Shiguang Shan

Botao Ye, Hong Chang, Bingpeng Ma et al.

The current popular two-stream, two-stage tracking framework extracts the template and the search region features separately and then performs relation modeling, thus the extracted features lack the awareness of the target and have limited target-background discriminability. To tackle the above issue, we propose a novel one-stream tracking (OSTrack) framework that unifies feature learning and relation modeling by bridging the template-search image pairs with bidirectional information flows. In this way, discriminative target-oriented features can be dynamically extracted by mutual guidance. Since no extra heavy relation modeling module is needed and the implementation is highly parallelized, the proposed tracker runs at a fast speed. To further improve the inference efficiency, an in-network candidate early elimination module is proposed based on the strong similarity prior calculated in the one-stream framework. As a unified framework, OSTrack achieves state-of-the-art performance on multiple benchmarks, in particular, it shows impressive results on the one-shot tracking benchmark GOT-10k, i.e., achieving 73.7% AO, improving the existing best result (SwinTrack) by 4.3\%. Besides, our method maintains a good performance-speed trade-off and shows faster convergence. The code and models are available at https://github.com/botaoye/OSTrack.

Xinqian Gu, Hong Chang, Bingpeng Ma et al.

The key to address clothes-changing person re-identification (re-id) is to extract clothes-irrelevant features, e.g., face, hairstyle, body shape, and gait. Most current works mainly focus on modeling body shape from multi-modality information (e.g., silhouettes and sketches), but do not make full use of the clothes-irrelevant information in the original RGB images. In this paper, we propose a Clothes-based Adversarial Loss (CAL) to mine clothes-irrelevant features from the original RGB images by penalizing the predictive power of re-id model w.r.t. clothes. Extensive experiments demonstrate that using RGB images only, CAL outperforms all state-of-the-art methods on widely-used clothes-changing person re-id benchmarks. Besides, compared with images, videos contain richer appearance and additional temporal information, which can be used to model proper spatiotemporal patterns to assist clothes-changing re-id. Since there is no publicly available clothes-changing video re-id dataset, we contribute a new dataset named CCVID and show that there exists much room for improvement in modeling spatiotemporal information. The code and new dataset are available at: https://github.com/guxinqian/Simple-CCReID.

Dongyang Liu, Meina Kan, Shiguang Shan et al.

Feature distillation makes the student mimic the intermediate features of the teacher. Nearly all existing feature-distillation methods use L2 distance or its slight variants as the distance metric between teacher and student features. However, while L2 distance is isotropic w.r.t. all dimensions, the neural network's operation on different dimensions is usually anisotropic, i.e., perturbations with the same 2-norm but in different dimensions of intermediate features lead to changes in the final output with largely different magnitude. Considering this, we argue that the similarity between teacher and student features should not be measured merely based on their appearance (i.e., L2 distance), but should, more importantly, be measured by their difference in function, namely how later layers of the network will read, decode, and process them. Therefore, we propose Function-Consistent Feature Distillation (FCFD), which explicitly optimizes the functional similarity between teacher and student features. The core idea of FCFD is to make teacher and student features not only numerically similar, but more importantly produce similar outputs when fed to the later part of the same network. With FCFD, the student mimics the teacher more faithfully and learns more from the teacher. Extensive experiments on image classification and object detection demonstrate the superiority of FCFD to existing methods. Furthermore, we can combine FCFD with many existing methods to obtain even higher accuracy. Our codes are available at https://github.com/LiuDongyang6/FCFD.

Zhongqi Wang, Jie Zhang, Zhilong Ji et al.

With the development of deep generative models, recent years have seen great success of Chinese landscape painting generation. However, few works focus on controllable Chinese landscape painting generation due to the lack of data and limited modeling capabilities. In this work, we propose a controllable Chinese landscape painting generation method named CCLAP, which can generate painting with specific content and style based on Latent Diffusion Model. Specifically, it consists of two cascaded modules, i.e., content generator and style aggregator. The content generator module guarantees the content of generated paintings specific to the input text. While the style aggregator module is to generate paintings of a style corresponding to a reference image. Moreover, a new dataset of Chinese landscape paintings named CLAP is collected for comprehensive evaluation. Both the qualitative and quantitative results demonstrate that our method achieves state-of-the-art performance, especially in artfully-composed and artistic conception. Codes are available at https://github.com/Robin-WZQ/CCLAP.

Yiheng Li, Zhuo Li, Ruibing Hou et al.

Conditional human motion generation remains a fundamental challenge in computer vision and robotics. Despite significant progress, current methods are often constrained by fixed modality configurations and task-specific architectures, leaving cross-modal interactions and the scaling laws of multimodal-conditioned synthesis largely underexplored. A key bottleneck is the scarcity of large-scale modality-aligned motion data, limiting generalization across diverse control signals. In this work, we introduce OmniHuMo, a large-scale, high-quality dataset comprising over 5,000 hours of motion and 3.2 million sequences with precisely aligned multimodal annotations (e.g., text, speech, music, and trajectory). Leveraging OmniHuMo, we propose AnyMo, a unified multimodal framework combining a Residual FSQ-based motion tokenizer with a scalable masked modeling transformer, enabling high-quality motion synthesis under arbitrary modality combinations. Extensive experiments show that AnyMo achieves high-fidelity synthesis while offering flexible control over both spatial and stylistic attributes.

Wenrui Liu, Hong Chang, Bingpeng Ma et al.

Reconstruction-based anomaly detection models achieve their purpose by suppressing the generalization ability for anomaly. However, diverse normal patterns are consequently not well reconstructed as well. Although some efforts have been made to alleviate this problem by modeling sample diversity, they suffer from shortcut learning due to undesired transmission of abnormal information. In this paper, to better handle the tradeoff problem, we propose Diversity-Measurable Anomaly Detection (DMAD) framework to enhance reconstruction diversity while avoid the undesired generalization on anomalies. To this end, we design Pyramid Deformation Module (PDM), which models diverse normals and measures the severity of anomaly by estimating multi-scale deformation fields from reconstructed reference to original input. Integrated with an information compression module, PDM essentially decouples deformation from prototypical embedding and makes the final anomaly score more reliable. Experimental results on both surveillance videos and industrial images demonstrate the effectiveness of our method. In addition, DMAD works equally well in front of contaminated data and anomaly-like normal samples.

Yuanyuan Liu, Wei Dai, Chuanxu Feng et al.

Dynamic facial expression recognition (FER) databases provide important data support for affective computing and applications. However, most FER databases are annotated with several basic mutually exclusive emotional categories and contain only one modality, e.g., videos. The monotonous labels and modality cannot accurately imitate human emotions and fulfill applications in the real world. In this paper, we propose MAFW, a large-scale multi-modal compound affective database with 10,045 video-audio clips in the wild. Each clip is annotated with a compound emotional category and a couple of sentences that describe the subjects' affective behaviors in the clip. For the compound emotion annotation, each clip is categorized into one or more of the 11 widely-used emotions, i.e., anger, disgust, fear, happiness, neutral, sadness, surprise, contempt, anxiety, helplessness, and disappointment. To ensure high quality of the labels, we filter out the unreliable annotations by an Expectation Maximization (EM) algorithm, and then obtain 11 single-label emotion categories and 32 multi-label emotion categories. To the best of our knowledge, MAFW is the first in-the-wild multi-modal database annotated with compound emotion annotations and emotion-related captions. Additionally, we also propose a novel Transformer-based expression snippet feature learning method to recognize the compound emotions leveraging the expression-change relations among different emotions and modalities. Extensive experiments on MAFW database show the advantages of the proposed method over other state-of-the-art methods for both uni- and multi-modal FER. Our MAFW database is publicly available from https://mafw-database.github.io/MAFW.

