model’s discriminative performance under low-visibility conditions. In the end, the model applies iterative refinement strategy for progressively optimizing the detection outcomes. Comprehensive experiments conducted on the LVScene4K demonstrate the effectiveness and robustness of PGSNet in the LVCD task.

Designing 3D indoor layouts is a crucial task with significant applications in embodied robot intelligence, virtual reality, and interior design. Existing methods for 3D layout design either rely on diffusion models, which utilize spatial relationship priors, or heavily leverage the inferential capabilities of proprietary Large Language Models (LLMs) , which require extensive prompt engineering and in-context exemplars via black-box trials. These methods often face limitations in generalization and dynamic scene editing. In this paper, we introduce LLplace, a novel 3D indoor scene layout designer based on lightweight, fine-tuned, open-source LLM Llama3. LLplace circumvents the need for spatial relationship priors and in-context exemplars, enabling efficient and credible room layout generation based solely on user inputs specifying the room type and desired objects. We curated a new dialogue dataset based on the 3D-Front dataset, expanding the original data volume and incorporating dialogue data for adding and removing objects. This dataset can enhance the LLM’s spatial understanding. Furthermore, through dialogue, LLplace activates the LLM’s capability to understand 3D layouts and perform dynamic scene editing, enabling the addition and removal of objects. Our approach demonstrates that LLplace can effectively generate and edit 3D indoor layouts interactively and outperform existing methods in delivering high-quality 3D design solutions.

The ability of robots to interpret human instructions and execute manipulation tasks necessitates the availability of task-relevant tabletop scenes for training. However, traditional methods for creating these scenes rely on time-consuming manual layout design or purely randomized layouts, which are limited in terms of plausibility or alignment with the tasks. In this paper, we formulate a novel task, namely task-oriented tabletop scene generation, which poses significant challenges due to the substantial gap between high-level task instructions and the tabletop scenes. To support research on such a challenging task, we introduce \textbf{MesaTask-10K}, a large-scale dataset comprising approximately 10,700 synthetic tabletop scenes with \emph{manually crafted layouts} that ensure realistic layouts and intricate inter-object relations. To bridge the gap between tasks and scenes, we propose a \textbf{Spatial Reasoning Chain} that decomposes the generation process into object inference, spatial interrelation reasoning, and scene graph construction for the final 3D layout. We present \textbf{MesaTask}, an LLM-based framework that utilizes this reasoning chain and is further enhanced with DPO algorithms to generate physically plausible tabletop scenes that align well with given task descriptions. Exhaustive experiments demonstrate the superior performance of MesaTask compared to baselines in generating task-conforming tabletop scenes with realistic layouts.

Automatic indoor layout generation has attracted increasing attention due to its potential in interior design, virtual environment construction, and embodied AI. Existing methods fall into two categories: prompt-driven approaches that leverage proprietary LLM services (e.g., GPT APIs), and learning-based methods trained on layout data upon diffusion-based models. Prompt-driven methods often suffer from spatial inconsistency and high computational costs, while learning-based methods are typically constrained by coarse relational graphs and limited datasets, restricting their generalization to diverse room categories. In this paper, we revisit LLM-based indoor layout generation and present 3D-SynthPlace, a large-scale dataset that combines synthetic layouts generated via a `GPT synthesize, Human inspect' pipeline, upgraded from the 3D-Front dataset. 3D-SynthPlace contains nearly 17,000 scenes, covering four common room types—bedroom, living room, kitchen, and bathroom—enriched with diverse objects and high-level spatial annotations. We further introduce OptiScene, a strong open-source LLM optimized for indoor layout generation, fine-tuned based on our 3D-SynthPlace dataset through our two-stage training. For the warum-up stage I, we adopt supervised fine-tuning (SFT), which is taught to first generate high-level spatial descriptions then conditionally predict concrete object placements. For the reinforcing stage II, to better align the generated layouts with human design preferences, we apply multi-turn direct preference optimization (DPO), which significantly improving layout quality and generation success rates. Extensive experiments demonstrate that OptiScene outperforms traditional prompt-driven and learning-based baselines. Moreover, OptiScene shows promising potential in interactive tasks such as scene editing and robot navigation, highlighting its applicability beyond static layout generation.

Visual information is first encoded into spike trains by retinal ganglion cells (RGCs), forming the foundation of biological vision. Decoding the semantic and perceptual content embedded in these spikes remains a key challenge in neuroscience. We introduce a novel framework that leverages recent advances in artificial intelligence to interpret spike-based visual signals. Our framework consists of spike-driven multimodal large language model (MLLM) and a spike-driven ControlNet to emulate two core functions of the visual cortex: semantic understanding and image reconstruction. By bridging biological and computational vision, our framework enables effective decoding of spike signals generated by RGCs. We further validate the model on the spike-driven MLLM on the MSCOCO test set. The experiment results demonstrate that our framework not only enhances interpretability and usability of spike-driven outputs but also holds promise as a tool to support neuroscience research and aid visually impaired individuals. Participant feedback highlights its potential to facilitate future advances in neural decoding and vision restoration technologies.

Video event localization tasks include temporal action localization (TAL), sound event detection (SED) and audio-visual event localization (AVEL). Existing methods tend to over-specialize on individual tasks, neglecting the equal importance of these different events for a complete understanding of video content. In this work, we aim to develop a unified framework to solve TAL, SED and AVEL tasks together to facilitate holistic video understanding. However, it is challenging since different tasks emphasize distinct event characteristics and there are substantial disparities in existing task-specific datasets (size/domain/duration). It leads to unsatisfactory results when applying a naive multi-task strategy. To tackle the problem, we introduce UniAV, a Unified Audio-Visual perception network to effectively learn and share mutually beneficial knowledge across tasks and modalities. Concretely, we propose a unified audio-visual encoder to derive generic representations from multiple temporal scales for videos from all tasks. Meanwhile, task-specific experts are designed to capture the unique knowledge specific to each task. Besides, instead of using separate prediction heads, we develop a novel unified language-aware classifier by utilizing semantic-aligned task prompts, enabling our model to flexibly localize various instances across tasks with an impressive open-set ability to localize novel categories. Extensive experiments demonstrate that UniAV, with its unified architecture, significantly outperforms both single-task models and the naive multi-task baseline across all three tasks. It achieves superior or on-par performances compared to the state-of-the-art task-specific methods on ActivityNet 1.3, DESED and UnAV-100 benchmarks.

Existing video inpainting approaches tend to adopt vision transformers with rare customized designs, which poses two limitations. Firstly, the conventional self-attention mechanism treats tokens from invalid and valid regions equally and mingles them, which may incur blurriness. Secondly, these approaches merely employ forward frames as references, while ignoring the past inpainted frames, which are also valuable in enhancing temporal consistency and offering more available information. In this paper, we propose a new video inpainting network, called Bidirectional Error-Aware Fusion Network (BEAF-Net). Concretely, on one hand, we propose a tailored Error-Aware Transformer (EAT) that discerns different tokens by assigning dynamic weights to bridle the use of erroneous tokens. Meanwhile, each EAT is equipped with a Spatial Feature Enhancement (SFE) layer to synthesize features with multi-scales. On the other hand, we apply a pair of EATs to utilize forward reference frames and past inpainted frames simultaneously, and a proposed Bidirectional Fusion (BiF) layer is exerted to blend the aggregation results adaptively. By coupling these novel designs, our proposed BEAF-Net completely leverages the location priors, multi-scale perception, and past predictions to produce more faithful and consistent inpainting results. We corroborate our BEAF-Net on two commonly-used video inpainting datasets: DAVIS and Youtube-VOS, where the experimental results demonstrate BEAF-Net compares favorably with state-of-the-art solutions. Video examples can be found athttps://github.com/JCATCV/BEAF-Net.

Deep neural networks (DNNs) have shown an astonishing ability to unlock the complicated relationships among the inputs and their responses. Along with empirical successes, some approximation analysis of DNNs has also been provided to understand their generalization performance. However, the existing analysis depends heavily on the independently identically distribution (i.i.d.) assumption of observations, which may be too ideal and often violated in real-world applications. To relax the i.i.d. assumption, this article develops the covering number-based concentration estimation to establish generalization bounds of DNNs with $\tau $ -mixing samples, where the dependency between samples is much general including $\alpha $ -mixing process as a special case. By assigning a specific parameter value to the $\tau $ -mixing process, our results are consistent with the existing convergence analysis under the i.i.d. case. Experiments on simulated data validate the theoretical findings.

Unsupervised Anomaly Detection (UAD) with incremental training is crucial in industrial manufacturing, as unpredictable defects make obtaining sufficient labeled data infeasible. However, continual learning methods primarily rely on supervised annotations, while the application in UAD is limited due to the absence of supervision. Current UAD methods train separate models for different classes sequentially, leading to catastrophic forgetting and a heavy computational burden. To address this issue, we introduce a novel Unsupervised Continual Anomaly Detection framework called UCAD, which equips the UAD with continual learning capability through contrastively-learned prompts. In the proposed UCAD, we design a Continual Prompting Module (CPM) by utilizing a concise key-prompt-knowledge memory bank to guide task-invariant 'anomaly' model predictions using task-specific 'normal' knowledge. Moreover, Structure-based Contrastive Learning (SCL) is designed with the Segment Anything Model (SAM) to improve prompt learning and anomaly segmentation results. Specifically, by treating SAM's masks as structure, we draw features within the same mask closer and push others apart for general feature representations. We conduct comprehensive experiments and set the benchmark on unsupervised continual anomaly detection and segmentation, demonstrating that our method is significantly better than anomaly detection methods, even with rehearsal training. The code will be available at https://github.com/shirowalker/UCAD.

One of the ultimate goals of representation learning is to achieve compactness within a class and well-separability between classes. Many outstanding metric-based and prototype-based methods following the Expectation-Maximization paradigm, have been proposed for this objective. However, they inevitably introduce biases into the learning process, particularly with long-tail distributed training data. In this paper, we reveal that the class prototype is not necessarily to be derived from training features and propose a novel perspective to use pre-defined class anchors serving as feature centroid to unidirectionally guide feature learning. However, the pre-defined anchors may have a large semantic distance from the pixel features, which prevents them from being directly applied. To address this issue and generate feature centroid independent from feature learning, a simple yet effective Semantic Anchor Regularization (SAR) is proposed. SAR ensures the inter-class separability of semantic anchors in the semantic space by employing a classifier-aware auxiliary cross-entropy loss during training via disentanglement learning. By pulling the learned features to these semantic anchors, several advantages can be attained: 1) the intra-class compactness and naturally inter-class separability, 2) induced bias or errors from feature learning can be avoided, and 3) robustness to the long-tailed problem. The proposed SAR can be used in a plug-and-play manner in the existing models. Extensive experiments demonstrate that the SAR performs better than previous sophisticated prototype-based methods. The implementation is available at https://github.com/geyanqi/SAR.

Block image compressive sensing methods, which divide a single image into small blocks for efficient sampling and reconstruction, have achieved significant success. However, these methods process each block locally and thus disregard the global communication among different blocks in the reconstruction step. Existing methods have attempted to address this issue with local filters or by directly reconstructing the entire image, but they have only achieved insufficient communication among adjacent pixels or bypassed the problem. To directly confront the communication problem among blocks and effectively resolve it, we propose a novel approach called Block Reconstruction with Blocks' Communication Network (BRBCN). BRBCN focuses on both local and global information, while further taking their interactions into account. Specifically, BRBCN comprises dual CNN and Transformer architectures, in which CNN is used to reconstruct each block for powerful local processing and Transformer is used to calculate the global communication among all the blocks. Moreover, we propose a global-to-local module (G2L) and a local-to-global module (L2G) to effectively integrate the representations of CNN and Transformer, with which our BRBCN network realizes the bidirectional interaction between local and global information. Extensive experiments show our BRBCN method outperforms existing state-of-the-art methods by a large margin. The code is available at https://github.com/kongxiuxiu/BRBCN

Concealed Object Detection (COD) aims to identify objects visually embedded in their background. Existing COD datasets and methods predominantly focus on animals or humans, ignoring the agricultural domain, which often contains numerous, small, and concealed crops with severe occlusions. In this paper, we introduce Concealed Crop Detection (CCD), which extends classic COD to agricultural domains. Experimental study shows that unimodal data provides insufficient information for CCD. To address this gap, we first collect a large-scale RGB-D dataset, ACOD-12K, containing high-resolution crop images and depth maps. Then, we propose a foundational framework named Recurrent Iterative Segmentation Network (RISNet). To tackle the challenge of dense objects, we employ multi-scale receptive fields to capture objects of varying sizes, thus enhancing the detection performance for dense objects. By fusing depth features, our method can acquire spatial information about concealed objects to mitigate disturbances caused by intricate backgrounds and occlusions. Furthermore, our model adopts a multi-stage iterative approach, using predictions from each stage as gate attention to reinforce position information, thereby improving the detection accuracy for small objects. Extensive experimental results demonstrate that our RISNet achieves new state-of-the-art performance on both newly proposed CCD and classic COD tasks. All resources will be available at https://github.com/Kki2Eve/RISNet.

