论文检索

Sisi You, Bowen Yuan, Bing-Kun Bao

Video understanding seeks to enable machines to interpret visual content across three levels: action, event, and story. Existing models are limited in their ability to perform high-level long-term story understanding, due to (1) the oversimplified treatment of temporal information and (2) the training bias introduced by action/event-centric datasets. To address this, we introduce SCVBench, a novel benchmark for story-centric video understanding. SCVBench evaluates LVLMs through an event ordering task decomposed into sub-questions leading to a final question, quantitatively measuring historical dialogue exploration. We collected 1,253 final questions and 6,027 sub-question pairs from 925 videos, constructing continuous multi-turn dialogues. Experimental results show that while closed-source GPT-4o outperforms other models, most open-source LVLMs struggle with story-centric video understanding. Additionally, our StoryCoT model significantly surpasses open-source LVLMs on SCVBench. SCVBench aims to advance research by comprehensively analyzing LVLMs' temporal reasoning and comprehension capabilities. Code can be accessed at https://github.com/yuanrr/SCVBench.

Rui Yan, Jin Wang, Hongyu Qu, Xiaoyu Du, Dong Zhang, Jinhui Tang, Tieniu Tan

Recently, adapting Vision Language Models (VLMs) to zero-shot visual classification by tuning class embedding with a few prompts (Test-time Prompt Tuning, TPT) or replacing class names with generated visual samples (support-set) has shown promising results. However, TPT cannot avoid the semantic gap between modalities while the support-set cannot be tuned. To this end, we draw on each other's strengths and propose a novel framework, namely TEst-time Support-set Tuning for zero-shot Video Classification (TEST-V). It first dilates the support-set with multiple prompts (Multi-prompting Support-set Dilation, MSD) and then erodes the support-set via learnable weights to mine key cues dynamically (Temporal-aware Support-set Erosion, TSE). Specifically, i) MSD expands the support samples for each class based on multiple prompts inquired from LLMs to enrich the diversity of the support-set. ii) TSE tunes the support-set with factorized learnable weights according to the temporal prediction consistency in a self-supervised manner to dig pivotal supporting cues for each class. TEST-V achieves state-of-the-art results across four benchmarks and shows good interpretability.

Siyuan Xu, Haofei Song, Yingjiao Deng, Jiansheng Wang, Yan Wang, Qingli Li

Histopathological examination primarily relies on hematoxylin and eosin (H&E) and immunohistochemical (IHC) staining. Though IHC provides more crucial molecular information for diagnosis, it is more costly than H&E staining. Stain transfer technology seeks to efficiently generate virtual IHC images from H&E images. While current deep learning-based methods have made progress, they still struggle to maintain pathological and structural consistency across biomarkers without pixel-level aligned reference. To address the problem, we propose an Auxiliary Task supervision-based Stain Transfer method for multi-biomarkers (ATST-Net), which pioneeringly employs human annotation-free masks as ground truth (GT). ATST-Net ensures pathological consistency, structural preservation and style transfer. It automatically annotates H&E masks in a cost-effective manner by utilizing consecutive IHC sections. Multiple auxiliary tasks provide diverse supervisory information on the location and intensity of biomarker expression, ensuring model accuracy and interpretability. We design a pretrained model-based generator to extract deep feature in H&E images, improving generalization performance. Extensive experiments demonstrate the effectiveness of ATST-Net's components. Compared to existing methods, ATST-Net achieves state-of-the-art (SOTA) accuracy on datasets with multiple biomarkers and intensity levels, while also reflecting high practical value. Code is available at https://github.com/SikangSHU/ATST-Net.

Xiaoxi Sun, Jianxin Liang, Yueqian Wang, Huishuai Zhang, Dongyan Zhao

Understanding small visual objects is crucial in fields such as video surveillance, remote sensing, and autonomous driving. In this paper, we investigate the capability of advanced large vision-language models (LVLMs) to recognize and interpret small objects in visual data. To this end, we curate a specialized dataset for evaluating fine-grained visual hallucinations, incorporating two object categories and three types of hallucinations. First, we assess 11 state-of-the-art LVLMs, yielding several key insights, as anticipated, LVLMs perform significantly worse on queries related to small objects compared to regular-sized ones, with performance on regular objects proving to be an unreliable predictor of that on small objects. This finding underscores the need for dedicated research on fine-grained visual hallucinations. Second, we evaluate three training-free methods: Scaffold, Chain of Thought (CoT), and Image Resizing, all of which result in varying degrees of improvement. Furthermore, we conduct a series of detailed ablation studies on the visual encoders of Eagle-X5, examining their performance across fine-grained visual hallucination tasks. Our findings reveal that ConvNeXt architecture is critical for object existence recognition tasks. In contrast, for mitigating other types of hallucinations, integrating information from multiple visual encoders is significantly more effective than relying on a single encoder. These results highlight several promising directions for advancing small object recognition with LVLMs.