Zhongqi Wang, Jie Zhang, Shiguang Shan et al.

While text-to-image diffusion models demonstrate impressive generation capabilities, they also exhibit vulnerability to backdoor attacks, which involve the manipulation of model outputs through malicious triggers. In this paper, for the first time, we propose a comprehensive defense method named T2IShield to detect, localize, and mitigate such attacks. Specifically, we find the "Assimilation Phenomenon" on the cross-attention maps caused by the backdoor trigger. Based on this key insight, we propose two effective backdoor detection methods: Frobenius Norm Threshold Truncation and Covariance Discriminant Analysis. Besides, we introduce a binary-search approach to localize the trigger within a backdoor sample and assess the efficacy of existing concept editing methods in mitigating backdoor attacks. Empirical evaluations on two advanced backdoor attack scenarios show the effectiveness of our proposed defense method. For backdoor sample detection, T2IShield achieves a detection F1 score of 88.9$\%$ with low computational cost. Furthermore, T2IShield achieves a localization F1 score of 86.4$\%$ and invalidates 99$\%$ poisoned samples. Codes are released at https://github.com/Robin-WZQ/T2IShield.

Changzhen Li, Jie Zhang, Shuzhe Wu et al.

Recently action recognition has received more and more attention for its comprehensive and practical applications in intelligent surveillance and human-computer interaction. However, few-shot action recognition has not been well explored and remains challenging because of data scarcity. In this paper, we propose a novel hierarchical compositional representations (HCR) learning approach for few-shot action recognition. Specifically, we divide a complicated action into several sub-actions by carefully designed hierarchical clustering and further decompose the sub-actions into more fine-grained spatially attentional sub-actions (SAS-actions). Although there exist large differences between base classes and novel classes, they can share similar patterns in sub-actions or SAS-actions. Furthermore, we adopt the Earth Mover's Distance in the transportation problem to measure the similarity between video samples in terms of sub-action representations. It computes the optimal matching flows between sub-actions as distance metric, which is favorable for comparing fine-grained patterns. Extensive experiments show our method achieves the state-of-the-art results on HMDB51, UCF101 and Kinetics datasets.

Liang Shi, Jie Zhang, Shiguang Shan

The emergence of deepfake technologies has become a matter of social concern as they pose threats to individual privacy and public security. It is now of great significance to develop reliable deepfake detectors. However, with numerous face manipulation algorithms present, it is almost impossible to collect sufficient representative fake faces, and it is hard for existing detectors to generalize to all types of manipulation. Therefore, we turn to learn the distribution of real faces, and indirectly identify fake images that deviate from the real face distribution. In this study, we propose Real Face Foundation Representation Learning (RFFR), which aims to learn a general representation from large-scale real face datasets and detect potential artifacts outside the distribution of RFFR. Specifically, we train a model on real face datasets by masked image modeling (MIM), which results in a discrepancy between input faces and the reconstructed ones when applying the model on fake samples. This discrepancy reveals the low-level artifacts not contained in RFFR, making it easier to build a deepfake detector sensitive to all kinds of potential artifacts outside the distribution of RFFR. Extensive experiments demonstrate that our method brings about better generalization performance, as it significantly outperforms the state-of-the-art methods in cross-manipulation evaluations, and has the potential to further improve by introducing extra real faces for training RFFR.

Ruibing Hou, Hong Chang, Bingpeng Ma et al.

Learning generalizable representation and classifier for class-imbalanced data is challenging for data-driven deep models. Most studies attempt to re-balance the data distribution, which is prone to overfitting on tail classes and underfitting on head classes. In this work, we propose Dual Compensation Residual Networks to better fit both tail and head classes. Firstly, we propose dual Feature Compensation Module (FCM) and Logit Compensation Module (LCM) to alleviate the overfitting issue. The design of these two modules is based on the observation: an important factor causing overfitting is that there is severe feature drift between training and test data on tail classes. In details, the test features of a tail category tend to drift towards feature cloud of multiple similar head categories. So FCM estimates a multi-mode feature drift direction for each tail category and compensate for it. Furthermore, LCM translates the deterministic feature drift vector estimated by FCM along intra-class variations, so as to cover a larger effective compensation space, thereby better fitting the test features. Secondly, we propose a Residual Balanced Multi-Proxies Classifier (RBMC) to alleviate the under-fitting issue. Motivated by the observation that re-balancing strategy hinders the classifier from learning sufficient head knowledge and eventually causes underfitting, RBMC utilizes uniform learning with a residual path to facilitate classifier learning. Comprehensive experiments on Long-tailed and Class-Incremental benchmarks validate the efficacy of our method.

Yuanhang Zhang, Susan Liang, Shuang Yang et al.

This report presents a brief description of our winning solution to the AVA Active Speaker Detection (ASD) task at ActivityNet Challenge 2022. Our underlying model UniCon+ continues to build on our previous work, the Unified Context Network (UniCon) and Extended UniCon which are designed for robust scene-level ASD. We augment the architecture with a simple GRU-based module that allows information of recurring identities to flow across scenes through read and update operations. We report a best result of 94.47% mAP on the AVA-ActiveSpeaker test set, which continues to rank first on this year's challenge leaderboard and significantly pushes the state-of-the-art.

Songtao Luo, Shuang Yang, Shiguang Shan et al.

In this paper, we propose a novel method for speaker adaptation in lip reading, motivated by two observations. Firstly, a speaker's own characteristics can always be portrayed well by his/her few facial images or even a single image with shallow networks, while the fine-grained dynamic features associated with speech content expressed by the talking face always need deep sequential networks to represent accurately. Therefore, we treat the shallow and deep layers differently for speaker adaptive lip reading. Secondly, we observe that a speaker's unique characteristics ( e.g. prominent oral cavity and mandible) have varied effects on lip reading performance for different words and pronunciations, necessitating adaptive enhancement or suppression of the features for robust lip reading. Based on these two observations, we propose to take advantage of the speaker's own characteristics to automatically learn separable hidden unit contributions with different targets for shallow layers and deep layers respectively. For shallow layers where features related to the speaker's characteristics are stronger than the speech content related features, we introduce speaker-adaptive features to learn for enhancing the speech content features. For deep layers where both the speaker's features and the speech content features are all expressed well, we introduce the speaker-adaptive features to learn for suppressing the speech content irrelevant noise for robust lip reading. Our approach consistently outperforms existing methods, as confirmed by comprehensive analysis and comparison across different settings. Besides the evaluation on the popular LRW-ID and GRID datasets, we also release a new dataset for evaluation, CAS-VSR-S68h, to further assess the performance in an extreme setting where just a few speakers are available but the speech content covers a large and diversified range.

Changzhen Li, Jie Zhang, Yang Wei et al.

Vision Transformers have achieved great success in computer visions, delivering exceptional performance across various tasks. However, their inherent reliance on sequential input enforces the manual partitioning of images into patch sequences, which disrupts the image's inherent structural and semantic continuity. To handle this, we propose a novel Pattern Transformer (Patternformer) to adaptively convert images to pattern sequences for Transformer input. Specifically, we employ the Convolutional Neural Network to extract various patterns from the input image, with each channel representing a unique pattern that is fed into the succeeding Transformer as a visual token. By enabling the network to optimize these patterns, each pattern concentrates on its local region of interest, thereby preserving its intrinsic structural and semantic information. Only employing the vanilla ResNet and Transformer, we have accomplished state-of-the-art performance on CIFAR-10 and CIFAR-100, and have achieved competitive results on ImageNet.