Zhepeng Wang, Runxue Bao, Yawen Wu, Jackson Taylor, Cao Xiao, Feng Zheng, Weiwen Jiang, Shangqian Gao, Yanfu Zhang. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

Out-of-distribution (OOD) detection aims at identifying samples from unknown classes, playing a crucial role in trustworthy models against errors on unexpected inputs. Extensive research has been dedicated to exploring OOD detection in the vision modality. {Vision-language models (VLMs) can leverage both textual and visual information for various multi-modal applications, whereas few OOD detection methods take into account information from the text modality. In this paper, we propose a novel post hoc OOD detection method, called NegLabel, which takes a vast number of negative labels from extensive corpus databases. We design a novel scheme for the OOD score collaborated with negative labels. Theoretical analysis helps to understand the mechanism of negative labels. Extensive experiments demonstrate that our method NegLabel achieves state-of-the-art performance on various OOD detection benchmarks and generalizes well on multiple VLM architectures. Furthermore, our method NegLabel exhibits remarkable robustness against diverse domain shifts. The codes are available at https://github.com/tmlr-group/NegLabel.

Emotion recognition aims to discern the emotional state of subjects within an image, relying on subject-centric and contextual visual cues. Current approaches typically follow a two-stage pipeline: first localize subjects by off-the-shelf detectors, then perform emotion classification through the late fusion of subject and context features. However, the complicated paradigm suffers from disjoint training stages and limited fine-grained interaction between subject-context elements. To address the challenge, we present a single-stage emotion recognition approach, employing a Decoupled Subject-Context Transformer (DSCT), for simultaneous subject localization and emotion classification. Rather than compartmentalizing training stages, we jointly leverage box and emotion signals as supervision to enrich subject-centric feature learning. Furthermore, we introduce DSCT to facilitate interactions between fine-grained subject-context cues in a ''decouple-then-fuse'' manner. The decoupled query tokens-subject queries and context queries-gradually intertwine across layers within DSCT, during which spatial and semantic relations are exploited and aggregated. We evaluate our single-stage framework on two widely used context-aware emotion recognition datasets, CAER-S and EMOTIC. Our approach surpasses two-stage alternatives with fewer parameter numbers, achieving a 3.39% accuracy improvement and a 6.46% average precision gain on CAER-S and EMOTIC datasets, respectively. Code and models are available at: https://github.com/Sampson-Lee/DSCT.

Large language models (LLMs) have shown impressive performance on downstream tasks by in-context learning (ICL), which heavily relies on the quality of demonstrations selected from a large set of annotated examples. Recent works claim that in-context learning is robust to noisy demonstrations in text classification. In this work, we show that, on text generation tasks, noisy annotations significantly hurt the performance of in-context learning. To circumvent the issue, we propose a simple and effective approach called Local Perplexity Ranking (LPR), which replaces the "noisy" candidates with their nearest neighbors that are more likely to be clean. Our method is motivated by analyzing the perplexity deviation caused by noisy labels and decomposing perplexity into inherent perplexity and matching perplexity. Our key idea behind LPR is thus to decouple the matching perplexity by performing the ranking among the neighbors in semantic space. Our approach can prevent the selected demonstrations from including mismatched input-label pairs while preserving the effectiveness of the original selection methods. Extensive experiments demonstrate the effectiveness of LPR, improving the EM score by up to 18.75 on common benchmarks with noisy annotations.

Federated learning (FL) allows multiple clients to collaboratively learn a globally shared model through cycles of model aggregation and local model training, without the need to share data. Most existing FL methods train local models separately on different clients, and then simply average their parameters to obtain a centralized model on the server side. However, these approaches generally suffer from large aggregation errors and severe local forgetting, which are particularly bad in heterogeneous data settings. To tackle these issues, in this paper, we propose a novel FL framework that uses online Laplace approximation to approximate posteriors on both the client and server side. On the server side, a multivariate Gaussian product mechanism is employed to construct and maximize a global posterior, largely reducing the aggregation errors induced by large discrepancies between local models. On the client side, a prior loss that uses the global posterior probabilistic parameters delivered from the server is designed to guide the local training. Binding such learning constraints from other clients enables our method to mitigate local forgetting. Finally, we achieve state-of-the-art results on several benchmarks, clearly demonstrating the advantages of the proposed method.

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.

Despite recent progress, Video Object Segmentation (VOS) remains challenging in complex situations such as low light and dark scenes. In this paper, we tackle the visibility limitations by introducing thermal information as auxillary for VOS. Specifically, we generate a hybrid benchmark dataset for Visible-Thermal VOS, named VisT300, which contains 300 challenging videos with visible light and thermal frames and corresponding object mask annotations. Besides, a Visible-Thermal integration Network, named as VTiNet, is proposed to use both cross-modal and cross-frame propagation for accurate video object segmentation. It is advantageous in two aspects: 1) effective cross-modal feature fusion and propagation for strong expressions on visible, thermal, and fused modalities; 2) effective modality-sensitive memory bank enables preserving the most valuable historical contexts in each modality. Extensive experiments demonstrate our VTiNet outperforms the state-of-the-art VOS works by a large margin (over 5% than RGB SotAs in Mean J&F). Our preliminary research clearly recovers that importing complementary modalities can effectively increase the strength of models to achieve robust segmentation in challenging scenarios. Data and code are released at https://github.com/yjybuaa/vtinet, and we hope this work will promote the progress of visible-thermal VOS.

Image anomaly detection (IAD) is an emerging and vital computer vision task in industrial manufacturing (IM). Recently, many advanced algorithms have been reported, but their performance deviates considerably with various IM settings. We realize that the lack of a uniform IM benchmark is hindering the development and usage of IAD methods in real-world applications. In addition, it is difficult for researchers to analyze IAD algorithms without a uniform benchmark. To solve this problem, we propose a uniform IM benchmark, for the first time, to assess how well these algorithms perform, which includes various levels of supervision (unsupervised versus fully supervised), learning paradigms (few-shot, continual and noisy label), and efficiency (memory usage and inference speed). Then, we construct a comprehensive IAD benchmark (IM-IAD), which includes 19 algorithms on seven major datasets with a uniform setting. Extensive experiments (17 017 total) on IM-IAD provide in-depth insights into IAD algorithm redesign or selection. Moreover, the proposed IM-IAD benchmark challenges existing algorithms and suggests future research directions. For reproducibility and accessibility, the source code is uploaded to the website: https://github.com/M-3LAB/open-iad.

Video inpainting gains an increasing amount of attention ascribed to its wide applications in intelligent video editing. However, despite tremendous progress made in RGB video inpainting, the existing RGB-D video inpainting models are still incompetent to inpaint real-world RGB-D videos, as they simply fuse color and depth via explicit feature concatenation, neglecting the natural modality gap. Moreover, current RGB-D video inpainting datasets are synthesized with homogeneous and delusive RGB-D data, which is far from real-world application and cannot provide comprehensive evaluation. To alleviate these problems and achieve real-world RGB-D video inpainting, on one hand, we propose a Mutually-guided Color and Depth Inpainting Network (MCD-Net), where color and depth are reciprocally leveraged to inpaint each other implicitly, mitigating the modality gap and fully exploiting cross-modal association for inpainting. On the other hand, we build a Video Inpainting with Depth (VID) dataset to supply diverse and authentic RGB-D video data with various object annotation masks to enable comprehensive evaluation for RGB-D video inpainting under real-world scenes. Experimental results on the DynaFill benchmark and our collected VID dataset demonstrate our MCD-Net not only yields the state-of-the-art quantitative performance but successfully achieves high-quality RGB-D video inpainting under real-world scenes. All resources are available at https://github.com/JCATCV/MCD-Net.

Depth information opens up new opportunities for video object segmentation (VOS) to be more accurate and robust in complex scenes. However, the RGBD VOS task is largely unexplored due to the expensive collection of RGBD data and time-consuming annotation of segmentation. In this work, we first introduce a new benchmark for RGBD VOS, named DepthVOS, which contains 350 videos (over 55k frames in total) annotated with masks and bounding boxes. We futher propose a novel, strong baseline model - Fused Color-Depth Network (FusedCDNet), which can be trained solely under the supervision of bounding boxes, while being used to generate masks with a bounding box guideline only in the first frame. Thereby, the model possesses three major advantages: a weakly-supervised training strategy to overcome the high-cost annotation, a cross-modal fusion module to handle complex scenes, and weakly-supervised inference to promote ease of use. Extensive experiments demonstrate that our proposed method performs on par with top fully-supervised algorithms. We will open-source our project on https://github.com/yjybuaa/depthvos/ to facilitate the development of RGBD VOS.

Continual learning is a research field of artificial neural networks to simulate human lifelong learning ability. Although a surge of investigations has achieved considerable performance, most rely only on image modality for incremental image recognition tasks. In this paper, we propose a novel yet effective framework coined cross-modal Alternating Learning with Task-Aware representations (ALTA) to make good use of visual and linguistic modal information and achieve more effective continual learning. To do so, ALTA presents a cross-modal joint learning mechanism that leverages simultaneous learning of image and text representations to provide more effective supervision. And it mitigates forgetting by endowing task-aware representations with continual learning capability. Concurrently, considering the dilemma of stability and plasticity, ALTA proposes a cross-modal alternating learning strategy that alternately learns the task-aware cross-modal representations to match the image-text pairs between tasks better, further enhancing the ability of continual learning. We conduct extensive experiments under various popular image classification benchmarks to demonstrate that our approach achieves state-of-the-art performance. At the same time, systematic ablation studies and visualization analyses validate the effectiveness and rationality of our method. Our code will be available upon publication.

Variable selection methods aim to select the key covariates related to the response variable for learning problems with high-dimensional data. Typical methods of variable selection are formulated in terms of sparse mean regression with a parametric hypothesis class, such as linear functions or additive functions. Despite rapid progress, the existing methods depend heavily on the chosen parametric function class and are incapable of handling variable selection for problems where the data noise is heavy-tailed or skewed. To circumvent these drawbacks, we propose sparse gradient learning with the mode-induced loss (SGLML) for robust model-free (MF) variable selection. The theoretical analysis is established for SGLML on the upper bound of excess risk and the consistency of variable selection, which guarantees its ability for gradient estimation from the lens of gradient risk and informative variable identification under mild conditions. Experimental analysis on the simulated and real data demonstrates the competitive performance of our method over the previous gradient learning (GL) methods.

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.

Triplet learning, i.e. learning from triplet data, has attracted much attention in computer vision tasks with an extremely large number of categories, e.g., face recognition and person re-identification. Albeit with rapid progress in designing and applying triplet learning algorithms, there is a lacking study on the theoretical understanding of their generalization performance. To fill this gap, this paper investigates the generalization guarantees of triplet learning by leveraging the stability analysis. Specifically, we establish the first general high-probability generalization bound for the triplet learning algorithm satisfying the uniform stability, and then obtain the excess risk bounds of the order O(log(n)/(√n) ) for both stochastic gradient descent (SGD) and regularized risk minimization (RRM), where 2n is approximately equal to the number of training samples. Moreover, an optimistic generalization bound in expectation as fast as O(1/n) is derived for RRM in a low noise case via the on-average stability analysis. Finally, our results are applied to triplet metric learning to characterize its theoretical underpinning.

Figure skating scoring is challenging because it requires judging players’ technical moves as well as coordination with the background music. Most learning-based methods struggle for two reasons: 1) each move in figure skating changes quickly, hence simply applying traditional frame sampling will lose a lot of valuable information, especially in 3 to 5 minutes lasting videos; 2) prior methods rarely considered the critical audio-visual relationship in their models. Due to these reasons, we introduce a novel architecture, named Skating-Mixer. It extends the MLP framework into a multimodal fashion and effectively learns long-term representations through our designed memory recurrent unit (MRU). Aside from the model, we collected a high-quality audio-visual FS1000 dataset, which contains over 1000 videos on 8 types of programs with 7 different rating metrics, overtaking other datasets in both quantity and diversity. Experiments show the proposed method achieves SOTAs over all major metrics on the public Fis-V and our FS1000 dataset. In addition, we include an analysis applying our method to the recent competitions in Beijing 2022 Winter Olympic Games, proving our method has strong applicability.

