论文检索

Wei Li, Dezhao Luo, Dongbao Yang, Zhenhang Li, Weiping Wang, Yu Zhou

Video action understanding tasks in real-world scenarios often suffer from data limitations. In this paper, we address the data-limited action understanding problem by bridging data scarcity. We propose a novel method that leverages a text-to-video diffusion transformer to generate annotated data for model training. This paradigm enables the generation of realistic annotated data on an infinite scale without human intervention. We proposed the Information Enhancement Strategy and the Uncertainty-Based Soft Target tailored to generate sample training. Through quantitative and qualitative analyzes, we discovered that real samples generally contain a richer level of information compared to generated samples. Based on this observation, the information enhancement strategy was designed to enhance the informational content of the generated samples from two perspectives: the environment and the character. Furthermore, we observed that a portion of low-quality generated samples might negatively affect model training. To address this, we devised an uncertainty-based label-smoothing strategy to increase the smoothing of these low-quality samples, thereby reducing their impact. We demonstrate the effectiveness of the proposed method on four datasets and five tasks, and achieve state-of-the-art performance for zero-shot action recognition.

Shenglan Li, Rui Yao, Yong Zhou, Hancheng Zhu, Kunyang Sun, Bing Liu, Zhiwen Shao, Jiaqi Zhao

To reduce the reliance on large-scale annotations, self-supervised RGB-T tracking approaches have garnered significant attention. However, the omission of the object region by erroneous pseudo-label or the introduction of background noise affects the efficiency of modality fusion, while pseudo-label noise triggered by similar object noise can further affect the tracking performance. In this paper, we propose GDSTrack, a novel approach that introduces dynamic graph fusion and temporal diffusion to address the above challenges in self-supervised RGB-T tracking. GDSTrack dynamically fuses the modalities of neighboring frames, treats them as distractor noise, and leverages the denoising capability of a generative model. Specifically, by constructing an adjacency matrix via an Adjacency Matrix Generator (AMG), the proposed Modality-guided Dynamic Graph Fusion (MDGF) module uses a dynamic adjacency matrix to guide graph attention, focusing on and fusing the object’s coherent regions. Temporal Graph-Informed Diffusion (TGID) models MDGF features from neighboring frames as interference, and thus improving robustness against similar-object noise. Extensive experiments conducted on four public RGB-T tracking datasets demonstrate that GDSTrack outperforms the existing state-of-the-art methods. The source code is available at https://github.com/LiShenglana/GDSTrack.

Ping Li, Jianan Ni, Bo Pang

Action recognition models using deep learning are vulnerable to adversarial examples, which are transferable across other models trained on the same data modality. Existing transferable attack methods face two major challenges: 1) they heavily rely on the assumption that the decision boundaries of the surrogate (a.k.a., source) model and the target model are similar, which limits the adversarial transferability; and 2) their decision boundary difference makes the attack direction uncertain, which may result in the gradient oscillation, weakening the adversarial attack. This motivates us to propose a Background Mixup-induced Temporal Consistency (BMTC) attack method for action recognition. From the input transformation perspective, we design a model-agnostic background adversarial mixup module to reduce the surrogate-target model dependency. In particular, we randomly sample one video from each category and make its background frame, while selecting the background frame with the top attack ability for mixup with the clean frame by reinforcement learning. Moreover, to ensure an explicit attack direction, we leverage the background category as guidance for updating the gradient of adversarial example, and design a temporal gradient consistency loss, which strengthens the stability of the attack direction on subsequent frames. Empirical studies on two video datasets, i.e., UCF101 and Kinetics-400, and one image dataset, i.e., ImageNet, demonstrate that our method significantly boosts the transferability of adversarial examples across several action/image recognition models.

Moqi Li, Xu Yang, Cheng Deng

Spiking Neural Networks (SNNs), inspired by the behavior of biological neurons, have gained significant research interest for resource-constrained edge devices and neuromorphic hardware due to their use of binary spike signals for inter-unit communication with low power consumption. However, the absence of research on spiking neural networks on long-tailed data has severely limited the deployment and application of this emerging network in practical scenarios. To fill this gap, this paper proposes a long-tail learning framework based on spiking neural networks, named LT-SpikingFormer, to alleviate the distribution bias between head and tail classes. LT-SpikingFormer adopts a widely trained Convolutional Neural Network to construct a heterogeneous knowledge distillation paradigm, offering balanced and reliable prior knowledge. Moreover, a multi-granularity hierarchical feature distillation objective is proposed to leverage cross-layer local features and network global predictions to facilitate refined information distillation to optimize the network, specifically for the performance of the tailed classes. Extensive experimental results demonstrate that our method performs well on several benchmark datasets.