Feixiang Wang, Shuang Yang, Shiguang Shan et al.

In this work, we focus on leveraging facial cues beyond the lip region for robust Audio-Visual Speech Enhancement (AVSE). The facial region, encompassing the lip region, reflects additional speech-related attributes such as gender, skin color, nationality, etc., which contribute to the effectiveness of AVSE. However, static and dynamic speech-unrelated attributes also exist, causing appearance changes during speech. To address these challenges, we propose a Dual Attention Cooperative Framework, DualAVSE, to ignore speech-unrelated information, capture speech-related information with facial cues, and dynamically integrate it with the audio signal for AVSE. Specifically, we introduce a spatial attention-based visual encoder to capture and enhance visual speech information beyond the lip region, incorporating global facial context and automatically ignoring speech-unrelated information for robust visual feature extraction. Additionally, a dynamic visual feature fusion strategy is introduced by integrating a temporal-dimensional self-attention module, enabling the model to robustly handle facial variations. The acoustic noise in the speaking process is variable, impacting audio quality. Therefore, a dynamic fusion strategy for both audio and visual features is introduced to address this issue. By integrating cooperative dual attention in the visual encoder and audio-visual fusion strategy, our model effectively extracts beneficial speech information from both audio and visual cues for AVSE. Thorough analysis and comparison on different datasets, including normal and challenging cases with unreliable or absent visual information, consistently show our model outperforming existing methods across multiple metrics.

Junqi Yang, Yuecong Min, Jie Zhang et al.

Despite rapid progress, Video Large Language Models (Video-LLMs) remain unreliable due to hallucinations, which are outputs that contradict either video evidence (faithfulness) or verifiable world knowledge (factuality). Existing benchmarks provide limited coverage of factuality hallucinations and predominantly evaluate models only in clean settings. We introduce \textsc{INFACT}, a diagnostic benchmark comprising 9{,}800 QA instances with fine-grained taxonomies for faithfulness and factuality, spanning real and synthetic videos. \textsc{INFACT} evaluates models in four modes: Base (clean), Visual Degradation, Evidence Corruption, and Temporal Intervention for order-sensitive items. Reliability under induced modes is quantified using Resist Rate (RR) and Temporal Sensitivity Score (TSS). Experiments on 14 representative Video-LLMs reveal that higher Base-mode accuracy does not reliably translate to higher reliability in the induced modes, with evidence corruption reducing stability and temporal intervention yielding the largest degradation. Notably, many open-source baselines exhibit near-zero TSS on factuality, indicating pronounced temporal inertia on order-sensitive questions.

Zonghui Guo, Yingjie Liu, Jie Zhang et al.

Face Forgery Detection (FFD), or Deepfake detection, aims to determine whether a digital face is real or fake. Due to different face synthesis algorithms with diverse forgery patterns, FFD models often overfit specific patterns in training datasets, resulting in poor generalization to other unseen forgeries. This severe challenge requires FFD models to possess strong capabilities in representing complex facial features and extracting subtle forgery cues. Although previous FFD models directly employ existing backbones to represent and extract facial forgery cues, the critical role of backbones is often overlooked, particularly as their knowledge and capabilities are insufficient to address FFD challenges, inevitably limiting generalization. Therefore, it is essential to integrate the backbone pre-training configurations and seek practical solutions by revisiting the complete FFD workflow, from backbone pre-training and fine-tuning to inference of discriminant results. Specifically, we analyze the crucial contributions of backbones with different configurations in FFD task and propose leveraging the ViT network with self-supervised learning on real-face datasets to pre-train a backbone, equipping it with superior facial representation capabilities. We then build a competitive backbone fine-tuning framework that strengthens the backbone's ability to extract diverse forgery cues within a competitive learning mechanism. Moreover, we devise a threshold optimization mechanism that utilizes prediction confidence to improve the inference reliability. Comprehensive experiments demonstrate that our FFD model with the elaborate backbone achieves excellent performance in FFD and extra face-related tasks, i.e., presentation attack detection. Code and models are available at https://github.com/zhenglab/FFDBackbone.

Yuwei Chen, Zhenliang He, Jia Tang et al.

Watermarking is an important mechanism for provenance and copyright protection of diffusion-generated images. Training-free methods, exemplified by Gaussian Shading, embed watermarks into the initial noise of diffusion models with negligible impact on the quality of generated images. However, extracting this type of watermark typically requires multi-step diffusion inversion to obtain precise initial noise, which is computationally expensive and time-consuming. To address this issue, we propose One-step Inversion (OSI), a significantly faster and more accurate method for extracting Gaussian Shading style watermarks. OSI reformulates watermark extraction as a learnable sign classification problem, which eliminates the need for precise regression of the initial noise. Then, we initialize the OSI model from the diffusion backbone and finetune it on synthesized noise-image pairs with a sign classification objective. In this manner, the OSI model is able to accomplish the watermark extraction efficiently in only one step. Our OSI substantially outperforms the multi-step diffusion inversion method: it is 20x faster, achieves higher extraction accuracy, and doubles the watermark payload capacity. Extensive experiments across diverse schedulers, diffusion backbones, and cryptographic schemes consistently show improvements, demonstrating the generality of our OSI framework.

Wancheng Feng, Chen An, Zhenliang He et al.

Panorama generation has recently attracted growing interest in the research community, with two core tasks, text-to-panorama and view-to-panorama generation. However, existing methods still face two major challenges: their U-Net-based architectures constrain the visual quality of the generated panoramas, and they usually treat the two core tasks independently, which leads to modeling redundancy and inefficiency. To overcome these challenges, we propose a joint-face panorama (JoPano) generation approach that unifies the two core tasks within a DiT-based model. To transfer the rich generative capabilities of existing DiT backbones learned from natural images to the panorama domain, we propose a Joint-Face Adapter built on the cubemap representation of panoramas, which enables a pretrained DiT to jointly model and generate different views of a panorama. We further apply Poisson Blending to reduce seam inconsistencies that often appear at the boundaries between cube faces. Correspondingly, we introduce Seam-SSIM and Seam-Sobel metrics to quantitatively evaluate the seam consistency. Moreover, we propose a condition switching mechanism that unifies text-to-panorama and view-to-panorama tasks within a single model. Comprehensive experiments show that JoPano can generate high-quality panoramas for both text-to-panorama and view-to-panorama generation tasks, achieving state-of-the-art performance on FID, CLIP-FID, IS, and CLIP-Score metrics.

Haoge Deng, Ting Pan, Haiwen Diao et al.

This paper presents a novel approach that enables autoregressive video generation with high efficiency. We propose to reformulate the video generation problem as a non-quantized autoregressive modeling of temporal frame-by-frame prediction and spatial set-by-set prediction. Unlike raster-scan prediction in prior autoregressive models or joint distribution modeling of fixed-length tokens in diffusion models, our approach maintains the causal property of GPT-style models for flexible in-context capabilities, while leveraging bidirectional modeling within individual frames for efficiency. With the proposed approach, we train a novel video autoregressive model without vector quantization, termed NOVA. Our results demonstrate that NOVA surpasses prior autoregressive video models in data efficiency, inference speed, visual fidelity, and video fluency, even with a much smaller model capacity, i.e., 0.6B parameters. NOVA also outperforms state-of-the-art image diffusion models in text-to-image generation tasks, with a significantly lower training cost. Additionally, NOVA generalizes well across extended video durations and enables diverse zero-shot applications in one unified model. Code and models are publicly available at https://github.com/baaivision/NOVA.