Existing audio-visual event localization (AVE) handles manually trimmed videos with only a single instance in each of them. However, this setting is unrealistic as natural videos often contain numerous audio-visual events with different categories. To better adapt to real-life applications, in this paper we focus on the task of dense-localizing audio-visual events, which aims to jointly localize and recognize all audio-visual events occurring in an untrimmed video. The problem is challenging as it requires fine-grained audio-visual scene and context understanding. To tackle this problem, we introduce the first Untrimmed Audio-Visual (UnAV-J 00) dataset, which contains 10K untrimmed videos with over 30K audio-visual events. Each video has 2.8 audio-visual events on average, and the events are usually related to each other and might co-occur as in real-life scenes. Next, we formulate the task using a new learning-based framework, which is capable of fully integrating audio and visual modalities to localize audio-visual events with various lengths and capture dependencies between them in a single pass. Extensive experiments demonstrate the effectiveness of our method as well as the significance of multi-scale cross-modal perception and dependency modeling for this task. The dataset and code are available at https://unav100.github.io.

The state of the arts in vision-language pretraining (VLP) achieves exemplary performance but suffers from high training costs resulting from slow convergence and long training time, especially on large-scale web datasets. An essential obstacle to training efficiency lies in the entangled prediction rate (percentage of tokens for reconstruction) and corruption rate (percentage of corrupted tokens) in masked language modeling (MLM), that is, a proper corruption rate is achieved at the cost of a large portion of output tokens being excluded from prediction loss. To accelerate the convergence of VLP, we propose a new pretraining task, namely, free language modeling (FLM), that enables a 100% prediction rate with arbitrary corruption rates. FLM successfully frees the prediction rate from the tie-up with the corruption rate while allowing the corruption spans to be customized for each token to be predicted. FLM-trained models are encouraged to learn better and faster given the same GPU time by exploiting bidirectional contexts more flexibly. Extensive experiments show FLM could achieve an impressive 2.5 × pretraining time reduction in comparison to the MLM-based methods, while keeping competitive performance on both vision-language understanding and generation tasks. Code will be public at https://github.com/TencentARC/FLM.

Aerial robots are now able to fly in complex environments, and drone-captured data gains lots of attention in object tracking. However, current research on aerial perception has mainly focused on limited categories, such as pedestrian or vehicle, and most scenes are captured in urban environments from a birds-eye view. Recently, UAVs equipped with depth cameras have been also deployed for more complex applications, while RGBD aerial tracking is still unexplored. Compared with traditional RGB object tracking, adding depth information can more effectively deal with more challenging scenes such as target and background interference. To this end, in this paper, we explore RGBD aerial tracking in an overhead space, which can greatly enlarge the development of drone-based visual perception. To boost the research, we first propose a large-scale benchmark for RGBD aerial tracking, containing 1,000 drone-captured RGBD videos with dense annotations. Then, as drone-based applications require for real-time processing with limited computational resources, we also propose an efficient RGBD tracker named EMT. Our tracker runs at over 100 fps on GPU, and 25 fps on the edge platform of NVidia Jetson NX Xavier, benefiting from its efficient multimodal fusion and feature matching. Extensive experiments show that our EMT achieves promising tracking performance. All resources are available at https://github.com/yjybuaa/RGBDAerialTracking.

Image-to-text generation aims to describe images using natural language. Recently, zero-shot image captioning based on pre-trained vision-language models (VLMs) and large language models (LLMs) has made significant progress. However, we have observed and empirically demonstrated that these methods are susceptible to modality bias induced by LLMs and tend to generate descriptions containing objects (entities) that do not actually exist in the image but frequently appear during training (i.e., object hallucination). In this paper, we propose ViECap, a transferable decoding model that leverages entity-aware decoding to generate descriptions in both seen and unseen scenarios. ViECap incorporates entity-aware hard prompts to guide LLMs’ attention toward the visual entities present in the image, enabling coherent caption generation across diverse scenes. With entity-aware hard prompts, ViECap is capable of maintaining performance when transferring from in-domain to out-of-domain scenarios. Extensive experiments demonstrate that ViECap sets a new state-of-the-art cross-domain (transferable) captioning and performs competitively in-domain captioning compared to previous VLMs-based zero-shot methods. Our code is available at: https://github.com/FeiElysia/ViECap

Pre-trained vision-language models, e.g., CLIP, working with manually designed prompts have demonstrated great capacity of transfer learning. Recently, learnable prompts achieve state-of-the-art performance, which however are prone to overfit to seen classes, failing to generalize to unseen classes. In this paper, we propose a Knowledge-Aware Prompt Tuning (KAPT) framework for vision-language models. Our approach takes the inspiration from human intelligence in which external knowledge is usually incorporated into recognizing novel categories of objects. Specifically, we design two complementary types of knowledge-aware prompts for the text encoder to leverage the distinctive characteristics of category-related external knowledge. The discrete prompt extracts the key information from descriptions of an object category, and the learned continuous prompt captures overall contexts. We further design an adaptation head for the visual encoder to aggregate salient attentive visual cues, which establishes discriminative and task-aware visual representations. We conduct extensive experiments on 11 widely-used benchmark datasets and the results verify the effectiveness in few-shot image classification, especially in generalizing to unseen categories. Compared with the state-of-the-art CoCoOp method, KAPT exhibits favorable performance and achieves an absolute gain of 3.22% on new classes and 2.57% in terms of harmonic mean.

Referring video object segmentation (RVOS), as a supervised learning task, relies on sufficient annotated data for a given scene. However, in more realistic scenarios, only minimal annotations are available for a new scene, which poses significant challenges to existing RVOS methods. With this in mind, we propose a simple yet effective model with a newly designed cross-modal affinity (CMA) module based on a Transformer architecture. The CMA module builds multimodal affinity with a few samples, thus quickly learning new semantic information, and enabling the model to adapt to different scenarios. Since the proposed method targets limited samples for new scenes, we generalize the problem as - few-shot referring video object segmentation (FS-RVOS). To foster research in this direction, we build up a new FS-RVOS benchmark based on currently available datasets. The benchmark covers a wide range and includes multiple situations, which can maximally simulate real-world scenarios. Extensive experiments show that our model adapts well to different scenarios with only a few samples, reaching state-of-the-art performance on the benchmark. On Mini-Ref-YouTube-VOS, our model achieves an average performance of 53.1 ${\mathcal{J}}$ and 54.8 ${\mathcal{F}}$, which are 10% better than the baselines. Furthermore, we show impressive results of 77.7 ${\mathcal{J}}$ and 74.8 ${\mathcal{F}}$ on Mini-Ref-SAIL-VOS, which are significantly better than the baselines. Code is publicly available at https://github.com/hengliusky/Few_shot_RVOS.

Vision-language pre-training (VLP) models have shown vulnerability to adversarial examples in multimodal tasks. Furthermore, malicious adversaries can be deliberately transferred to attack other black-box models. However, existing work has mainly focused on investigating white-box attacks. In this paper, we present the first study to investigate the adversarial transferability of recent VLP models. We observe that existing methods exhibit much lower transferability, compared to the strong attack performance in white-box settings. The transferability degradation is partly caused by the under-utilization of cross-modal interactions. Particularly, unlike unimodal learning, VLP models rely heavily on cross-modal interactions and the multimodal alignments are many-to-many, e.g., an image can be described in various natural languages. To this end, we propose a highly transferable Set-level Guidance Attack (SGA) that thoroughly leverages modality interactions and incorporates alignment-preserving augmentation with cross-modal guidance. Experimental results demonstrate that SGA could generate adversarial examples that can strongly transfer across different VLP models on multiple downstream vision-language tasks. On image-text retrieval, SGA significantly enhances the attack success rate for transfer attacks from ALBEF to TCL by a large margin (at least 9.78% and up to 30.21%), compared to the state-of-the-art. Our code is available at https://github.com/Zoky-2020/SGA.

Given a pre-trained in-distribution (ID) model, the inference-time out-of-distribution (OOD) detection aims to recognize OOD data during the inference stage. However, some representative methods share an unproven assumption that the probability that OOD data belong to every ID class should be the same, i.e., these OOD-to-ID probabilities actually form a uniform distribution. In this paper, we show that this assumption makes the above methods incapable when the ID model is trained with class-imbalanced data.Fortunately, by analyzing the causal relations between ID/OOD classes and features, we identify several common scenarios where the OOD-to-ID probabilities should be the ID-class-prior distribution and propose two strategies to modify existing inference-time detection methods: 1) replace the uniform distribution with the ID-class-prior distribution if they explicitly use the uniform distribution; 2) otherwise, reweight their scores according to the similarity between the ID-class-prior distribution and the softmax outputs of the pre-trained model. Extensive experiments show that both strategies can improve the OOD detection performance when the ID model is pre-trained with imbalanced data, reflecting the importance of ID-class prior in OOD detection.

3D anomaly detection is an emerging and vital computer vision task in industrial manufacturing (IM). Recently many advanced algorithms have been published, but most of them cannot meet the needs of IM. There are several disadvantages: i) difficult to deploy on production lines since their algorithms heavily rely on large pretrained models; ii) hugely increase storage overhead due to overuse of memory banks; iii) the inference speed cannot be achieved in real-time. To overcome these issues, we propose an easy and deployment-friendly network (called EasyNet) without using pretrained models and memory banks: firstly, we design a multi-scale multi-modality feature encoder-decoder to accurately reconstruct the segmentation maps of anomalous regions and encourage the interaction between RGB images and depth images; secondly, we adopt a multi-modality anomaly segmentation network to achieve a precise anomaly map; thirdly, we propose an attention-based information entropy fusion module for feature fusion during inference, making it suitable for real-time deployment. Extensive experiments show that EasyNet achieves an anomaly detection AUROC of 92.6% without using pretrained models and memory banks. In addition, EasyNet is faster than existing methods, with a high frame rate of 94.55 FPS on a Tesla V100 GPU.

By integrating complementary information from RGB image and depth map, the ability of salient object detection (SOD) for complex and challenging scenes can be improved. In recent years, the important role of Convolutional Neural Networks (CNNs) in feature extraction and cross-modality interaction has been fully explored, but it is still insufficient in modeling global long-range dependencies of self-modality and cross-modality. To this end, we introduce CNNs-assisted Transformer architecture and propose a novel RGB-D SOD network with Point-aware Interaction and CNN-induced Refinement (PICR-Net). On the one hand, considering the prior correlation between RGB modality and depth modality, an attention-triggered cross-modality point-aware interaction (CmPI) module is designed to explore the feature interaction of different modalities with positional constraints. On the other hand, in order to alleviate the block effect and detail destruction problems brought by the Transformer naturally, we design a CNN-induced refinement (CNNR) unit for content refinement and supplementation. Extensive experiments on five RGB-D SOD datasets show that the proposed network achieves competitive results in both quantitative and qualitative comparisons. Our code is publicly available at: https://github.com/rmcong/PICR-Net_ACMMM23.

Camouflaged Object Detection (COD) aims to identify and segment objects that blend into their surroundings. Since the color and texture of the camouflaged objects are extremely similar to the surrounding environment, it is super challenging for vision models to precisely detect them. Inspired by research on biology and evolution, we introduce depth information as an additional cue to help break camouflage, which can provide spatial information and texture-free separation for foreground and background. To dig clues of camouflaged objects in both RGB and depth modalities, we innovatively propose Depth-aided Camouflaged Object Detection (DaCOD), which involves two key components. We firstly propose the Multi-modal Collaborative Learning (MCL) module, which aims to collaboratively learning deep features from both RGB and depth channels via a hybrid backbone. Then, we propose a novel Cross-modal Asymmetric Fusion (CAF) strategy, which asymmetrically fuse RGB and depth information for complementary depth feature enhancement to produce accurate predictions. We conducted numerous experiments of the proposed DaCOD on three widely-used challenging COD benchmark datasets, in which DaCOD outperforms the current state-of-the-arts by a large margin. All resources are available at https://github.com/qingwei-wang/DaCOD.

High-precision point cloud anomaly detection is the gold standard for identifying the defects of advancing machining and precision manufacturing. Despite some methodological advances in this area, the scarcity of datasets and the lack of a systematic benchmark hinder its development. We introduce Real3D-AD, a challenging high-precision point cloud anomaly detection dataset, addressing the limitations in the field. With 1,254 high-resolution 3D items (from forty thousand to millions of points for each item), Real3D-AD is the largest dataset for high-precision 3D industrial anomaly detection to date. Real3D-AD surpasses existing 3D anomaly detection datasets available in terms of point cloud resolution (0.0010mm-0.0015mm), $360^{\circ}$ degree coverage and perfect prototype. Additionally, we present a comprehensive benchmark for Real3D-AD, revealing the absence of baseline methods for high-precision point cloud anomaly detection. To address this, we propose Reg3D-AD, a registration-based 3D anomaly detection method incorporating a novel feature memory bank that preserves local and global representations. Extensive experiments on the Real3D-AD dataset highlight the effectiveness of Reg3D-AD. For reproducibility and accessibility, we provide the Real3D-AD dataset, benchmark source code, and Reg3D-AD on our website: https://github.com/M-3LAB/Real3D-AD.