Minghao Li, Rui Wang, Ming Sun, Lihua Jing

The remarkable progress of Latent Diffusion Models (LDMs) in image generation has raised concerns about the potential for unauthorized image mimicry. To address these concerns, studies on adversarial attacks against LDMs have gained increasing attention in recent years. However, existing methods face bottlenecks when attacking the denoising module. In this work, we reveal that the robustness of the denoising module stems from two key factors: the cancellation effect between adversarial perturbations and estimated noise, and unstable gradients caused by randomly sampled timesteps and Gaussian noise. Based on these insights, we introduce a cosine similarity adversarial loss to prevent the generation of perturbations that are easily impaired and develop a more stable optimization strategy by ensembling gradients and fixing the noise in the latent space. Additionally, we propose an alternating iterative framework to reduce memory usage by mathematically dividing the optimization process into two spaces: latent space and pixel space. Compared to previous strategies, our proposed framework reduces video memory demands without sacrificing attack effectiveness. Extensive experiments demonstrate that the alternating iterative framework and the stable optimization strategy on cosine similarity loss are more efficient and more effective. Code is available at https://github.com/MinghaoLi01/cosattack.

Jiao Li, Houcheng Su, Bingli Wang, Yuandong Min, Mengzhu Wang, Nan Yin, Shanshan Wang, Jingcai Guo

Domain adaptation (DA) is crucial for transferring models trained in one domain to perform well in a different, often unseen domain. Traditional methods, including unsupervised domain adaptation (UDA) and source-free domain adaptation (SFDA), have made significant progress. However, most existing DA methods rely heavily on Batch Normalization (BN) layers, which are not optimal in source-free settings, where the source domain is unavailable for comparison. In this study, we propose a novel method, ESBN, which addresses the challenge of domain shift by adjusting the placement of normalization layers and replacing BN with Batch-free Normalization (BFN). Unlike BN, BFN is less dependent on batch statistics and provides more robust feature representations through instance-specific statistics. We systematically investigate the effects of different BN layer placements across various network configurations and demonstrate that selective replacement with BFN improves generalization performance. Extensive experiments on multiple domain adaptation benchmarks show that our approach outperforms state-of-the-art methods, particularly in challenging scenarios such as Open-Partial Domain Adaptation (OPDA).

Hangyu Li, Yixin Zhang, Jiangchao Yao, Nannan Wang, Bo Han

Semi-supervised facial expression recognition (SSFER) effectively assigns pseudo-labels to confident unlabeled samples when only limited emotional annotations are available. Existing SSFER methods are typically built upon an assumption of the class-balanced distribution. However, they are far from real-world applications due to biased pseudo-labels caused by class imbalance. To alleviate this issue, we propose Regularized Mixture of Predictions (ReMoP), a simple yet effective method to generate high-quality pseudo-labels for imbalanced samples. Specifically, we first integrate feature similarity into the linear prediction to learn a mixture of predictions. Furthermore, we introduce a class regularization term that constrains the feature geometry to mitigate imbalance bias. Being practically simple, our method can be integrated with existing semi-supervised learning and SSFER methods to tackle the challenge associated with class-imbalanced SSFER effectively. Extensive experiments on four facial expression datasets demonstrate the effectiveness of the proposed method across various imbalanced conditions. The source code is made publicly available at https://github.com/hangyu94/ReMoP.

Dongdong Li, Zhinan Gao, Yangliu Kuai, Rui Chen

Sequence learning based tracking frameworks are popular in the tracking community. In practice, its auto-regressive sequence generation manner leads to inferior performance and high latency compared with latest advanced trackers. In this paper, to mitigate this issue, we propose an efficient and effective sequence-to-sequence tracking framework named FastSeqTrack. FastSeqTrack differs from previous sequence learning based trackers in terms of token initialization and sequence generation manner. Four tracking tokens are appended to patch embeddings and generated in the encoder as initial guesses for the bounding box sequence, which improves the tracking accuracy compared with randomly initialized tokens. Tracking tokens are then parallelly fed into the decoder in a one-pass manner and greatly boost the forward inference speed compared with the auto-regressive manner. Inspired by the early-exit mechanism, we inject internal classifiers after each decoder layer to early terminate forward inference when the softmax confidence is sufficiently reliable. In easy tracking frames, early exits avoid network overthinking and unnecessary computation. Extensive experiments on multiple benchmarks demonstrate that FastSeqTrack runs over 100 fps and showcases superior performance against state-of-the-art trackers. Codes and models are available at https://github.com/vision4drones/FastSeqTrack.