Wenrui Liu, Hong Chang, Ruibing Hou et al.

Out-of-Distribution (OOD) detection requires sensitivity to subtle shifts without overreacting to natural In-Distribution (ID) diversity. However, from the viewpoint of detection granularity, global representation inevitably suppress local OOD cues, while patch-based methods are unstable due to entangled spurious-correlation and noise. And neither them is effective in detecting compositional OODs composed of valid ID components. Inspired by recognition-by-components theory, we present a training-free Component-Based OOD Detection (CoOD) framework that addresses the existing limitations by decomposing inputs into functional components. To instantiate CoOD, we derive Component Shift Score (CSS) to detect local appearance shifts, and Compositional Consistency Score (CCS) to identify cross-component compositional inconsistencies. Empirically, CoOD achieves consistent improvements on both coarse- and fine-grained OOD detection.

Xiaolong Tang, Meina Kan, Shiguang Shan et al.

Predicting the trajectories of road agents is essential for autonomous driving systems. The recent mainstream methods follow a static paradigm, which predicts the future trajectory by using a fixed duration of historical frames. These methods make the predictions independently even at adjacent time steps, which leads to potential instability and temporal inconsistency. As successive time steps have largely overlapping historical frames, their forecasting should have intrinsic correlation, such as overlapping predicted trajectories should be consistent, or be different but share the same motion goal depending on the road situation. Motivated by this, in this work, we introduce HPNet, a novel dynamic trajectory forecasting method. Aiming for stable and accurate trajectory forecasting, our method leverages not only historical frames including maps and agent states, but also historical predictions. Specifically, we newly design a Historical Prediction Attention module to automatically encode the dynamic relationship between successive predictions. Besides, it also extends the attention range beyond the currently visible window benefitting from the use of historical predictions. The proposed Historical Prediction Attention together with the Agent Attention and Mode Attention is further formulated as the Triple Factorized Attention module, serving as the core design of HPNet.Experiments on the Argoverse and INTERACTION datasets show that HPNet achieves state-of-the-art performance, and generates accurate and stable future trajectories. Our code are available at https://github.com/XiaolongTang23/HPNet.

Ruibing Hou, Mingyue Zhou, Yuwei Gui et al.

Faithfully modeling human behavior in dynamic environments is a foundational challenge for embodied intelligence. While conditional motion synthesis has achieved significant advances, egocentric motion generation remains largely underexplored due to the inherent complexity of first-person perception. In this work, we investigate Egocentric Vision-Language (Ego-VL) motion generation. This task requires synthesizing 3D human motion conditioned jointly on first-person visual observations and natural language instructions. We identify a critical \textit{reasoning-generation entanglement} challenge: the simultaneous optimization of semantic reasoning and kinematic modeling introduces gradient conflicts. These conflicts systematically degrade the fidelity of multimodal grounding and motion quality. To address this challenge, we propose a hierarchical generative framework \textbf{EgoMotion}. Inspired by the biological decoupling of cognitive reasoning and motor control, EgoMotion operates in two stages. In the Cognitive Reasoning stage, A vision-language model (VLM) projects multimodal inputs into a structured space of discrete motion primitives. This forces the VLM to acquire goal-consistent representations, effectively bridging the semantic gap between high-level perceptual understanding and low-level action execution. In the Motion Generation stage, these learned representations serve as expressive conditioning signals for a diffusion-based motion generator. By performing iterative denoising within a continuous latent space, the generator synthesizes physically plausible and temporally coherent trajectories. Extensive evaluations demonstrate that EgoMotion achieves state-of-the-art performance, and produces motion sequences that are both semantically grounded and kinematically superior to existing approaches.

Sibo Wang, Jie Zhang, Zheng Yuan et al.

Large-scale pre-trained vision-language models like CLIP have demonstrated impressive performance across various tasks, and exhibit remarkable zero-shot generalization capability, while they are also vulnerable to imperceptible adversarial examples. Existing works typically employ adversarial training (fine-tuning) as a defense method against adversarial examples. However, direct application to the CLIP model may result in overfitting, compromising the model's capacity for generalization. In this paper, we propose Pre-trained Model Guided Adversarial Fine-Tuning (PMG-AFT) method, which leverages supervision from the original pre-trained model by carefully designing an auxiliary branch, to enhance the model's zero-shot adversarial robustness. Specifically, PMG-AFT minimizes the distance between the features of adversarial examples in the target model and those in the pre-trained model, aiming to preserve the generalization features already captured by the pre-trained model. Extensive Experiments on 15 zero-shot datasets demonstrate that PMG-AFT significantly outperforms the state-of-the-art method, improving the top-1 robust accuracy by an average of 4.99%. Furthermore, our approach consistently improves clean accuracy by an average of 8.72%. Our code is available at https://github.com/serendipity1122/Pre-trained-Model-Guided-Fine-Tuning-for-Zero-Shot-Adversarial-Robustness.

Yin Chen, Jia Li, Yu Zhang et al.

Dynamic facial expression recognition (DFER) infers emotions from the temporal evolution of expressions, unlike static facial expression recognition (SFER), which relies solely on a single snapshot. This temporal analysis provides richer information and promises greater recognition capability. However, current DFER methods often exhibit unsatisfied performance largely due to fewer training samples compared to SFER. Given the inherent correlation between static and dynamic expressions, we hypothesize that leveraging the abundant SFER data can enhance DFER. To this end, we propose Static-for-Dynamic (S4D), a unified dual-modal learning framework that integrates SFER data as a complementary resource for DFER. Specifically, S4D employs dual-modal self-supervised pre-training on facial images and videos using a shared Vision Transformer (ViT) encoder-decoder architecture, yielding improved spatiotemporal representations. The pre-trained encoder is then fine-tuned on static and dynamic expression datasets in a multi-task learning setup to facilitate emotional information interaction. Unfortunately, vanilla multi-task learning in our study results in negative transfer. To address this, we propose an innovative Mixture of Adapter Experts (MoAE) module that facilitates task-specific knowledge acquisition while effectively extracting shared knowledge from both static and dynamic expression data. Extensive experiments demonstrate that S4D achieves a deeper understanding of DFER, setting new state-of-the-art performance on FERV39K, MAFW, and DFEW benchmarks, with weighted average recall (WAR) of 53.65\%, 58.44\%, and 76.68\%, respectively. Additionally, a systematic correlation analysis between SFER and DFER tasks is presented, which further elucidates the potential benefits of leveraging SFER.

Ting Pan, Lulu Tang, Xinlong Wang et al.

We present a unified, promptable model capable of simultaneously segmenting, recognizing, and captioning anything. Unlike SAM, we aim to build a versatile region representation in the wild via visual prompting. To achieve this, we train a generalizable model with massive segmentation masks, \eg, SA-1B masks, and semantic priors from a pre-trained CLIP model with 5 billion parameters. Specifically, we construct a promptable image decoder by adding a semantic token to each mask token. The semantic token is responsible for learning the semantic priors in a predefined concept space. Through joint optimization of segmentation on mask tokens and concept prediction on semantic tokens, our model exhibits strong regional recognition and localization capabilities. For example, an additional 38M-parameter causal text decoder trained from scratch sets a new record with a CIDEr score of 164.7 on the Visual Genome region captioning task. We believe this model can be a versatile region-level image tokenizer, capable of encoding general-purpose region context for a broad range of visual perception tasks. Code and models are available at {\footnotesize \url{https://github.com/baaivision/tokenize-anything}}.