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.

Recent years have witnessed the prevalence of memory-based methods for Semi-supervised Video Object Segmentation (SVOS) which utilise past frames efficiently for label propagation. When conducting feature matching, fine-grained multi-scale feature matching has typically been performed using all query points, which inevitably results in redundant computations and thus makes the fusion of multi-scale results ineffective. In this paper, we develop a new Point-based Memory Network, termed as PMNet, to perform fine-grained feature matching on hard samples only, assuming that easy samples can already obtain satisfactory matching results without the need for complicated multi-scale feature matching. Our approach first generates an uncertainty map from the initial decoding outputs. Next, the fine-grained features at uncertain locations are sampled to match the memory features on the same scale. Finally, the matching results are further decoded to provide a refined output. The point-based scheme works with the coarsest feature matching in a complementary and efficient manner. Furthermore, we propose an approach to adaptively perform global or regional matching based on the motion history of memory points, making our method more robust against ambiguous backgrounds. Experimental results on several benchmark datasets demonstrate the superiority of our proposed method over state-of-the-art methods.

Referring Video Object Segmentation (RVOS) aims to segment the text-depicted object from video sequences. With excellent capabilities in long-range modelling and information interaction, transformers have been increasingly applied in existing RVOS architectures. To better leverage multimodal data, most efforts focus on the interaction between visual and textual features. However, they ignore the syntactic structures of the text during the interaction, where all textual components are intertwined, resulting in ambiguous vision-language alignment. In this paper, we improve the multimodal interaction by DECOUPLING the interweave. Specifically, we train a lightweight subject perceptron, which extracts the subject part from the input text. Then, the subject and text features are fed into two parallel branches to interact with visual features. This enables us to perform subject-aware and context-aware interactions, respectively, thus encouraging more explicit and discriminative feature embedding and alignment. Moreover, we find the decoupled architecture also facilitates incorporating the vision-language pre-trained alignment into RVOS, further improving the segmentation performance. Experimental results on all RVOS benchmark datasets demonstrate the superiority of our proposed method over the state-of-the-arts. The code of our method is available at:https://github.com/gaomingqi/dmformer.

Existing methods for video-based person re- identification (ReID) mainly learn the appearance feature of a given pedestrian via a feature extractor and a feature aggregator. However, the appearance models would fail to learn a large inter-class variance when different pedestrians have similar appearances. Considering that different pedestrians have different walking postures and body proportions, we propose to learn the discriminative pose feature beyond the appearance feature for video retrieval. Specifically, we implement a two-branch architecture to separately learn the appearance feature and pose feature, and then concatenate them together for inference. To learn the pose feature, we first detect the pedestrian pose in each frame through an off-the-shelf pose detector, and construct a temporal graph using the pose sequence. We then exploit a recurrent graph convolutional network (RGCN) to learn the node embeddings of the temporal pose graph, which devises a global information propagation mechanism to simultaneously achieve the neighborhood aggregation of intra-frame nodes and message passing among inter-frame graphs. Finally, we propose a dual-attention method (DAM) consisting of node-attention and time-attention to obtain the temporal graph representation from the node embeddings, where the self-attention mechanism is employed to learn the importance of each node and each frame. We verify the proposed method on three video-based ReID datasets, i.e., Mars, DukeMTMC and iLIDS-VID, whose experimental results demonstrate that the learned pose feature can effectively improve the performance of existing appearance models.

In recent years, RGB-T salient object detection (SOD) has attracted continuous attention, which makes it possible to identify salient objects in environments such as low light by introducing thermal image. However, most of the existing RGB-T SOD models focus on how to perform cross-modality feature fusion, ignoring whether thermal image is really always matter in SOD task. Starting from the definition and nature of this task, this paper rethinks the connotation of thermal modality, and proposes a network named TNet to solve the RGB-T SOD task. In this paper, we introduce a global illumination estimation module to predict the global illuminance score of the image, so as to regulate the role played by the two modalities. In addition, considering the role of thermal modality, we set up different cross-modality interaction mechanisms in the encoding phase and the decoding phase. On the one hand, we introduce a semantic constraint provider to enrich the semantics of thermal images in the encoding phase, which makes thermal modality more suitable for the SOD task. On the other hand, we introduce a two-stage localization and complementation module in the decoding phase to transfer object localization cue and internal integrity cue in thermal features to the RGB modality. Extensive experiments on three datasets show that the proposed TNet achieves competitive performance compared with 20 state-of-the-art methods.

Describing a video using natural language is an inherently one-to-many translation task. To generate diverse captions, existing VAE-based generative models typically learn factorized latent codes via one-stage training merely from stand-alone video-caption pairs. However, such a paradigm neglects set-level relationships among captions from the same video, not fully capturing the underlying multimodality of the generative process. To overcome this shortcoming, we leverage neighbouring descriptions for the same video that are articulated with noticeable topics and language variations (i.e., paraphrases). To this end, we propose a novel progressive training method by decomposing the learning of latent variables into two stages that are topic-oriented and paraphrase-oriented, respectively. Specifically, the model learns from divergent topic sentences obtained by semantic-based clustering in the first stage. It is then trained again through paraphrases with a cluster-aware adaptive regularization, allowing more intra-cluster variations. Furthermore, we introduce an overall metric DAUM, aDiversity-AccuracyUnifiedMetric to consider both the precision of the generated caption set and its coverage on the reference set, which has proved to have a higher correlation with human judgment than previous precision-only metrics. Extensive experiments on three large-scale video datasets show that the proposed training strategy can achieve superior performance in terms of accuracy, diversity, and DAUM over several baselines.

Person image generation conditioned on natural language allows us to personalize image editing in a user-friendly manner. This fashion, however, involves different granularities of semantic relevance between texts and visual content. Given a sentence describing an unknown person, we propose a novel pose-guided multi-granularity attention architecture to synthesize the person image in an end-to-end manner. To determine what content to draw at a global outline, the sentence-level description and pose feature maps are incorporated into a U-Net architecture to generate a coarse person image. To further enhance the fine-grained details, we propose to draw the human body parts with highly correlated textual nouns and determine the spatial positions with respect to target pose points. Our model is premised on a conditional generative adversarial network (GAN) that translates language description into a realistic person image. The proposed model is coupled with two-stream discriminators: 1) text-relevant local discriminators to improve the fine-grained appearance by identifying the region-text correspondences at the finer manipulation and 2) a global full-body discriminator to regulate the generation via a pose-weighting feature selection. Extensive experiments conducted on benchmarks validate the superiority of our method for person image generation.

Invariance to diverse types of image corruption, such as noise, blurring, or colour shifts, is essential to establish robust models in computer vision. Data augmentation has been the major approach in improving the robustness against common corruptions. However, the samples produced by popular augmentation strategies deviate significantly from the underlying data manifold. As a result, performance is skewed toward certain types of corruption. To address this issue, we propose a multi-source vicinal transfer augmentation (VITA) method for generating diverse on-manifold samples. The proposed VITA consists of two complementary parts: tangent transfer and integration of multi-source vicinal samples. The tangent transfer creates initial augmented samples for improving corruption robustness. The integration employs a generative model to characterize the underlying manifold built by vicinal samples, facilitating the generation of on-manifold samples. Our proposed VITA significantly outperforms the current state-of-the-art augmentation methods, demonstrated in extensive experiments on corruption benchmarks.

Semi-supervised learning is a challenging problem which aims to construct a model by learning from limited labeled examples. Numerous methods for this task focus on utilizing the predictions of unlabeled instances consistency alone to regularize networks. However, treating labeled and unlabeled data separately often leads to the discarding of mass prior knowledge learned from the labeled examples. In this paper, we propose a novel method for semi-supervised semantic segmentation named GuidedMix-Net, by leveraging labeled information to guide the learning of unlabeled instances. Specifically, GuidedMix-Net employs three operations: 1) interpolation of similar labeled-unlabeled image pairs; 2) transfer of mutual information; 3) generalization of pseudo masks. It enables segmentation models can learning the higher-quality pseudo masks of unlabeled data by transfer the knowledge from labeled samples to unlabeled data. Along with supervised learning for labeled data, the prediction of unlabeled data is jointly learned with the generated pseudo masks from the mixed data. Extensive experiments on PASCAL VOC 2012, and Cityscapes demonstrate the effectiveness of our GuidedMix-Net, which achieves competitive segmentation accuracy and significantly improves the mIoU over 7$\%$ compared to previous approaches.

Recently, the scheme of model-X knockoffs was proposed as a promising solution to address controlled feature selection under high-dimensional finite-sample settings. However, the procedure of model-X knockoffs depends heavily on the coefficient-based feature importance and only concerns the control of false discovery rate (FDR). To further improve its adaptivity and flexibility, in this paper, we propose an error-based knockoff inference method by integrating the knockoff features, the error-based feature importance statistics, and the stepdown procedure together. The proposed inference procedure does not require specifying a regression model and can handle feature selection with theoretical guarantees on controlling false discovery proportion (FDP), FDR, or k-familywise error rate (k-FWER). Empirical evaluations demonstrate the competitive performance of our approach on both simulated and real data.

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.

Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization. However, its training procedure suffers from confirmation bias due to the noise contained in self-generated artificial labels. Moreover, the model's judgment becomes noisier in real-world applications with extensive out-of-distribution data. To address this issue, we propose a general method named Class-aware Contrastive Semi-Supervised Learning (CCSSL), which is a drop-in helper to improve the pseudo-label quality and enhance the model's robustness in the real-world setting. Rather than treating real-world data as a union set, our method separately handles reliable in-distribution data with class-wise clustering for blending into downstream tasks and noisy out-of-distribution data with image-wise contrastive for better generalization. Furthermore, by applying target reweighting, we successfully emphasize clean label learning and simultaneously reduce noisy label learning. Despite its simplicity, our proposed CCSSL has significant performance improvements over the state-of-the-art SSL methods on the standard datasets CIFAR100 [18] and STL10 [8]. On the real-world dataset Semi-iNat 2021 [27], we improve FixMatch [25] by 9.80% and CoMatch [19] by 3.18%. Code is available https://github.com/TencentYoutuResearch/Classification-SemiCLS.

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.

Existing vision-language pre-training (VLP) methods primarily rely on paired image-text datasets, which are either annotated by enormous human labors or crawled from the internet followed by elaborate data cleaning techniques. To reduce the dependency on well-aligned image-text pairs, it is promising to directly leverage the large-scale text-only and image-only corpora. This paper proposes a data augmentation method, namely cross-modal CutMix (CMC), for implicit cross-modal alignment learning in unpaired VLP. Specifically, CMC transforms natural sentences in the textual view into a multi-modal view, where visually-grounded words in a sentence are randomly replaced by diverse image patches with similar semantics. There are several appealing proprieties of the proposed CMC. First, it enhances the data diversity while keeping the semantic meaning intact for tackling problems where the aligned data are scarce; Second, by attaching cross-modal noise on uni-modal data, it guides models to learn token-level interactions across modalities for better denoising. Furthermore, we present a new unpaired VLP method, dubbed as VLMixer, that integrates CMC with contrastive learning to pull together the uni-modal and multi-modal views for better instance-level alignments among different modalities. Extensive experiments on five downstream tasks show that VLMixer could surpass previous state-of-the-art unpaired VLP methods.

Anomaly detection (AD) has gained widespread attention due to its ability to identify defects in industrial scenarios using only normal samples. Although traditional AD methods achieved acceptable performance, they mainly focus on the current set of examples solely, leading to catastrophic forgetting of previously learned tasks when trained on a new one. Due to the limitation of flexibility and the requirements of realistic industrial scenarios, it is urgent to enhance the ability of continual adaptation of AD models. Therefore, this paper proposes a unified framework by incorporating continual learning (CL) to achieve our newly designed task of continual anomaly detection (CAD). Note that, we observe that data augmentation strategy can make AD methods well adapted to supervised CL (SCL) via constructing anomaly samples. Based on this, we hence propose a novel method named Distribution of Normal Embeddings (DNE), which utilizes the feature distribution of normal training samples from past tasks. It not only effectively alleviates catastrophic forgetting in CAD but also can be integrated with SCL methods to further improve their performance. Extensive experiments and visualization results on the popular benchmark dataset MVTec AD, have demonstrated advanced performance and the excellent continual adaption ability of our proposed method compared to other AD methods. To the best of our knowledge, we are the first to introduce and tackle the task of CAD. We believe that the proposed task and benchmark will be beneficial to the field of AD. Our code is available in thesupplementary material.