Dong Li, Jiayíng Zhu, Yidi Liu, Xin Lu, Xueyang Fu, Jiawei Liu, Aiping Liu, Zheng-Jun Zha

Concern for image authenticity spurs research in image forgery detection and localization (IFDL). Most deep learning-based methods focus primarily on spatial domain modeling and have not fully explored frequency domain strategies. In this paper, we observe and analyze the frequency characteristic changes caused by image tampering. Observations indicate that manipulation traces are especially prominent in phase components and span both low and high-frequency bands. Based on these findings, we propose a forensic frequency decomposition network (F2D-Net), which incorporates deep Fourier transforms and leverages both phase information and high and low-frequency components to enhance IFDL. Specifically, F2D-Net consists of the Spectral Decomposition Subnetwork (SDSN) and the Frequency Separation Subnetwork (FSSN). The former decomposes the image into amplitude and phase, focusing on learning the semantic content in the phase spectrum to identify forged objects, thus improving forgery detection accuracy. The latter further adaptively decomposes the output of the SDSN to obtain corresponding high and low frequencies, and applies a divide-and-conquer strategy to refine each frequency band, mitigating the optimization difficulties caused by coupled forgery traces across different frequencies, thereby better capturing the pixels belonging to the forged object to improve localization accuracy. Experiments on multiple datasets demonstrate that our method outperforms state-of-the-art image forgery detection and localization techniques both qualitatively and quantitatively.

Chunming Li, Shidong Wang, Haofeng Zhang

The recently proposed Novel Category Discovery (NCD) adapt paradigm of transductive learning hinders its application in more real-world scenarios. In fact, few labeled data in part of new categories can well alleviate this burden, which coincides with the ease that people can label few of new category data. Therefore, this paper presents a new setting in which a trained agent is able to flexibly switch between the tasks of identifying examples of known (labelled) classes and clustering novel (completely unlabeled) classes as the number of query examples increases by leveraging knowledge learned from only a few (handful) support examples. Drawing inspiration from the discovery of novel categories using prior-based clustering algorithms, we introduce a novel framework that further relaxes its assumptions to the real-world open set level by unifying the concept of model adaptability in few-shot learning. We refer to this setting as Few-Shot Novel Category Discovery (FSNCD) and propose Semi-supervised Hierarchical Clustering (SHC) and Uncertainty-aware K-means Clustering (UKC) to examine the model's reasoning capabilities. Extensive experiments and detailed analysis on five commonly used datasets demonstrate that our methods can achieve leading performance levels across different task settings and scenarios. Code is available at: https://github.com/Ashengl/FSNCD.

Chuanhao Li, Wenbo Ye, Zhen Li, Yuwei Wu, Yunde Jia

Compositional generalization is the ability of generalizing novel compositions from seen primitives, and has received much attention in vision-and-language (V&L) recently. Due to the multi-modal nature of V&L tasks, the primitives composing compositions source from different modalities, resulting in multi-sourced novel compositions. However, the generalization ability over multi-sourced novel compositions, i.e., multi-sourced compositional generalization (MSCG) remains unexplored. In this paper, we explore MSCG in the context of visual question answering (VQA), and propose a retrieval-augmented training framework to enhance the MSCG ability of VQA models by learning unified representations for primitives from different modalities. Specifically, semantically equivalent primitives are retrieved for each primitive in the training samples, and the retrieved features are aggregated with the original primitive to refine the model. This process helps the model learn consistent representations for the same semantic primitives across different modalities. To evaluate the MSCG ability of VQA models, we construct a new GQA-MSCG dataset based on the GQA dataset, in which samples include three types of novel compositions composed of primitives from different modalities. The GQA-MSCG dataset is available at https://github.com/NeverMoreLCH/MSCG.

Chaozhuo Li, Zhihao Tang, Mingji Zhang, Zhiquan Liu, Litian Zhang, Xi Zhang

Survival prediction is a pivotal task for estimating mortality risk within a given timeframe based on whole slide images (WSIs). Conventional models typically assume that WSIs across patients are independent and identically distributed, an assumption that may not hold due to inherent variability in WSI preparation and the uncertain condition of infected tissues. These uncontrollable external factors introduce significant variability in the numbers and resolutions of WSIs across patients, leading to bias and compromised performance, particularly for tail patients with limited data. In this paper, we propose a novel approach, PathoKD, based on knowledge distillation. Recognizing the hierarchical nature of disease progression and the data scarcity issues associated with vanilla knowledge distillation methods, PathoKD integrates a novel curriculum learning framework with hierarchical knowledge distillation. This integration effectively mitigates the performance gap between head and tail patients, thereby enhancing prediction accuracy across patient groups. Our proposal is extensively evaluated over popular datasets and experimental results demonstrate its superiority.