Hao Lu, Xuesong Niu, Jiyao Wang et al.

Multimodal large language models (MLLMs) are designed to process and integrate information from multiple sources, such as text, speech, images, and videos. Despite its success in language understanding, it is critical to evaluate the performance of downstream tasks for better human-centric applications. This paper assesses the application of MLLMs with 5 crucial abilities for affective computing, spanning from visual affective tasks and reasoning tasks. The results show that \gpt has high accuracy in facial action unit recognition and micro-expression detection while its general facial expression recognition performance is not accurate. We also highlight the challenges of achieving fine-grained micro-expression recognition and the potential for further study and demonstrate the versatility and potential of \gpt for handling advanced tasks in emotion recognition and related fields by integrating with task-related agents for more complex tasks, such as heart rate estimation through signal processing. In conclusion, this paper provides valuable insights into the potential applications and challenges of MLLMs in human-centric computing. Our interesting examples are at https://github.com/EnVision-Research/GPT4Affectivity.

Jie Zhang, Shuai Dong, Shiguang Shan et al.

Recent progress in text-to-image diffusion models has transformed image editing via text prompts, yet this also introduces significant ethical challenges from potential misuse in creating deceptive or harmful content. While current defenses seek to mitigate this risk by embedding imperceptible perturbations, their effectiveness is limited against malicious tampering. To address this issue, we propose a Dual Attention-Guided Noise Perturbation (DANP) immunization method that adds imperceptible perturbations to disrupt the model's semantic understanding and generation process. DANP functions over multiple timesteps to manipulate both cross-attention maps and the noise prediction process, using a dynamic threshold to generate masks that identify text-relevant and irrelevant regions. It then reduces attention in relevant areas while increasing it in irrelevant ones, thereby misguides the edit towards incorrect regions and preserves the intended targets. Additionally, our method maximizes the discrepancy between the injected noise and the model's predicted noise to further interfere with the generation. By targeting both attention and noise prediction mechanisms, DANP exhibits impressive immunity against malicious edits, and extensive experiments confirm that our method achieves state-of-the-art performance.

Shuai Dong, Jie Zhang, Guoying Zhao et al.

Text-guided image editing via diffusion models, while powerful, raises significant concerns about misuse, motivating efforts to immunize images against unauthorized edits using imperceptible perturbations. Prevailing metrics for evaluating immunization success typically rely on measuring the visual dissimilarity between the output generated from a protected image and a reference output generated from the unprotected original. This approach fundamentally overlooks the core requirement of image immunization, which is to disrupt semantic alignment with attacker intent, regardless of deviation from any specific output. We argue that immunization success should instead be defined by the edited output either semantically mismatching the prompt or suffering substantial perceptual degradations, both of which thwart malicious intent. To operationalize this principle, we propose Synergistic Intermediate Feature Manipulation (SIFM), a method that strategically perturbs intermediate diffusion features through dual synergistic objectives: (1) maximizing feature divergence from the original edit trajectory to disrupt semantic alignment with the expected edit, and (2) minimizing feature norms to induce perceptual degradations. Furthermore, we introduce the Immunization Success Rate (ISR), a novel metric designed to rigorously quantify true immunization efficacy for the first time. ISR quantifies the proportion of edits where immunization induces either semantic failure relative to the prompt or significant perceptual degradations, assessed via Multimodal Large Language Models (MLLMs). Extensive experiments show our SIFM achieves the state-of-the-art performance for safeguarding visual content against malicious diffusion-based manipulation.

Haoze Li, Jie Zhang, Guoying Zhao et al.

Face Presentation Attack Detection (PAD) demands incremental learning (IL) to combat evolving spoofing tactics and domains. Privacy regulations, however, forbid retaining past data, necessitating rehearsal-free IL (RF-IL). Vision-Language Pre-trained (VLP) models, with their prompt-tunable cross-modal representations, enable efficient adaptation to new spoofing styles and domains. Capitalizing on this strength, we propose \textbf{SVLP-IL}, a VLP-based RF-IL framework that balances stability and plasticity via \textit{Multi-Aspect Prompting} (MAP) and \textit{Selective Elastic Weight Consolidation} (SEWC). MAP isolates domain dependencies, enhances distribution-shift sensitivity, and mitigates forgetting by jointly exploiting universal and domain-specific cues. SEWC selectively preserves critical weights from previous tasks, retaining essential knowledge while allowing flexibility for new adaptations. Comprehensive experiments across multiple PAD benchmarks show that SVLP-IL significantly reduces catastrophic forgetting and enhances performance on unseen domains. SVLP-IL offers a privacy-compliant, practical solution for robust lifelong PAD deployment in RF-IL settings.

Chunhui Zhang, Yawen Cui, Weilin Lin et al.

The recent wave of foundation models has witnessed tremendous success in computer vision (CV) and beyond, with the segment anything model (SAM) having sparked a passion for exploring task-agnostic visual foundation models. Empowered by its remarkable zero-shot generalization, SAM is currently challenging numerous traditional paradigms in CV, delivering extraordinary performance not only in various image segmentation and multi-modal segmentation (\eg, text-to-mask) tasks, but also in the video domain. Additionally, the latest released SAM 2 is once again sparking research enthusiasm in the realm of promptable visual segmentation for both images and videos. However, existing surveys mainly focus on SAM in various image processing tasks, a comprehensive and in-depth review in the video domain is notably absent. To address this gap, this work conducts a systematic review on SAM for videos in the era of foundation models. As the first to review the progress of SAM for videos, this work focuses on its applications to various tasks by discussing its recent advances, and innovation opportunities of developing foundation models on broad applications. We begin with a brief introduction to the background of SAM and video-related research domains. Subsequently, we present a systematic taxonomy that categorizes existing methods into three key areas: video understanding, video generation, and video editing, analyzing and summarizing their advantages and limitations. Furthermore, comparative results of SAM-based and current state-of-the-art methods on representative benchmarks, as well as insightful analysis are offered. Finally, we discuss the challenges faced by current research and envision several future research directions in the field of SAM for video and beyond.

Sen Nie, Jie Zhang, Zhuo Wang et al.

Vision-language models (VLMs) such as CLIP have demonstrated remarkable zero-shot generalization, yet remain highly vulnerable to adversarial examples (AEs). While test-time defenses are promising, existing methods fail to provide sufficient robustness against strong attacks and are often hampered by high inference latency and task-specific applicability. To address these limitations, we start by investigating the intrinsic properties of AEs, which reveals that AEs exhibit severe feature inconsistency under progressive frequency attenuation. We further attribute this to the model's inherent spectral bias. Leveraging this insight, we propose an efficient test-time defense named Contrastive Spectral Rectification (CSR). CSR optimizes a rectification perturbation to realign the input with the natural manifold under a spectral-guided contrastive objective, which is applied input-adaptively. Extensive experiments across 16 classification benchmarks demonstrate that CSR outperforms the SOTA by an average of 18.1% against strong AutoAttack with modest inference overhead. Furthermore, CSR exhibits broad applicability across diverse visual tasks. Code is available at https://github.com/Summu77/CSR.