The existence of completely aligned and paired multi-modal neuroimaging data has proved its effectiveness in the diagnosis of brain diseases. However, collecting the full set of well-aligned and paired data is impractical, since the practical difficulties may include high cost, long time acquisition, image corruption, and privacy issues. Previously, the misaligned unpaired neuroimaging data (termed as MUD) are generally treated as noisy labels. However, such a noisy label-based method fails to accomplish well when misaligned data occurs distortions severely. For example, the angle of rotation is different. In this paper, we propose a novel federated self-supervised learning (FedMed) for brain image synthesis. An affine transform loss (ATL) was formulated to make use of severely distorted images without violating privacy legislation for the hospital. We then introduce a new data augmentation procedure for self-supervised training and fed it into three auxiliary heads, namely auxiliary rotation, auxiliary translation, and auxiliary scaling heads. The proposed method demonstrates the advanced performance in both the quality of our synthesized results under a severely misaligned and unpaired data setting, and better stability than other GAN-based algorithms. The proposed method also reduces the demand for deformable registration while encouraging to leverage the misaligned and unpaired data. Experimental results verify the outstanding performance of our learning paradigm compared to other state-of-the-art approaches.

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.

Although mainstream unsupervised anomaly detection (AD) algorithms perform well in academic datasets, their performance is limited in practical application due to the ideal experimental setting of clean training data. Training with noisy data is an inevitable problem in real-world anomaly detection but is seldom discussed. This paper considers label-level noise in image sensory anomaly detection for the first time. To solve this problem, we proposed a memory-based unsupervised AD method, SoftPatch, which efficiently denoises the data at the patch level. Noise discriminators are utilized to generate outlier scores for patch-level noise elimination before coreset construction. The scores are then stored in the memory bank to soften the anomaly detection boundary. Compared with existing methods, SoftPatch maintains a strong modeling ability of normal data and alleviates the overconfidence problem in coreset. Comprehensive experiments in various noise scenes demonstrate that SoftPatch outperforms the state-of-the-art AD methods on the MVTecAD and BTAD benchmarks and is comparable to those methods under the setting without noise.

Camouflaged object detection (COD) is an emerging visual detection task, which aims to locate and distinguish the disguised target in complex backgrounds by imitating the human visual detection system. Recently, COD has attracted increasing attention in computer vision, and a few models of camouflaged object detection have been successfully explored. However, most existing works primarily focus on modeling camouflaged object detection over in-depth analyzing existing COD structures. To the best of our knowledge, a systematic review for COD has not been publicly reported, especially for recently proposed deep learning-based COD models. To make up this vacancy, we firstly proposed a comprehensive review on both COD models and public benchmark datasets and provide potential directions for future COD studies. Specifically, we conduct a comprehensive summary of 39 existing COD models from 1998 to 2021. And then, to facilitate subsequent research on COD, we classify the existing structures into two categories, 27 traditional handcrafted feature-based structures and 12 structures based on deep learning. In addition, we further group traditional handcrafted feature-based structures into six sub-classes based on the detection mechanism: texture, color, motion, intensity, optical flow, and multi-modal fusion. Furthermore, we take an in-depth analysis of the deep learning-based structure based on both detection motivation and detection performance and evaluate the performance of each structure. Moreover, we sum up four widely used COD datasets and describe the details of each one. Finally, we also discuss the limitations of COD and the corresponding solutions to improve detection accuracy. We still mention the relevant applications of camouflaged object detection and its future research directions to promote the development of camouflaged object detection.

Cross-modal hashing that leverages hash functions to project high-dimensional data from different modalities into the compact common hamming space, has shown immeasurable potential in cross-modal retrieval. To ease labor costs, unsupervised cross-modal hashing methods are proposed. However, existing unsupervised methods still suffer from two factors in the optimization of hash functions: 1) similarity guidance, they barely give a clear definition of whether is similar or not between data points, leading to the residual of the redundant information; 2) optimization strategy, they ignore the fact that the similarity learning abilities of different hash functions are different, which makes the hash function of one modality weaker than the hash function of the other modality. To alleviate such limitations, this paper proposes an unsupervised cross-modal hashing method to train hash functions with discriminative similarity guidance and adaptively-enhanced optimization strategy, termed Deep Adaptively-Enhanced Hashing (DAEH). Specifically, to estimate the similarity relations with discriminability, Information Mixed Similarity Estimation (IMSE) is designed by integrating information from distance distributions and the similarity ratio. Moreover, Adaptive Teacher Guided Enhancement (ATGE) optimization strategy is also designed, which employs information theory to discover the weaker hash function and utilizes an extra teacher network to enhance it. Extensive experiments on three benchmark datasets demonstrate the superiority of the proposed DAEH against the state-of-the-arts.

Text-based person search aims at retrieving the target person in an image gallery using a descriptive sentence of that person. The core of this task is to calculate a similarity score between the pedestrian image and description, which requires inferring the complex latent correspondence between image sub-regions and textual phrases at different scales. Transformer is an intuitive way to model the complex alignment by its self-attention mechanism. Most previous Transformer-based methods simply concatenate image region features and text features as input and learn a cross-modal representation in a brute force manner. Such weakly supervised learning approaches fail to explicitly build alignment between image region features and text features, causing an inferior feature distribution. In this paper, we present CFLT, Conditional Feature Learning based Transformer. It maps the sub-regions and phrases into a unified latent space and explicitly aligns them by constructing conditional embeddings where the feature of data from one modality is dynamically adjusted based on the data from the other modality. The output of our CFLT is a set of similarity scores for each sub-region or phrase rather than a cross-modal representation. Furthermore, we propose a simple and effective multi-modal re-ranking method named Re-ranking scheme by Visual Conditional Feature (RVCF). Benefit from the visual conditional feature and better feature distribution in our CFLT, the proposed RVCF achieves significant performance improvement. Experimental results show that our CFLT outperforms the state-of-the-art methods by 7.03% in terms of top-1 accuracy and 5.01% in terms of top-5 accuracy on the text-based person search dataset.

Spatial-temporal relation reasoning is a significant yet challenging problem for video action recognition. Previous works typically apply local operations like 2D or 3D CNNs to conduct space-time interactions in video sequences, or simply capture space-time long-range relations of a single fixed scale. However, this is inadequate for obtaining a comprehensive action representation. Besides, most models treat all input frames equally for the final classification, without selecting key frames and motion-sensitive regions. This introduces irrelevant video content and hurts the performance of models. In this paper, we propose a generic Spatial-Temporal Pyramid Graph Network (STPG-Net) to adaptively capture long-range spatial-temporal relations in video sequences at multiple scales. Specifically, we design a temporal attention (TA) module and a spatial-temporal attention (STA) module to learn the contribution of each frame and each space-time region to an action at a feature level, respectively. We then apply the selected key information to build spatial-temporal pyramid graphs for long-range relation reasoning and more comprehensive action representation learning. STPG-Net can be flexibly integrated into 2D and 3D backbone networks in a plug-and-play manner. Extensive experiments show that it brings consistent improvements over many challenging baselines on several standard action recognition benchmarks (i.e., Something-Something V1 & V2, and FineGym), demonstrating the effectiveness of our approach.

Although Person Re-Identification has made impressive progress, difficult cases like occlusion, change of view-point, and similar clothing still bring great challenges. In order to tackle these challenges, extracting discriminative feature representation is crucial. Most of the existing methods focus on extracting ReID features from individual images separately. However, when matching two images, we propose that the ReID features of a query image should be dynamically adjusted based on the contextual information from the gallery image it matches. We call this type of ReID features conditional feature embedding. In this paper, we propose a novel ReID framework that extracts conditional feature embedding based on the aligned visual clues between image pairs, called Clue Alignment based Conditional Embedding (CACE-Net). CACE-Net applies an attention module to build a detailed correspondence graph between crucial visual clues in image pairs and uses discrepancy-based GCN to embed the obtained complex correspondence information into the conditional features. The experiments show that CACE-Net achieves state-of-the-art performance on three public datasets.

Domain generalization (DG) offers a preferable real-world setting for Person Re-Identification (Re-ID), which trains a model using multiple source domain datasets and expects it to perform well in an unseen target domain without any model updating. Unfortunately, most DG approaches are designed explicitly for classification tasks, which fundamentally differs from the retrieval task Re-ID. Moreover, existing applications of DG in Re-ID cannot correctly handle the massive variation among Re-ID datasets. In this paper, we identify two fundamental challenges in DG for Person Re-ID: domain-wise variations and identity-wise similarities. To this end, we propose an end-to-end Dual Distribution Alignment Network (DDAN) to learn domain-invariant features with dual-level constraints: the domain-wise adversarial feature learning and the identity-wise similarity enhancement. These constraints effectively reduce the domain-shift among multiple source domains further while agreeing to real-world scenarios. We evaluate our method in a large-scale DG Re-ID benchmark and compare it with various cutting-edge DG approaches. Quantitative results show that DDAN achieves state-of-the-art performance.

Existing methods of adversarial attacks successfully generate adversarial examples to confuse Deep Neural Networks (DNNs) of image classification and object detection, resulting in wrong predictions. However, these methods are difficult to attack models of video object tracking, because the tracking algorithms could handle sequential information across video frames and the categories of targets tracked are normally unknown in advance. In this paper, we propose a Unified and Effective Network, named UEN, to attack visual object tracking models. There are several appealing characteristics of UEN: (1) UEN could produce various invisible adversarial perturbations according to different attack settings by using only one simple end-to-end network with three ingenious loss function; (2) UEN could generate general visible adversarial patch patterns to attack the advanced trackers in the real-world; (3) Extensive experiments show that UEN is able to attack many state-of-the-art trackers effectively (e.g. SiamRPN-based networks and DiMP) on popular tracking datasets including OTB100, UAV123, and GOT10K, making online real-time attacks possible. The attack results outperform the introduced baseline in terms of attacking ability and attacking efficiency.

Fairness in machine learning is getting rising attention as it is directly related to real-world applications and social problems. Recent methods have been explored to alleviate the discrimination between certain demographic groups that are characterized by sensitive attributes (such as race, age, or gender). Some studies have found that the data itself is biased, so training directly on the data causes unfair decision making. Models directly trained on raw data can replicate or even exacerbate bias in the prediction between demographic groups. This leads to vastly different prediction performance in different demographic groups. In order to address this issue, we propose a new approach to improve machine learning fairness by generating fair data. We introduce a generative model to generate cross-domain samples w.r.t. multiple sensitive attributes. This ensures that we can generate infinite number of samples that are balanced \wrt both target label and sensitive attributes to enhance fair prediction. By training the classifier solely with the synthetic data and then transfer the model to real data, we can overcome the under-representation problem which is non-trivial since collecting real data is extremely time and resource consuming. We provide empirical evidence to demonstrate the benefit of our model with respect to both fairness and accuracy.

Current training objectives of existing person Re-IDentification (ReID) models only ensure that the loss of the model decreases on selected training batch, with no regards to the performance on samples outside the batch. It will inevitably cause the model to over-fit the data in the dominant position (e.g., head data in imbalanced class, easy samples or noisy samples). The latest resampling methods address the issue by designing specific criterion to select specific samples that trains the model generalize more on certain type of data (e.g., hard samples, tail data), which is not adaptive to the inconsistent real world ReID data distributions. Therefore, instead of simply presuming on what samples are generalizable, this paper proposes a one-for-more training objective that directly takes the generalization ability of selected samples as a loss function and learn a sampler to automatically select generalizable samples. More importantly, our proposed one-for-more based sampler can be seamlessly integrated into the ReID training framework which is able to simultaneously train ReID models and the sampler in an end-to-end fashion. The experimental results show that our method can effectively improve the ReID model training and boost the performance of ReID models.

It is well acknowledged that person re-identification (person ReID) highly relies on visual texture information like clothing. Despite significant progress has been made in recent years, texture-confusing situations like clothing changing and persons wearing the same clothes receive little attention from most existing ReID methods. In this paper, rather than relying on texture based information, we propose to improve the robustness of person ReID against clothing texture by exploiting the information of a person’s 3D shape. Existing shape learning schemas for person ReID either ignore the 3D information of a person, or require extra physical devices to collect 3D source data. Differently, we propose a novel ReID learning framework that directly extracts a texture-insensitive 3D shape embedding from a 2D image by adding 3D body reconstruction as an auxiliary task and regularization, called 3D Shape Learning (3DSL). The 3D reconstruction based regularization forces the ReID model to decouple the 3D shape information from the visual texture, and acquire discriminative 3D shape ReID features. To solve the problem of lacking 3D ground truth, we design an adversarial self-supervised projection (ASSP) model, performing 3D reconstruction without ground truth. Extensive experiments on common ReID datasets and texture-confusing datasets validate the effectiveness of our model.