Byeonggwon Lee, Junkyu Park, Khang Truong Giang, Soohwan Song

This study addresses the challenge of generating online 3D Gaussian Splatting (3DGS) models from RGB-only frames. Previous studies have employed dense SLAM techniques to estimate 3D scenes from keyframes for 3DGS model construction. However, these methods are limited by their reliance solely on keyframes, which are insufficient to capture an entire scene, resulting in incomplete reconstructions. Moreover, building a generalizable model requires incorporating frames from diverse viewpoints to achieve broader scene coverage. However, online processing restricts the use of many frames or extensive training iterations. Therefore, we propose a novel method for high-quality 3DGS modeling that improves model completeness through adaptive view selection. By analyzing reconstruction quality online, our approach selects optimal non-keyframes for additional training. By integrating both keyframes and selected non-keyframes, the method refines incomplete regions from diverse viewpoints, significantly enhancing completeness. We also present a framework that incorporates an online multi-view stereo approach, ensuring consistency in 3D information throughout the 3DGS modeling process. Experimental results demonstrate that our method outperforms state-of-the-art methods, delivering exceptional performance in complex outdoor scenes.

Yutong Kou, Shubo Lin, Liang Li, Bing Li, Weiming Hu, Jin Gao

In recent years, CPU real-time object tracking has gained significant attention due to its broad applications such as UAV-tracking. To maintain computational efficiency, most existing CPU real-time object trackers rely on lightweight backbones and employ a single initial template image without intermediate online templates. Although the appearance variance between the template and the search is larger under this single template setting, the representation ability of lightweight backbones is weaker which poses a challenge when training lightweight object trackers. To address this issue, we propose SSTrack, a new easier-to-harder training schedule for the lightweight object tracker. From the data perspective, our method designed a success-aware sample scheduler that gradually increases difficult training samples with longer template-search time intervals and reduces the amount of the easier samples so the training cost remains unchanged. From the optimization perspective, we utilized a gradient scaling strategy that retains the original training objective of easier samples despite the reduction in their quantities. With the collective effort from both perspectives, our method achieves State-of-the-Art CPU-real-time accuracy on 5 UAV-tracking benchmarks and 5 general object tracking benchmarks. Codes and models will be available at https://github.com/Kou-99/SSTrack.

Min Hyuk Kim, Seok Bong Yoo

Federated learning has significant demonstrated potential in medical image segmentation to protect data privacy by retaining local data. However, its application is still hindered by two critical challenges: 1) the retained data poisoning attacks that severely compromise the accuracy of the global segmentation model and 2) domain gaps among clients, undermining its generalizability. To address these issues, we propose AdaShield-FL, a data poisoning attack defense and evolutionary domain adaptation for federated medical image segmentation. AdaShield-FL incorporates a disentangled reconstruction and segmentation module that purifies data in the k-space domain to mitigate the effects of adversarial attacks iteratively. Moreover, it introduces a data poisoning attack detection mechanism that analyzes abnormal patterns in training loss sequences to identify malicious clients. This method also aligns local and global covariance matrices via evolutionary optimization to minimize the domain gap efficiently. The experimental validation on cardiac magnetic resonance imaging datasets demonstrates the robustness and superior performance of AdaShield-FL compared with other federated learning methods.

Xiao Ke, Weijie Zhou, Yuzhen Niu

In recent years, deep learning-based Salient Object Detection (SOD) methods have made tremendous progress; however, their performance in complex scenarios has reached a bottleneck. In this paper, we propose a novel Progressive Difference Fusion Network (PDFNet) based on fine-grained feature fusion. First, to address the scale variability of salient objects, we introduce a Self-Guided Module (SGM) with dynamic receptive fields. Second, to tackle the shape variability of salient objects, we design a Feature Aggregation Module (FAM) incorporating cross convolutions and a feedback loop. Finally, to alleviate the issue of confusion between global and detail information during multi-scale feature fusion in existing models, we develop a Progressive Difference Fusion Unit (PDFU) to project multi-scale features into fine-grained nodes and enhance them through node interaction based on difference features. Additionally, we propose a Conditional Random Field Based on Patch (CRFbp), which focuses on handling discrete points, further improving the model’s performance. Extensive experiments demonstrate that our method achieves state-of-the-art (SOTA) performance on five benchmark datasets. Code is available at: https://github.com/pdfnet2025/PDFNet.git.