Yifeng Xu, Zhenliang He, Shiguang Shan et al.

Recently, large-scale diffusion models have made impressive progress in text-to-image (T2I) generation. To further equip these T2I models with fine-grained spatial control, approaches like ControlNet introduce an extra network that learns to follow a condition image. However, for every single condition type, ControlNet requires independent training on millions of data pairs with hundreds of GPU hours, which is quite expensive and makes it challenging for ordinary users to explore and develop new types of conditions. To address this problem, we propose the CtrLoRA framework, which trains a Base ControlNet to learn the common knowledge of image-to-image generation from multiple base conditions, along with condition-specific LoRAs to capture distinct characteristics of each condition. Utilizing our pretrained Base ControlNet, users can easily adapt it to new conditions, requiring as few as 1,000 data pairs and less than one hour of single-GPU training to obtain satisfactory results in most scenarios. Moreover, our CtrLoRA reduces the learnable parameters by 90% compared to ControlNet, significantly lowering the threshold to distribute and deploy the model weights. Extensive experiments on various types of conditions demonstrate the efficiency and effectiveness of our method. Codes and model weights will be released at https://github.com/xyfJASON/ctrlora.

Bei Yan, Jie Zhang, Zhiyuan Chen et al.

Recently, large foundation models, including large language models (LLMs) and large vision-language models (LVLMs), have become essential tools in critical fields such as law, finance, and healthcare. As these models increasingly integrate into our daily life, it is necessary to conduct moral evaluation to ensure that their outputs align with human values and remain within moral boundaries. Previous works primarily focus on LLMs, proposing moral datasets and benchmarks limited to text modality. However, given the rapid development of LVLMs, there is still a lack of multimodal moral evaluation methods. To bridge this gap, we introduce M$^3$oralBench, the first MultiModal Moral Benchmark for LVLMs. M$^3$oralBench expands the everyday moral scenarios in Moral Foundations Vignettes (MFVs) and employs the text-to-image diffusion model, SD3.0, to create corresponding scenario images. It conducts moral evaluation across six moral foundations of Moral Foundations Theory (MFT) and encompasses tasks in moral judgement, moral classification, and moral response, providing a comprehensive assessment of model performance in multimodal moral understanding and reasoning. Extensive experiments on 10 popular open-source and closed-source LVLMs demonstrate that M$^3$oralBench is a challenging benchmark, exposing notable moral limitations in current models. Our benchmark is publicly available.

Changzhen Li, Yuecong Min, Jie Zhang et al.

The rapid evolution of Text-to-Video (T2V) diffusion models has driven remarkable advancements in generating high-quality, temporally coherent videos from natural language descriptions. Despite these achievements, their vulnerability to adversarial attacks remains largely unexplored. In this paper, we introduce T2VAttack, a comprehensive study of adversarial attacks on T2V diffusion models from both semantic and temporal perspectives. Considering the inherently dynamic nature of video data, we propose two distinct attack objectives: a semantic objective to evaluate video-text alignment and a temporal objective to assess the temporal dynamics. To achieve an effective and efficient attack process, we propose two adversarial attack methods: (i) T2VAttack-S, which identifies semantically or temporally critical words in prompts and replaces them with synonyms via greedy search, and (ii) T2VAttack-I, which iteratively inserts optimized words with minimal perturbation to the prompt. By combining these objectives and strategies, we conduct a comprehensive evaluation on the adversarial robustness of several state-of-the-art T2V models, including ModelScope, CogVideoX, Open-Sora, and HunyuanVideo. Our experiments reveal that even minor prompt modifications, such as the substitution or insertion of a single word, can cause substantial degradation in semantic fidelity and temporal dynamics, highlighting critical vulnerabilities in current T2V diffusion models.

Xuanyu Ge, Zhongqi Wang, Jie Zhang et al.

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to backdoor attacks. Existing defense methods predominantly focus on sample-level defense, which relies on the knowledge of training data or triggers. However, identifying whether a given model is backdoored remains a critical but unexplored task. To fill this gap, we propose EntropyScan, a lightweight and trigger-agnostic method for model-level backdoor detection in LVLMs. We first observe that backdoor injection disrupts the cross-modal alignment, resulting in pronounced structural anomalies in visual attention allocation on benign samples. Based on this insight, EntropyScan detects the backdoor models by quantifying such attention deviations. Specifically, it extracts visual attention distributions from the initial layers of the Large Language Model (LLM) and applies Tsallis entropy to capture these structural distortions. By employing a reference-anchored Z-score normalization on a small set of benign samples, it effectively identifies the backdoored model. Extensive experiments across two LVLMs architectures and three advanced attack scenarios show that EntropyScan achieves an F1 score of 98.5% in average and an AUC of 96.6%. Our code will be publicly available soon.

Xiaolong Tang, Meina Kan, Shiguang Shan et al.

Safe and feasible trajectory planning is critical for real-world autonomous driving systems. However, existing learning-based planners rely heavily on expert demonstrations, which not only lack explicit safety awareness but also risk inheriting undesirable behaviors such as speeding from suboptimal human driving data. Inspired by the success of large language models, we propose Plan-R1, a two-stage trajectory planning framework that decouples principle alignment from behavior learning. In the first stage, a general trajectory predictor is pre-trained on expert data to capture diverse, human-like driving behaviors. In the second stage, the model is fine-tuned with rule-based rewards using Group Relative Policy Optimization (GRPO), explicitly aligning ego planning with principles such as safety, comfort, and traffic rule compliance. This two-stage paradigm retains human-like behaviors while enhancing safety awareness and discarding undesirable patterns from demonstrations. Furthermore, we identify a key limitation of directly applying GRPO to planning: group-wise normalization erases cross-group scale differences, causing rare, high-variance safety-violation groups to have similar advantages as abundant low-variance safe groups, thereby suppressing optimization for safety-critical objectives. To address this, we propose Variance-Decoupled GRPO (VD-GRPO), which replaces normalization with centering and fixed scaling to preserve absolute reward magnitudes, ensuring that safety-critical objectives remain dominant throughout training. Experiments on the nuPlan benchmark demonstrate that Plan-R1 significantly improves planning safety and feasibility, achieving state-of-the-art performance, particularly in realistic reactive settings. Our code is available at https://github.com/XiaolongTang23/Plan-R1.

Jiahe Zhao, Ruibing Hou, Zejie Tian et al.

We propose a new task to benchmark human-in-scene understanding for embodied agents: Human-In-Scene Question Answering (HIS-QA). Given a human motion within a 3D scene, HIS-QA requires the agent to comprehend human states and behaviors, reason about its surrounding environment, and answer human-related questions within the scene. To support this new task, we present HIS-Bench, a multimodal benchmark that systematically evaluates HIS understanding across a broad spectrum, from basic perception to commonsense reasoning and planning. Our evaluation of various vision-language models on HIS-Bench reveals significant limitations in their ability to handle HIS-QA tasks. To this end, we propose HIS-GPT, the first foundation model for HIS understanding. HIS-GPT integrates 3D scene context and human motion dynamics into large language models while incorporating specialized mechanisms to capture human-scene interactions. Extensive experiments demonstrate that HIS-GPT sets a new state-of-the-art on HIS-QA tasks. We hope this work inspires future research on human behavior analysis in 3D scenes, advancing embodied AI and world models. The codes and data: https://github.com/ZJHTerry18/HumanInScene.