Recent advances in neuroscience have highlighted the effectiveness of multi-modal medical data for investigating certain pathologies and understanding human cognition. However, obtaining full sets of different modalities is limited by various factors, such as long acquisition times, high examination costs and artifact suppression. In addition, the complexity, high dimensionality and heterogeneity of neuroimaging data remains another key challenge in leveraging existing randomized scans effectively, as data of the same modality is often measured differently by different machines. There is a clear need to go beyond the traditional imaging-dependent process and synthesize anatomically specific target-modality data from a source in-put. In this paper, we propose to learn dedicated features that cross both intre- and intra-modal variations using a novel CSCℓ4Net. Through an initial unification of intra-modal data in the feature maps and multivariate canonical adaptation, CSC ℓ4Net facilitates feature-level mutual transformation. The positive definite Riemannian manifold-penalized data fidelity term further enables CSCℓ4Net to re-construct missing measurements according to transformed features. Finally, the maximization ℓ4-norm boils down to a computationally efficient optimization problem. Extensive experiments validate the ability and robustness of our CSC ℓ4Net compared to the state-of-the-art methods on multiple datasets.

The Competition on Human Identification at a Distance 2021 (HID 2021) is to promote the research in human identification at a distance and to provide a benchmark to evaluate different methods. HID 2021 is the second follow-up from the first one, HID 2020. The dataset size and the evaluation protocal are the same with the previous competition, but the data in the test set has been changed. The paper firstly introduces the dataset and the evaluation protocol, then describes the methods from the top teams and their results. The methods show how to achieve state-of-the-art performance on gait recognition. The results in HID 2021 are better than those in HID 2020. From the comparisons and analysis, some useful conclusions can be drawn. We hope more improvements can be achieved by better followup competitions.

Generalized zero-shot learning (GZSL) has achieved significant progress, with many efforts dedicated to over-coming the problems of visual-semantic domain gap and seen-unseen bias. However, most existing methods directly use feature extraction models trained on ImageNet alone, ignoring the cross-dataset bias between ImageNet and GZSL benchmarks. Such a bias inevitably results in poor-quality visual features for GZSL tasks, which potentially limits the recognition performance on both seen and unseen classes. In this paper, we propose a simple yet effective GZSL method, termed feature refinement for generalized zero-shot learning (FREE), to tackle the above problem. FREE employs a feature refinement (FR) module that in-corporates semantic→visual mapping into a unified generative model to refine the visual features of seen and unseen class samples. Furthermore, we propose a self-adaptive margin center loss (SAMC-loss) that cooperates with a semantic cycle-consistency loss to guide FR to learn class- and semantically-relevant representations, and concatenate the features in FR to extract the fully refined features. Extensive experiments on five benchmark datasets demonstrate the significant performance gain of FREE over its baseline and current state-of-the-art methods. The code is available at https://github.com/shiming-chen/FREE.

Annotation burden has become one of the biggest barriers to semantic segmentation. Approaches based on click-level annotations have therefore attracted increasing attention due to their superior trade-off between supervision and annotation cost. In this paper, we propose seminar learning, a new learning paradigm for semantic segmentation with click-level supervision. The fundamental rationale of seminar learning is to leverage the knowledge from different networks to compensate for insufficient information provided in click-level annotations. Mimicking a seminar, our seminar learning involves a teacher-student and a student-student module, where a student can learn from both skillful teachers and other students. The teacher-student module uses a teacher network based on the exponential moving average to guide the training of the student network. In the student-student module, heterogeneous pseudo-labels are proposed to bridge the transfer of knowledge among students to enhance each other’s performance. Experimental results demonstrate the effectiveness of seminar learning, which achieves the new state-of-the-art performance of 72.51% (mIOU), surpassing previous methods by a large margin of up to 16.88% on the Pascal VOC 2012 dataset.

Dense video captioning aims to generate multiple associated captions with their temporal locations from the video. Previous methods follow a sophisticated "localizethen-describe" scheme, which heavily relies on numerous hand-crafted components. In this paper, we proposed a simple yet effective framework for end-to-end dense video captioning with parallel decoding (PDVC), by formulating the dense caption generation as a set prediction task. In practice, through stacking a newly proposed event counter on the top of a transformer decoder, the PDVC precisely segments the video into a number of event pieces under the holistic understanding of the video content, which effectively increases the coherence and readability of predicted captions. Compared with prior arts, the PDVC has several appealing advantages: (1) Without relying on heuristic non-maximum suppression or a recurrent event sequence selection network to remove redundancy, PDVC directly produces an event set with an appropriate size; (2) In contrast to adopting the two-stage scheme, we feed the enhanced representations of event queries into the localization head and caption head in parallel, making these two sub-tasks deeply interrelated and mutually promoted through the optimization; (3) Without bells and whistles, extensive experiments on ActivityNet Captions and YouCook2 show that PDVC is capable of producing high-quality captioning results, surpassing the state-of-the-art two-stage methods when its localization accuracy is on par with them. Code is available at https://github.com/ttengwang/PDVC.

RGBD (RGB plus depth) object tracking is gaining momentum as RGBD sensors have become popular in many application fields such as robotics. However, the best RGBD trackers are extensions of the state-of-the-art deep RGB trackers. They are trained with RGB data and the depth channel is used as a sidekick for subtleties such as occlusion detection. This can be explained by the fact that there are no sufficiently large RGBD datasets to 1) train "deep depth trackers" and to 2) challenge RGB trackers with sequences for which the depth cue is essential. This work introduces a new RGBD tracking dataset - Depth-Track - that has twice as many sequences (200) and scene types (40) than in the largest existing dataset, and three times more objects (90). In addition, the average length of the sequences (1473), the number of deformable objects (16) and the number of annotated tracking attributes (15) have been increased. Furthermore, by running the SotA RGB and RGBD trackers on DepthTrack, we propose a new RGBD tracking baseline, namely DeT, which reveals that deep RGBD tracking indeed benefits from genuine training data. The code and dataset is available at https://github.com/xiaozai/DeT.

Most existing trackers based on deep learning perform tracking in a holistic strategy, which aims to learn deep representations of the whole target for localizing the target. It is arduous for such methods to track targets with various appearance variations. To address this limitation, another type of methods adopts a part-based tracking strategy which divides the target into equal patches and tracks all these patches in parallel. The target state is inferred by summarizing the tracking results of these patches. A potential limitation of such trackers is that not all patches are equally informative for tracking. Some patches that are not discriminative may have adverse effects. In this paper, we propose to track the salient local parts of the target that are discriminative for tracking. In particular, we propose a fine-grained saliency mining module to capture the local saliencies. Further, we design a saliency-association modeling module to associate the captured saliencies together to learn effective correlation representations between the exemplar and the search image for state estimation. Extensive experiments on five diverse datasets demonstrate that the proposed method performs favorably against state-of-the-art trackers.

Zero-shot sketch-based image retrieval (ZS-SBIR), which aims to retrieve photos with sketches under the zero-shot scenario, has shown extraordinary talents in real-world applications. Most existing methods leverage language models to generate class-prototypes and use them to arrange the locations of all categories in the common space for photos and sketches. Although great progress has been made, few of them consider whether such pre-defined prototypes are necessary for ZS-SBIR, where locations of unseen class samples in the embedding space are actually determined by visual appearance and a visual embedding actually performs better. To this end, we propose a novel Norm-guided Adaptive Visual Embedding (NAVE) model, for adaptively building the common space based on visual similarity instead of language-based pre-defined prototypes. To further enhance the representation quality of unseen classes for both photo and sketch modality, modality norm discrepancy and noisy label regularizer are jointly employed to measure and repair the modality bias of the learned common embedding. Experiments on two challenging datasets demonstrate the superiority of our NAVE over state-of-the-art competitors.

Compared with tedious per-pixel mask annotating, it is much easier to annotate data by clicks, which costs only several seconds for an image. However, applying clicks to learn video semantic segmentation model has not been explored before. In this work, we propose an effective weakly-supervised video semantic segmentation pipeline with click annotations, called WeClick, for saving laborious annotating effort by segmenting an instance of the semantic class with only a single click. Since detailed semantic information is not captured by clicks, directly training with click labels leads to poor segmentation predictions. To mitigate this problem, we design a novel memory flow knowledge distillation strategy to exploit temporal information (named memory flow) in abundant unlabeled video frames, by distilling the neighboring predictions to the target frame via estimated motion. Moreover, we adopt vanilla knowledge distillation for model compression. In this case, WeClick learns compact video semantic segmentation models with the low-cost click annotations during the training phase yet achieves real-time and accurate models during the inference period. Experimental results on Cityscapes and Camvid show that WeClick outperforms the state-of-the-art methods, increases performance by 10.24% mIoU than baseline, and achieves real-time execution.

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.

Three-dimensional (3D) human pose estimation involves estimating the articulated 3D joint locations of a human body from an image or video. Due to its widespread applications in a great variety of areas, such as human motion analysis, human–computer interaction, robots, 3D human pose estimation has recently attracted increasing attention in the computer vision community, however, it is a challenging task due to depth ambiguities and the lack of in-the-wild datasets. A large number of approaches, with many based on deep learning, have been developed over the past decade, largely advancing the performance on existing benchmarks. To guide future development, a comprehensive literature review is highly desired in this area. However, existing surveys on 3D human pose estimation mainly focus on traditional methods and a comprehensive review on deep learning based methods remains lacking in the literature. In this paper, we provide a thorough review of existing deep learning based works for 3D pose estimation, summarize the advantages and disadvantages of these methods and provide an in-depth understanding of this area. Furthermore, we also explore the commonly-used benchmark datasets on which we conduct a comprehensive study for comparison and analysis. Our study sheds light on the state of research development in 3D human pose estimation and provides insights that can facilitate the future design of models and algorithms.

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.

Sparse additive models have been successfully applied to high-dimensional data analysis due to the flexibility and interpretability of their representation. However, the existing methods are often formulated using the least-squares loss with learning the conditional mean, which is sensitive to data with the non-Gaussian noises, e.g., skewed noise, heavy-tailed noise, and outliers. To tackle this problem, we propose a new robust regression method, called as sparse modal additive model (SpMAM), by integrating the modal regression metric, the data-dependent hypothesis space, and the weightedlq,1-norm regularizer (q ≥ 1) into the additive models. Specifically, the modal regression metric assures the model robustness to complex noises via learning the conditional mode, the data-dependent hypothesis space offers the model adaptivity via sample-based presentation, and thelq,1-norm regularizer addresses the algorithmic interpretability via sparse variable selection. In theory, the proposed SpMAM enjoys statistical guarantees on asymptotic consistency for regression estimation and variable selection simultaneously. Experimental results on both synthetic and real-world benchmark data sets validate the effectiveness and robustness of the proposed model.

Recently, the research interest of person re-identification (ReID) has gradually turned to video-based methods, which acquire a person representation by aggregating frame features of an entire video. However, existing video-based ReID methods do not consider the semantic difference brought by the outputs of different network stages, which potentially compromises the information richness of the person features. Furthermore, traditional methods ignore important relationship among frames, which causes information redundancy in fusion along the time axis. To address these issues, we propose a novel general temporal fusion framework to aggregate frame features on both semantic aspect and time aspect. As for the semantic aspect, a multi-stage fusion network is explored to fuse richer frame features at multiple semantic levels, which can effectively reduce the information loss caused by the traditional single-stage fusion. While, for the time axis, the existing intra-frame attention method is improved by adding a novel inter-frame attention module, which effectively reduces the information redundancy in temporal fusion by taking the relationship among frames into consideration. The experimental results show that our approach can effectively improve the video-based re-identification accuracy, achieving the state-of-the-art performance.

Although great progress in supervised person re-identification (Re-ID) has been made recently, due to the viewpoint variation of a person, Re-ID remains a massive visual challenge. Most existing viewpoint-based person Re-ID methods project images from each viewpoint into separated and unrelated sub-feature spaces. They only model the identity-level distribution inside an individual viewpoint but ignore the underlying relationship between different viewpoints. To address this problem, we propose a novel approach, called Viewpoint-Aware Loss with Angular Regularization (VA-reID). Instead of one subspace for each viewpoint, our method projects the feature from different viewpoints into a unified hypersphere and effectively models the feature distribution on both the identity-level and the viewpoint-level. In addition, rather than modeling different viewpoints as hard labels used for conventional viewpoint classification, we introduce viewpoint-aware adaptive label smoothing regularization (VALSR) that assigns the adaptive soft label to feature representation. VALSR can effectively solve the ambiguity of the viewpoint cluster label assignment. Extensive experiments on the Market1501 and DukeMTMC-reID datasets demonstrated that our method outperforms the state-of-the-art supervised Re-ID methods.

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.