Luoxi Jing, Dianxi Shi, Zhe Liu, Songchang Jin, Chunping Qiu, Ziteng Qiao, Yuxian Li, Jianqiang Xia

Depth estimation plays a crucial role in 3D scene understanding and is extensively used in a wide range of vision tasks. Image-based methods struggle in challenging scenarios, while event cameras offer high dynamic range and temporal resolution but face difficulties with sparse data. Combining event and image data provides significant advantages, yet effective integration remains challenging. Existing CNN-based fusion methods struggle with occlusions and depth disparities due to limited receptive fields, while Transformer-based fusion methods often lack deep modality interaction. To address these issues, we propose UniCT Depth, an event-image fusion method that unifies CNNs and Transformers to model local and global features. We propose the Convolution-compensated ViT Dual SA (CcViT-DA) Block, designed for the encoder, which integrates Context Modeling Self-Attention (CMSA) to capture spatial dependencies and Modal Fusion Self-Attention (MFSA) for effective cross-modal fusion. Furthermore, we design the tailored Detail Compensation Convolution (DCC) Block to improve texture details and enhances edge representations. Extensive experiments show that UniCT Depth outperforms existing image, event, and fusion-based monocular depth estimation methods across key metrics.

Chenchen Jing, Mingyu Liu, Hao Chen, Yuling Xi, Xingyuan Bu, Dong Gong, Chunhua Shen

Compositional zero-shot learning (CZSL) is to recognize unseen attribute-object compositions by learning from seen compositions. The distribution shift between unseen compositions and seen compositions poses challenges to CZSL models, especially when test images are mixed with both seen and unseen compositions. The challenge will be addressed more easily if a model can distinguish unseen/seen compositions and treat them with specific recognition strategies. However, identifying images with unseen compositions is non-trivial, considering that unseen compositions are absent in training and usually contain only subtle differences from seen compositions. In this paper, we propose a novel compositional zero-shot learning method called COMO, which composes outliers in training for distinguishing seen and unseen compositions and further applying specific strategies for them. Specifically, we compose attribute-object representations for unseen compositions based on primitive representations of training images as outliers to enable the model to identify unseen compositions in inference. At test time, the method distinguishes images containing seen/unseen compositions and uses different weights for composition classification and primitive classification to recognize seen/unseen compositions. Experimental results on three datasets show the effectiveness of our method in both the closed-world setting and the open-world setting.

Xianghao Jiao, Di Wang, Jiawei Liang, Jianjie Huang, Wei Wang, Xiaochun Cao

The escalating threat of backdoor risks in deep vision models is a pressing concern. Existing research on backdoor attacks is often confined to a single modality, neglecting the challenges posed by multi-modality scene perception. This work is a pioneer of backdoor attacks in RGB-Thermal (RGB-T) semantic segmentation. We overcome the critical limitation of current segmentation backdoor attacks that indiscriminately compromise all objects of a victim class, failing to provide fine-grained control for selectively targeting specific objects as required by adversaries. To address this, we introduce a novel Object-level Backdoor Attack pipeline, termed OBA. The OBA first employs a precise data poisoning (PDP) to lock a specific victim object. Specifically, the PDP embeds the trigger into the only victim object and modifies its label’s pixels at the corresponding positions, thus enabling object-level attacks. In addition, the domain gap between static single-modality triggers and multi-modality scenarios limits the PDP. We therefore introduce a Cross-Modality Trigger Generation (CMTG) method. Through style designs of triggers and cross-modality trigger co-optimization, the target domain semantics and multi-modality model perception patterns are encoded into triggers, achieving high effectiveness, stealth, and physical feasibility of triggers. Extensive experiments show that the proposed OBA enables precise manipulation of the designated object within the specific class.

Yudong Jiang, Baohan Xu, Siqian Yang, Mingyu Ying, Jing Liu, Chao Xu, Siqi Wang, Yidi Wu, Bingwen Zhu, Yue Zhang 等

Animation has gained significant interest in the recent film and TV industry. Despite the success of advanced video generation models like Sora, Kling, and CogVideoX in generating natural videos, they lack the same effectiveness in handling animation videos. Evaluating animation video generation is also a great challenge due to its unique artist styles, violating the laws of physics and exaggerated motions. In this paper, we present a comprehensive system, AniSora, designed for animation video generation, which includes a data processing pipeline, a controllable generation model, and an evaluation benchmark. Supported by the data processing pipeline with over 10M high-quality data, the generation model incorporates a spatiotemporal mask module to facilitate key animation production functions such as image-to-video generation, frame interpolation, and localized image-guided animation. We also collect an evaluation benchmark of 948 various animation videos, with specifically developed metrics for animation video generation. Our entire project is publicly available on https://github.com/bilibili/Index-anisora/tree/main