Jia Li, Yu Zhang, Yin Chen et al.

Facial action unit (AU) detection and facial expression (FE) recognition can be jointly viewed as affective facial behavior tasks, representing fine-grained muscular activations and coarse-grained holistic affective states, respectively. Despite their inherent semantic correlation, existing studies predominantly focus on knowledge transfer from AUs to FEs, while bidirectional learning remains insufficiently explored. In practice, this challenge is further compounded by heterogeneous data conditions, where AU and FE datasets differ in annotation paradigms (frame-level vs.\ clip-level), label granularity, and data availability and diversity, hindering effective joint learning. To address these issues, we propose a Structured Semantic Mapping (SSM) framework for bidirectional AU--FE learning under different data domains and heterogeneous supervision. SSM consists of three key components: (1) a shared visual backbone that learns unified facial representations from dynamic AU and FE videos; (2) semantic mediation via a Textual Semantic Prototype (TSP) module, which constructs structured semantic prototypes from fixed textual descriptions augmented with learnable context prompts, serving as supervision signals and cross-task alignment anchors in a shared semantic space; and (3) a Dynamic Prior Mapping (DPM) module that incorporates prior knowledge derived from the Facial Action Coding System and learns a data-driven association matrix in a high-level feature space, enabling explicit and bidirectional knowledge transfer. Extensive experiments on popular AU detection and FE recognition benchmarks show that SSM achieves state-of-the-art performance on both tasks simultaneously, and demonstrate that holistic expression semantics can in turn enhance fine-grained AU learning even across heterogeneous datasets.

Keliang Li, Yansong Li, Hongze Shen et al.

The dense, temporal nature of video presents a profound challenge for automated analysis. Despite the use of powerful Vision-Language Models, prevailing methods for video understanding are limited by the inherent disconnect between reasoning and perception: they rely on static, pre-processed information and cannot actively seek raw evidence from video as their understanding evolves. To address this, we introduce LensWalk, a flexible agentic framework that empowers a Large Language Model reasoner to control its own visual observation actively. LensWalk establishes a tight reason-plan-observe loop where the agent dynamically specifies, at each step, the temporal scope and sampling density of the video it observes. Using a suite of versatile, Vision-Language Model based tools parameterized by these specifications, the agent can perform broad scans for cues, focus on specific segments for fact extraction, and stitch evidence from multiple moments for holistic verification. This design allows for progressive, on-demand evidence gathering that directly serves the agent's evolving chain of thought. Without requiring any model fine-tuning, LensWalk delivers substantial, plug-and-play performance gains on multiple model recipes, boosting their accuracy by over 5\% on challenging long-video benchmarks like LVBench and Video-MME. Our analysis reveals that enabling an agent to control how it sees is key to unlocking more accurate, robust, and interpretable video reasoning.

Haoge Deng, Ting Pan, Fan Zhang et al.

Continuous-space video generation has advanced rapidly, while discrete approaches lag behind due to error accumulation and long-context inconsistency. In this work, we revisit discrete generative modeling and present Uniform discRete diffuSion with metric pAth (URSA), a simple yet powerful framework that bridges the gap with continuous approaches for the scalable video generation. At its core, URSA formulates the video generation task as an iterative global refinement of discrete spatiotemporal tokens. It integrates two key designs: a Linearized Metric Path and a Resolution-dependent Timestep Shifting mechanism. These designs enable URSA to scale efficiently to high-resolution image synthesis and long-duration video generation, while requiring significantly fewer inference steps. Additionally, we introduce an asynchronous temporal fine-tuning strategy that unifies versatile tasks within a single model, including interpolation and image-to-video generation. Extensive experiments on challenging video and image generation benchmarks demonstrate that URSA consistently outperforms existing discrete methods and achieves performance comparable to state-of-the-art continuous diffusion methods. Code and models are available at https://github.com/baaivision/URSA

Yinqi Li, Jiahe Zhao, Hong Chang et al.

Contrastive Language-Image Pre-training (CLIP) has become a foundation model and has been applied to various vision and multimodal tasks. However, recent works indicate that CLIP falls short in distinguishing detailed differences in images and shows suboptimal performance on dense-prediction and vision-centric multimodal tasks. Therefore, this work focuses on improving existing CLIP models, aiming to capture as many visual details in images as possible. We find that a specific type of generative models, unCLIP, provides a suitable framework for achieving our goal. Specifically, unCLIP trains an image generator conditioned on the CLIP image embedding. In other words, it inverts the CLIP image encoder. Compared to discriminative models like CLIP, generative models are better at capturing image details because they are trained to learn the data distribution of images. Additionally, the conditional input space of unCLIP aligns with CLIP's original image-text embedding space. Therefore, we propose to invert unCLIP (dubbed un$^2$CLIP) to improve the CLIP model. In this way, the improved image encoder can gain unCLIP's visual detail capturing ability while preserving its alignment with the original text encoder simultaneously. We evaluate our improved CLIP across various tasks to which CLIP has been applied, including the challenging MMVP-VLM benchmark, the dense-prediction open-vocabulary segmentation task, and multimodal large language model tasks. Experiments show that un$^2$CLIP significantly improves the original CLIP and previous CLIP improvement methods. Code and models will be available at https://github.com/LiYinqi/un2CLIP.

Jie Zhang, Zheng Yuan, Zhongqi Wang et al.

The rapid evolution of Large Vision-Language Models (LVLMs) has highlighted the necessity for comprehensive evaluation frameworks that assess these models across diverse dimensions. While existing benchmarks focus on specific aspects such as perceptual abilities, cognitive capabilities, and safety against adversarial attacks, they often lack the breadth and depth required to provide a holistic understanding of LVLMs' strengths and limitations. To address this gap, we introduce REVAL, a comprehensive benchmark designed to evaluate the \textbf{RE}liability and \textbf{VAL}ue of LVLMs. REVAL encompasses over 144K image-text Visual Question Answering (VQA) samples, structured into two primary sections: Reliability, which assesses truthfulness (\eg, perceptual accuracy and hallucination tendencies) and robustness (\eg, resilience to adversarial attacks, typographic attacks, and image corruption), and Values, which evaluates ethical concerns (\eg, bias and moral understanding), safety issues (\eg, toxicity and jailbreak vulnerabilities), and privacy problems (\eg, privacy awareness and privacy leakage). We evaluate 26 models, including mainstream open-source LVLMs and prominent closed-source models like GPT-4o and Gemini-1.5-Pro. Our findings reveal that while current LVLMs excel in perceptual tasks and toxicity avoidance, they exhibit significant vulnerabilities in adversarial scenarios, privacy preservation, and ethical reasoning. These insights underscore critical areas for future improvements, guiding the development of more secure, reliable, and ethically aligned LVLMs. REVAL provides a robust framework for researchers to systematically assess and compare LVLMs, fostering advancements in the field.

Zhongqi Wang, Jie Zhang, Shiguang Shan et al.