Almost all adversarial attacks in computer vision are aimed at pre-known object categories, which could be offline trained for generating perturbations. But as for visual object tracking, the tracked target categories are normally unknown in advance. However, the tracking algorithms also have potential risks of being attacked, which could be maliciously used to fool the surveillance systems. Meanwhile, it is still a challenging task that adversarial attacks on tracking since it has the free-model tracked target. Therefore, to help draw more attention to the potential risks, we study adversarial attacks on tracking algorithms. In this paper, we propose a novel one-shot adversarial attack method to generate adversarial examples for free-model single object tracking, where merely adding slight perturbations on the target patch in the initial frame causes state-of-the-art trackers to lose the target in subsequent frames. Specifically, the optimization objective of the proposed attack consists of two components and leverages the dual attention mechanisms. The first component adopts a targeted attack strategy by optimizing the batch confidence loss with confidence attention while the second one applies a general perturbation strategy by optimizing the feature loss with channel attention. Experimental results show that our approach can significantly lower the accuracy of the most advanced Siamese network-based trackers on three benchmarks.

We investigate the emerging task of learning object detectors with sole image-level labels on the web without requiring any other supervision like precise annotations or additional images from well-annotated benchmark datasets. Such a task, termed as fully webly supervised object detection, is extremely challenging, since image-level labels on the web are always noisy, leading to poor performance of the learned detectors. In this work, we propose an end-to-end framework to jointly learn webly supervised detectors and reduce the negative impact of noisy labels. Such noise is heterogeneous, which is further categorized into two types, namely background noise and foreground noise. Regarding the background noise, we propose a residual learning structure incorporated with weakly supervised detection, which decomposes background noise and models clean data. To explicitly learn the residual feature between clean data and noisy labels, we further propose a spatially-sensitive entropy criterion, which exploits the conditional distribution of detection results to estimate the confidence of background categories being noise. Regarding the foreground noise, a bagging-mixup learning is introduced, which suppresses foreground noisy signals from incorrectly labelled images, whilst maintaining the diversity of training data. We evaluate the proposed approach on popular benchmark datasets by training detectors on web images, which are retrieved by the corresponding category tags from photo-sharing sites. Extensive experiments show that our method achieves significant improvements over the state-of-the-art methods.

Visual object tracking has made important breakthroughs with the assistance of deep learning models. Unfortunately, recent research has clearly proved that deep learning models are vulnerable to malicious adversarial attacks, which mislead the models making wrong decisions by perturbing the input image. The threat to the models alerts us to pay attention to the model security of deep learning- based tracking algorithms. Therefore, we study the adversarial attacks against advanced trackers based on deep learning to better identify the vulnerability of tracking algorithms. In this paper, we propose to add slight adversarial perturbations to the input image by an inconspicuous but powerful attack strategy-hijacking algorithm. Specifically, the hijacking strategy misleads trackers in two aspects: one is shape hijacking that changes the shape of the model output; the other is position hijacking that gradually pushes the output to any position in the image frame. Besides, we further propose an adaptive optimization approach to integrate two hijacking mechanisms efficiently. Eventually, the hijacking algorithm results in fooling the tracker to track the wrong target gradually. The experimental results demonstrate the powerful attack ability of our method-quickly hijacking state-of-the-art trackers and reducing the accuracy of these models by more than 90% on OTB2015.

Image super-resolution (SR) and image inpainting are two topical problems in medical image processing. Existing methods for solving the problems are either tailored to recovering a high-resolution version of the low-resolution image or focus on filling missing values, thus inevitably giving rise to poor performance when the acquisitions suffer from multiple degradations. In this paper, we explore the possibility of super-resolving and inpainting images to handle multiple degradations and therefore improve their usability. We construct a unified and scalable framework to overcome the drawbacks of propagated errors caused by independent learning. We additionally provide improvements over previously proposed super-resolution approaches by modeling image degradation directly from data observations rather than bicubic downsampling. To this end, we propose HLH-GAN, which includes a high-to-low (H-L) GAN together with a low-to-high (L-H) GAN in a cyclic pipeline for solving the medical image degradation problem. Our comparative evaluation demonstrates that the effectiveness of the proposed method on different brain MRI datasets. In addition, our method outperforms many existing super-resolution and inpainting approaches.

Zero-shot object detection (ZSD) has received considerable attention from the community of computer vision in recent years. It aims to simultaneously locate and categorize previously unseen objects during inference. One crucial problem of ZSD is how to accurately predict the label of each object proposal, i.e. categorizing object proposals, when conducting ZSD for unseen categories. Previous ZSD models generally relied on learning an embedding from visual space to semantic space or learning a joint embedding between semantic description and visual representation. As the features in the learned semantic space or the joint projected space tend to suffer from the hubness problem, namely the feature vectors are likely embedded to an area of incorrect labels, and thus it will lead to lower detection precision. In this paper, instead, we propose to learn a deep embedding from the semantic space to the visual space, which enables to well alleviate the hubness problem, because, compared with semantic space or joint embedding space, the distribution in visual space has smaller variance. After learning a deep embedding model, we perform $k$ nearest neighbor search in the visual space of unseen categories to determine the category of each semantic description. Extensive experiments on two public datasets show that our approach significantly outperforms the existing methods.

Zero-shot object detection aims to detect and recognize objects unobserved in training samples from images. Previous studies generally utilized concept names or textual descriptions to build relationships between seen and unseen classes. However, these works rarely exploited the valuable information in textual descriptions for optimizing the network. Actually, textual descriptions contain much valuable information related to categories. Exploiting this information can help training the network and improve the detection performance. Besides, textual descriptions usually contain the names of objects that need to be detected. By using this character, we can narrow the scope of candidate unseen categories, thus can improve the detection accuracy. In this regard, we propose a novel framework that incorporates both images and their text descriptions for zero-shot object detection. In particular, we employ text convolutional neural network (CNN) and Faster R-CNN to extract text features and image features respectively, and combine them to optimize the regions that contain objects in images and to classify those newly detected objects simultaneously. Besides, we try extracting potential object labels directly from textual descriptions and introducing online hard example mining (OHEM) to assist with object classification and network optimization. Our extensive experiments on two public datasets demonstrate the superior performance of our approach to state-of-the-art methods.

In this paper, we present a Large-Scale and high-diversity general Thermal InfraRed (TIR) Object Tracking Benchmark, called LSOTB-TIR, which consists of an evaluation dataset and a training dataset with a total of 1,400 TIR sequences and more than 600K frames. We annotate the bounding box of objects in every frame of all sequences and generate over 730K bounding boxes in total. To the best of our knowledge, LSOTB-TIR is the largest and most diverse TIR object tracking benchmark to date. To evaluate a tracker on different attributes, we define 4 scenario attributes and 12 challenge attributes in the evaluation dataset. By releasing LSOTB-TIR, we encourage the community to develop deep learning based TIR trackers and evaluate them fairly and comprehensively. We evaluate and analyze more than 30 trackers on LSOTB-TIR to provide a series of baselines, and the results show that deep trackers achieve promising performance. Furthermore, we re-train several representative deep trackers on LSOTB-TIR, and their results demonstrate that the proposed training dataset significantly improves the performance of deep TIR trackers. Codes and dataset are available at https://github.com/QiaoLiuHit/LSOTB-TIR.

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.

Additive models have attracted much attention for high-dimensional regression estimation and variable selection. However, the existing models are usually limited to the single-task learning framework under the mean squared error (MSE) criterion, where the utilization of variable structure depends heavily on priori knowledge among variables. For high-dimensional observations in real environment, e.g., Coronal Mass Ejections (CMEs) data, the learning performance of previous methods may be degraded seriously due to the complex non-Gaussian noise and the insufficiency of prior knowledge on variable structure. To tackle this problem, we propose a new class of additive models, called Multi-task Additive Models (MAM), by integrating the mode-induced metric, the structure-based regularizer, and additive hypothesis spaces into a bilevel optimization framework. Our approach does not require any priori knowledge of variable structure and suits for high-dimensional data with complex noise, e.g., skewed noise, heavy-tailed noise, and outliers. A smooth iterative optimization algorithm with convergence guarantees is provided to implement MAM efficiently. Experiments on simulations and the CMEs analysis demonstrate the competitive performance of our approach for robust estimation and automatic structure discovery.

The ability to synthesize multi-modality data is highly desirable for many computer-aided medical applications, e.g. clinical diagnosis and neuroscience research, since rich imaging cohorts offer diverse and complementary information unraveling human tissues. However, collecting acquisitions can be limited by adversary factors such as patient discomfort, expensive cost and scanner unavailability. In this paper, we propose a multi-task coherent modality transferable GAN (MCMT-GAN) to address this issue for brain MRI synthesis in an unsupervised manner. Through combining the bidirectional adversarial loss, cycle-consistency loss, domain adapted loss and manifold regularization in a volumetric space, MCMT-GAN is robust for multi-modality brain image synthesis with visually high fidelity. In addition, we complement discriminators collaboratively working with segmentors which ensure the usefulness of our results to segmentation task. Experiments evaluated on various cross-modality synthesis show that our method produces visually impressive results with substitutability for clinical post-processing and also exceeds the state-of-the-art methods.

Learning effective distance metric between data has gained increasing popularity, for its promising performance on various tasks, such as face verification, zero-shot learning, and image retrieval. A major line of researches employs hard data mining, which makes efforts on searching a subset of significant data. However, hard data mining based approaches only rely on a small percentage of data, which is apt to overfitting. This motivates us to propose a novel framework, named deep asymmetric metric learning via rich relationship mining (DAMLRRM), to mine rich relationship under satisfying sampling size. DAMLRRM constructs two asymmetric data streams that are differently structured and of unequal length. The asymmetric structure enables the two data streams to interlace each other, which allows for the informative comparison between new data pairs over iterations. To improve the generalization ability, we further relax the constraint on the intra-class relationship. Rather than greedily connecting all possible positive pairs, DAMLRRM builds a minimum-cost spanning tree within each category to ensure the formation of a connected region. As such there exists at least one direct or indirect path between arbitrary positive pairs to bridge intra-class relevance. Extensive experimental results on three benchmark datasets including CUB-200-2011, Cars196, and Stanford Online Products show that DAMLRRM effectively boosts the performance of existing deep metric learning approaches.

The clustering methods have recently absorbed even-increasing attention in learning and vision. Deep clustering combines embedding and clustering together to obtain optimal embedding subspace for clustering, which can be more effective compared with conventional clustering methods. In this paper, we propose a joint learning framework for discriminative embedding and spectral clustering. We first devise a dual autoencoder network, which enforces the reconstruction constraint for the latent representations and their noisy versions, to embed the inputs into a latent space for clustering. As such the learned latent representations can be more robust to noise. Then the mutual information estimation is utilized to provide more discriminative information from the inputs. Furthermore, a deep spectral clustering method is applied to embed the latent representations into the eigenspace and subsequently clusters them, which can fully exploit the relationship between inputs to achieve optimal clustering results. Experimental results on benchmark datasets show that our method can significantly outperform state-of-the-art clustering approaches.

Most existing Re-IDentification (Re-ID) methods are highly dependent on precise bounding boxes that enable images to be aligned with each other. However, due to the challenging practical scenarios, current detection models often produce inaccurate bounding boxes, which inevitably degenerate the performance of existing Re-ID algorithms. In this paper, we propose a novel coarse-to-fine pyramid model to relax the need of bounding boxes, which not only incorporates local and global information, but also integrates the gradual cues between them. The pyramid model is able to match at different scales and then search for the correct image of the same identity, even when the image pairs are not aligned. In addition, in order to learn discriminative identity representation, we explore a dynamic training scheme to seamlessly unify two losses and extract appropriate shared information between them. Experimental results clearly demonstrate that the proposed method achieves the state-of-the-art results on three datasets. Especially, our approach exceeds the current best method by 9.5% on the most challenging CUHK03 dataset.

Currently in object detection, deep learning based detectors are gaining their momentum. However, the supervision involved in the widely-used anchor paradigm within the detection pipeline is inadequate. Traditional object detectors opt for densely picking anchors to increase the training samples for faster convergence and better detection quality. However, dense anchor scheme requires extra computational budget which renders it infeasible for lightweight detectors. To address the problem, inspired by the cognitive consistency, we propose a novel Particle Swarm Loss for lightweight object detection. Experiments upon the MS-COCO challenge show that detectors compensated by PS loss can not only converge faster but also acquire better detection quality than their vanilla versions (YOLOv3 and SSD improves 2.0% and 2.5% on the harsh AP50respectively) without extra computational overhead. In addition, we propose a dapper backbone with high cost-efficiency for the resource-limited scenarios.