Recent studies have revealed that text-to-image diffusion models are vulnerable to backdoor attacks, where attackers implant stealthy textual triggers to manipulate model outputs. Previous backdoor detection methods primarily focus on the static features of backdoor samples. However, a vital property of diffusion models is their inherent dynamism. This study introduces a novel backdoor detection perspective named Dynamic Attention Analysis (DAA), showing that these dynamic characteristics serve as better indicators for backdoor detection. Specifically, by examining the dynamic evolution of cross-attention maps, we observe that backdoor samples exhibit distinct feature evolution patterns at the $<$EOS$>$ token compared to benign samples. To quantify these dynamic anomalies, we first introduce DAA-I, which treats the tokens' attention maps as spatially independent and measures dynamic feature using the Frobenius norm. Furthermore, to better capture the interactions between attention maps and refine the feature, we propose a dynamical system-based approach, referred to as DAA-S. This model formulates the spatial correlations among attention maps using a graph-based state equation and we theoretically analyze the global asymptotic stability of this method. Extensive experiments across five representative backdoor attack scenarios demonstrate that our approach significantly surpasses existing detection methods, achieving an average F1 Score of 79.49% and an AUC of 87.67%. The code is available at https://github.com/Robin-WZQ/DAA.

Jie Huang, Ruibing Hou, Jiahe Zhao et al.

Human-centric perceptions play a crucial role in real-world applications. While recent human-centric works have achieved impressive progress, these efforts are often constrained to the visual domain and lack interaction with human instructions, limiting their applicability in broader scenarios such as chatbots and sports analysis. This paper introduces Referring Human Perceptions, where a referring prompt specifies the person of interest in an image. To tackle the new task, we propose RefHCM (Referring Human-Centric Model), a unified framework to integrate a wide range of human-centric referring tasks. Specifically, RefHCM employs sequence mergers to convert raw multimodal data -- including images, text, coordinates, and parsing maps -- into semantic tokens. This standardized representation enables RefHCM to reformulate diverse human-centric referring tasks into a sequence-to-sequence paradigm, solved using a plain encoder-decoder transformer architecture. Benefiting from a unified learning strategy, RefHCM effectively facilitates knowledge transfer across tasks and exhibits unforeseen capabilities in handling complex reasoning. This work represents the first attempt to address referring human perceptions with a general-purpose framework, while simultaneously establishing a corresponding benchmark that sets new standards for the field. Extensive experiments showcase RefHCM's competitive and even superior performance across multiple human-centric referring tasks. The code and data are publicly at https://github.com/JJJYmmm/RefHCM.

Jiachen Liang, Ruibing Hou, Minyang Hu et al.

Pre-trained vision-language models (e.g., CLIP) have shown powerful zero-shot transfer capabilities. But they still struggle with domain shifts and typically require labeled data to adapt to downstream tasks, which could be costly. In this work, we aim to leverage unlabeled data that naturally spans multiple domains to enhance the transferability of vision-language models. Under this unsupervised multi-domain setting, we have identified inherent model bias within CLIP, notably in its visual and text encoders. Specifically, we observe that CLIP's visual encoder tends to prioritize encoding domain over discriminative category information, meanwhile its text encoder exhibits a preference for domain-relevant classes. To mitigate this model bias, we propose a training-free and label-free feature calibration method, Unsupervised Multi-domain Feature Calibration (UMFC). UMFC estimates image-level biases from domain-specific features and text-level biases from the direction of domain transition. These biases are subsequently subtracted from original image and text features separately, to render them domain-invariant. We evaluate our method on multiple settings including transductive learning and test-time adaptation. Extensive experiments show that our method outperforms CLIP and performs on par with the state-of-the-arts that need additional annotations or optimization. Our code is available at https://github.com/GIT-LJc/UMFC.

Sen Nie, Jie Zhang, Jianxin Yan et al.

Adversarial attacks have evolved from simply disrupting predictions on conventional task-specific models to the more complex goal of manipulating image semantics on Large Vision-Language Models (LVLMs). However, existing methods struggle with controllability and fail to precisely manipulate the semantics of specific concepts in the image. We attribute this limitation to semantic entanglement in the patch-token representations on which adversarial attacks typically operate: global context aggregated by self-attention in the vision encoder dominates individual patch features, making them unreliable handles for precise local semantic manipulation. Our systematic investigation reveals a key insight: value features (V) computed within the transformer attention block serve as much more precise handles for manipulation. We show that V suppresses global-context channels, allowing it to retain high-entropy, disentangled local semantic information. Building on this discovery, we propose V-Attack, a novel method designed for precise local semantic attacks. V-Attack targets the value features and introduces two core components: (1) a Self-Value Enhancement module to refine V's intrinsic semantic richness, and (2) a Text-Guided Value Manipulation module that leverages text prompts to locate source concept and optimize it toward a target concept. By bypassing the entangled patch features, V-Attack achieves highly effective semantic control. Extensive experiments across diverse LVLMs, including LLaVA, InternVL, DeepseekVL and GPT-4o, show that V-Attack improves the attack success rate by an average of 36% over state-of-the-art methods, exposing critical vulnerabilities in modern visual-language understanding. Our code and data are available https://github.com/Summu77/V-Attack.

Jiachen Liang, Ruibing Hou, Minyang Hu et al.

Out-of-distribution (OOD) detection is critical for ensuring the reliability of deep learning models in open-world applications. While post-hoc methods are favored for their efficiency and ease of deployment, existing approaches often underexploit the rich information embedded in the model's logits space. In this paper, we propose LogitGap, a novel post-hoc OOD detection method that explicitly exploits the relationship between the maximum logit and the remaining logits to enhance the separability between in-distribution (ID) and OOD samples. To further improve its effectiveness, we refine LogitGap by focusing on a more compact and informative subset of the logit space. Specifically, we introduce a training-free strategy that automatically identifies the most informative logits for scoring. We provide both theoretical analysis and empirical evidence to validate the effectiveness of our approach. Extensive experiments on both vision-language and vision-only models demonstrate that LogitGap consistently achieves state-of-the-art performance across diverse OOD detection scenarios and benchmarks. Code is available at https://github.com/GIT-LJc/LogitGap.

Zaifei Yang, Hong Chang, Ruibing Hou et al.

The molecular large language models have garnered widespread attention due to their promising potential on molecular applications. However, current molecular large language models face significant limitations in understanding molecules due to inadequate textual descriptions and suboptimal molecular representation strategies during pretraining. To address these challenges, we introduce KnowMol-100K, a large-scale dataset with 100K fine-grained molecular annotations across multiple levels, bridging the gap between molecules and textual descriptions. Additionally, we propose chemically-informative molecular representation, effectively addressing limitations in existing molecular representation strategies. Building upon these innovations, we develop KnowMol, a state-of-the-art multi-modal molecular large language model. Extensive experiments demonstrate that KnowMol achieves superior performance across molecular understanding and generation tasks. GitHub: https://github.com/yzf-code/KnowMol Huggingface: https://hf.co/datasets/yzf1102/KnowMol-100K

Yujie Wang, Yunwei Zhao, Jing Yang et al.

Digital social media platforms frequently contribute to cognitive-behavioral fixation, a phenomenon in which users exhibit sustained and repetitive engagement with narrow content domains. While cognitive-behavioral fixation has been extensively studied in psychology, methods for computationally detecting and evaluating such fixation remain underexplored. To address this gap, we propose a novel framework for assessing cognitive-behavioral fixation by analyzing users' multimodal social media engagement patterns. Specifically, we introduce a multimodal topic extraction module and a cognitive-behavioral fixation quantification module that collaboratively enable adaptive, hierarchical, and interpretable assessment of user behavior. Experiments on existing benchmarks and a newly curated multimodal dataset demonstrate the effectiveness of our approach, laying the groundwork for scalable computational analysis of cognitive fixation. All code in this project is publicly available for research purposes at https://github.com/Liskie/cognitive-fixation-evaluation.