Recently, person re-identification (re-ID) has attracted increasing research attention, which has broad application prospects in video surveillance and beyond. To this end, most existing methods highly relied on well-aligned pedestrian images and hand-engineered part-based model on the coarsest feature map. In this paper, to lighten the restriction of such fixed and coarse input alignment, an end-to-end part power set model with multi-scale features is proposed, which captures the discriminative parts of pedestrians from global to local, and from coarse to fine, enabling part-based scale-free person re-ID. In particular, we first factorize the visual appearance by enumerating $k$-combinations for all $k$ of $n$ body parts to exploit rich global and partial information to learn discriminative feature maps. Then, a combination ranking module is introduced to guide the model training with all combinations of body parts, which alternates between ranking combinations and estimating an appearance model. To enable scale-free input, we further exploit the pyramid architecture of deep networks to construct multi-scale feature maps with a feasible amount of extra cost in term of memory and time. Extensive experiments on the mainstream evaluation datasets, including Market-1501, DukeMTMC-reID and CUHK03, validate that our method achieves the state-of-the-art performance.

Cross-modal hashing intends to project data from two modalities into a common hamming space to perform cross-modal retrieval efficiently. Despite satisfactory performance achieved on real applications, existing methods are incapable of effectively preserving semantic structure to maintain inter-class relationship and improving discriminability to make intra-class samples aggregated simultaneously, which thus limits the higher retrieval performance. To handle this problem, we propose Equally-Guided Discriminative Hashing (EGDH), which jointly takes into consideration semantic structure and discriminability. Specifically, we discover the connection between semantic structure preserving and discriminative methods. Based on it, we directly encode multi-label annotations that act as high-level semantic features to build a common semantic structure preserving classifier. With the common classifier to guide the learning of different modal hash functions equally, hash codes of samples are intra-class aggregated and inter-class relationship preserving. Experimental results on two benchmark datasets demonstrate the superiority of EGDH compared with the state-of-the-arts.

Grassland degradation estimation is essential to prevent global land desertification and sandstorms. Typically, the key to such estimation is to measure the coverage of indicator plants. However, traditional methods of estimation rely heavily on human eyes and manual labor, thus inevitably leading to subjective results and high labor costs. In contrast, deep learning-based image segmentation algorithms are potentially capable of automatic assessment of the coverage of indicator plants. Nevertheless, a suitable image dataset comprising grassland images is not publicly available. To this end, we build an original Automatic Grassland Degradation Estimation Dataset (AGDE-Dataset), with a large number of grassland images captured from the wild. Based on AGDE-Dataset, we are able to propose a brand new scheme to automatically estimate grassland degradation, which mainly consists of two components. 1) Semantic segmentation: we design a deep neural network with an improved encoder-decoder structure to implement semantic segmentation of grassland images. In addition, we propose a novel Focal-Hinge Loss to alleviate the class imbalance of semantics in the training stage. 2) Degradation estimation: we provide the estimation of grassland degradation based on the results of semantic segmentation. Experimental results show that the proposed method achieves satisfactory accuracy in grassland degradation estimation.

In order to solve the problem of memory consumption and computational requirements, this paper proposes a novel learning binary neural network framework to achieve a resource-efficient deep hashing. In contrast to floating-point (32-bit) full-precision networks, the proposed method achieves a 32x model compression rate. At the same time, computational burden in convolution is greatly reduced due to efficient Boolean operations. To this end, in our framework, a new quantization loss defined between the binary weights and the learned real values is minimized to reduce the model distortion, while, by minimizing a binary entropy function, the discrete optimization is successfully avoided and the stochastic gradient descend method can be used smoothly. More importantly, we provide two theories to demonstrate the necessity and effectiveness of minimizing the quantization losses for both weights and activations. Numerous experiments show that the proposed method can achieve fast code generation without sacrificing accuracy.

Face retrieval has received much attention over the past few decades, and many efforts have been made in retrieving face images against pose, illumination, and expression variations. However, the conventional works fail to meet the requirements of a potential and novel task---retrieving a person's face image at a specific age, especially when the specific "age" is not given as a numeral, i.e. "retrieving someone's image at the similar age period shown by another person's image." To tackle this problem, we propose a dual reference face retrieval framework in this paper, where the system takes two inputs: an identity reference image which indicates the target identity and an age reference image which reflects the target age. In our framework, the raw images are first projected on a joint manifold, which preserves both the age and identity locality. Then two similarity metrics of age and identity are exploited and optimized by utilizing our proposed quartet-based model. The experiments show promising results, outperforming hierarchical methods.

Recently, binary hashing has been widely applied to data compression, ranking and nearest-neighbor search. Although some promising results have been achieved, effectively optimizing sign function related objectives is still highly challenging and thus pseudo-labels are inevitably used. In this paper, we propose a novel general framework to simultaneously minimize the measurement distortion and the quantization loss, which enable to learn hash functions directly without requiring the pseudo-labels. More significantly, a novel W-Shape Loss (WSL) is specifically developed for hashing so that both the two separate steps of relaxation and the NP-hard discrete optimization are successfully discarded. The experimental results demonstrate that the retrieval performance both in uni-modal and cross-modal settings can be improved.

Unsupervised deep hash functions have not shown satisfactory improvements against their shallow alternatives, and usually require supervised pretraining to avoid overfitting. In this paper, we propose a new deep unsupervised hashing function, called HashGAN, which efficiently obtains binary representation of input images without any supervised pretraining. HashGAN consists of three networks, a generator, a discriminator and an encoder. By sharing the parameters of the encoder and discriminator, we benefit from the adversarial loss as a data-dependent regularization in training our deep hash function. Moreover, a novel hashing loss function is introduced for real images, which results in minimum entropy, uniform frequency, consistent and independent hash bits. Furthermore, we employ a collaborative loss in training our model, enforcing similar random inputs and hash bits for synthesized images. In our experiments, HashGAN outperforms the previous unsupervised hash functions in image retrieval and achieves the state-of-the-art performance in image clustering on benchmark datasets. We also provide an ablation study, showing the contribution of each component in our loss function.

Identifying vehicles across cameras in traffic surveillance is fundamentally important for public safety purposes. However, despite some preliminary work, the rapid vehicle search in large-scale datasets has not been investigated. Moreover, modelling a view-invariant similarity between vehicle images from different views is still highly challenging. To address the problems, in this paper, we propose a Ranked Semantic Sampling (RSS) guided binary embedding method for fast cross-view vehicle Re-IDentification (Re-ID). The search can be conducted by efficiently computing similarities in the projected space. Unlike previous methods using random sampling, we design tree-structured attributes to guide the mini-batch sampling. The ranked pairs of hard samples in the mini-batch can improve the convergence of optimization. By minimizing a novel ranked semantic distance loss defined according to the structure, the learned Hamming distance is view-invariant, which enables cross-view Re-ID. The experimental results demonstrate that RSS outperforms the state-of-the-art approaches and the learned embedding from one dataset can be transferred to achieve the task of vehicle Re-ID on another dataset.

Recently, cross-modal search has attracted considerable attention but remains a very challenging task because of the integration complexity and heterogeneity of the multi-modal data. To address both challenges, in this paper, we propose a novel method termed hetero-manifold regularisation (HMR) to supervise the learning of hash functions for efficient cross-modal search. A hetero-manifold integrates multiple sub-manifolds defined by homogeneous data with the help of cross-modal supervision information. Taking advantages of the hetero-manifold, the similarity between each pair of heterogeneous data could be naturally measured by three order random walks on this hetero-manifold. Furthermore, a novel cumulative distance inequality defined on the hetero-manifold is introduced to avoid the computational difficulty induced by the discreteness of hash codes. By using the inequality, cross-modal hashing is transformed into a problem of hetero-manifold regularised support vector learning. Therefore, the performance of cross-modal search can be significantly improved by seamlessly combining the integrated information of the hetero-manifold and the strong generalisation of the support vector machine. Comprehensive experiments show that the proposed HMR achieve advantageous results over the state-of-the-art methods in several challenging cross-modal tasks.

Recently, support vector ranking (SVR) has been adopted to address the challenging person reidentification problem. However, the ranking model based on ordinary global features cannot well represent the significant variation of pose and viewpoint across camera views. To address this issue, a novel ranking method that fuses the dense invariant features (DIFs) is proposed in this paper to model the variation of images across camera views. An optimal space for ranking is learned by simultaneously maximizing the margin and minimizing the error on the fused features. The proposed method significantly outperforms the original SVR algorithm due to the invariance of the DIFs, the fusion of the bidirectional features, and the adaptive adjustment of parameters. Experimental results demonstrate that the proposed method is competitive with state-of-the-art methods on two challenging data sets, showing its potential for real-world person reidentification.

Recently, numerous state-of-the-art learning schemes are proposed for object tracking. However, typically, most methods can only solve certain type of challenges but are less effective for the rest-no single tracker is perfect for all challenges. In this paper, a winner-take-all (WTA) strategy is exploited to select a winner tracker (considering both accuracy and efficiency) from a set of prevailing methods to tackle the current challenge, according to features extracted from the current environment and an efficiency factor. To achieve this, a structural regression model to characterize the trackers is trained on a public dataset. By incorporating the complementary abilities from multiple trackers, the diversity of the model is improved so that the WTA tracker can tackle various unpredictable difficulties. Since only one tracker is selected at any time, the average efficiency of the proposed model is also higher than that of complex trackers in the tracker set. The proposed WTA framework is tested on two benchmark datasets as well as several long sequences, and extensive experimental results illustrate that WTA can significantly improve both the performance and the efficiency.

Recently, intelligent vehicles catch much attention in both academia and industry. The vision-based moving object/vehicle detection and tracking are typically the core techniques for the event and activity analysis and the understanding of the dynamic driving environment in an intelligent vehicle. However, due to the complicated non-stationary environment, most existing vision-based motion tracking algorithms proposed for other simple conditions are not able to consistently track the objects. Therefore, in this paper, we propose a robust and long-term tracking method for intelligent vehicles, in which a set of classifiers are dynamically maintained and sampled for tackling varied challenges. In contrast to previous methods, to increase the diversity, a set of basic classifiers trained sequentially on different small data sets over time is dynamically maintained. The subsets of basic classifiers are independent with each other and can be specified to solve certain different sub-problems occurred in a non-stationary environment. Thus, for every challenge, an optimal classifier can be approximated in a subspace spanned by the selected competitive classifiers, which can address the current problem according to the distribution of the samples and recent performance. As a result, the tracker can efficiently address the various “concept drift” problems occurred together in a long video sequence. Due to the use of sparse weights for the competitive classifiers, the tracker can keep the balance between the efficiency and the performance. Experimental results show that the tracker yields competitive performance under various challenging environmental conditions and, especially, can overcome several challenges simultaneously.

Multitarget regression has recently generated intensive popularity due to its ability to simultaneously solve multiple regression tasks with improved performance, while great challenges stem from jointly exploring inter-target correlations and input-output relationships. In this paper, we propose multitarget sparse latent regression (MSLR) to simultaneously model intrinsic intertarget correlations and complex nonlinear input-output relationships in one single framework. By deploying a structure matrix, the MSLR accomplishes a latent variable model which is able to explicitly encode intertarget correlations via -norm-based sparse learning; the MSLR naturally admits a representer theorem for kernel extension, which enables it to flexibly handle highly complex nonlinear input-output relationships; the MSLR can be solved efficiently by an alternating optimization algorithm with guaranteed convergence, which ensures efficient multitarget regression. Extensive experimental evaluation on both synthetic data and six greatly diverse real-world data sets shows that the proposed MSLR consistently outperforms the state-of-the-art algorithms, which demonstrates its great effectiveness for multivariate prediction.

Local features have been widely used in computer vision tasks, e.g., human action recognition, but it tends to be an extremely challenging task to deal with large-scale local features of high dimensionality with redundant information. In this paper, we propose a novel fully supervised local descriptor learning algorithm called discriminative embedding method based on the image-to-class distance (I2CDDE) to learn compact but highly discriminative local feature descriptors for more accurate and efficient action recognition. By leveraging the advantages of the I2C distance, the proposed I2CDDE incorporates class labels to enable fully supervised learning of local feature descriptors, which achieves highly discriminative but compact local descriptors. The objective of our I2CDDE is to minimize the I2C distances from samples to their corresponding classes while maximizing the I2C distances to the other classes in the low-dimensional space. To further improve the performance, we propose incorporating a manifold regularization based on the graph Laplacian into the objective function, which can enhance the smoothness of the embedding by extracting the local intrinsic geometrical structure. The proposed I2CDDE for the first time achieves fully supervised learning of local feature descriptors. It significantly improves the performance of I2C-based methods by increasing the discriminative ability of local features while greatly reducing the computational burden by dimensionality reduction to handle large-scale data. We apply the proposed I2CDDE algorithm to human action recognition on four widely used benchmark datasets. The results have shown that I2CDDE can significantly improve I2C-based classifiers and achieves state-of-the-art performance.