Yong Su, Defang Chen, Meng Xing, Changjae Oh, Xuewei Liu, Jieyang Li

Human pose estimation in low-light conditions is vital for applications such as surveillance and autonomous systems, yet the severe visual distortions hinder both manual annotation and estimation precision. Existing approaches typically rely on additional reference information to mitigate these issues, however, customized data collection equipment poses limitations on their scalability. To alleviate the issue, we construct a Low-Light Images and Poses (LLIP) dataset, which includes only paired low-light images and pose annotations obtained using off-the-shelf motion capture devices. Furthermore, we propose a Multi-grained High-frequency Feature Consistency Learning framework (MHFCL), which does not rely on additional reference information. MHFCL employs a Retinex-inspired restoration stream to recover high-frequency details and integrates them into pose estimation using a multi-grained consistency mechanism. Experiments demonstrate that our approach achieves a new benchmark in low-light pose estimation, while maintaining competitive performance in well-lit conditions.

Biao Liu, Xu Liu, Lingling Li, Licheng Jiao, Fang Liu, Xinyu Sun, Youlin Huang

Visual grounding (VG) refers to detecting the specific objects in images based on linguistic expressions, and it has profound significance in the advanced interpretation of natural images. In remote sensing image interpretation, visual grounding is limited by characteristics such as the complex scenes and diverse object sizes. To solve this problem, we propose a novel remote sensing visual grounding (RSVG) framework, named language-guided hybrid representation learning Transformer (LGFormer). Specifically, we designed a multimodal dual-encoder Transformer structure called the adaptive multimodal feature fusion module. This structure innovatively integrates text and visual features as hybrid queries, enabling early-stage decoding queries to perceive the target position accurately. Then, the different modal information from the dual encoders is aggregated by hybrid queries to obtain the final object embedding for coordinate regression. Besides, a multi-scale cross-modal feature enhancement module (MSCM) is designed to enhance the self-representation of the extracted text and visual features and align them semantically. As for the hybrid queries, we use linguistic guidance to select visual features as the visual part and sentence-level features as the textual part. Finally, the LGFormer model we designed achieved the best results compared to existing models on the DIOR-RSVG and OPT-RSVG datasets.

Shifei Ding, Qidong Wang, Lili Guo

In image denoising research, discriminative models have achieved impressive results which mainly owes to the powerful ability of convolutional networks in local feature extraction. However, there is still room for improvement due to insufficient utilization of global information. Although using fully connected layers or increasing network depth can supplement global information, this results in a significant increase in parameters and computational cost. To address these issues, we propose a global information compensation network (GICN) for image denoising in this paper. Firstly, at the shallow network part, we propose a global feature mining block that enhances the network's ability to extract global information by combining non-local blocks and the Fourier transform while improving the interpretability of the model. Secondly, between the encoder and decoder, we propose a cross-scale feature aggregation block to fuse information at different scales. Finally, we employ attention blocks to improve skip connections to better capture long-distance dependencies. Extensive experimental results show that our proposed GICN effectively compensates for global information, achieves a balance between denoising efficiency and effect, and surpasses mainstream methods in multiple benchmark tests.

Jisheng Dang, Ligen Chen, Jingze Wu, Ronghao Lin, Bimei Wang, Yun Wang, Liting Wang, Nannan Zhu, Teng Wang

Dynamic spatio-temporal understanding is essential for video-based multimodal tasks, yet existing methods often struggle to capture fine-grained temporal and spatial relationships in long videos. Current approaches primarily rely on pre-trained CLIP encoders, which excel in semantic understanding but lack spatially-aware visual context. This leads to hallucinated results when interpreting fine-grained objects or scenes. To address these limitations, we propose a novel framework that integrates diffusion models into multimodal video models. By employing diffusion encoders at intermediate layers, we enhance visual representations through feature alignment and knowledge distillation losses, significantly improving the model's ability to capture spatial patterns over time. Additionally, we introduce a multi-level alignment strategy to learn robust feature correspondence from pre-trained diffusion models. Extensive experiments on benchmark datasets demonstrate our approach's state-of-the-art performance across multiple video understanding tasks. These results establish diffusion models as a powerful tool for enhancing multimodal video models in complex, dynamic scenarios.

Rui Zuo, Simon Khan, Zifan Wang, Garrett Ethan Katz, Qinru Qiu

Reinforcement learning (RL) has demonstrated remarkable success in solving complex decision-making problems, yet its adoption in critical domains is hindered by the lack of interpretability in its decision-making processes. Existing explainable AI (xAI) approaches often fail to provide meaningful explanations for RL agents, particularly because they overlook the contrastive nature of human reasoning—answering "why this action instead of that one?" To address this gap, we propose a novel framework of contrastive learning to explain RL selected actions, named VisionMask. VisionMask is trained to generate explanations by explicitly contrasting the agent's chosen action with alternative actions in a given state using a self-supervised manner. We demonstrate the efficacy of our method through experiments across diverse RL environments, evaluating it in terms of faithfulness, robustness and complexity. Our results show that VisionMask significantly improves human understanding of agent behavior while maintaining accuracy and fidelity. Furthermore, we present examples illustrating how VisionMask can be used for counterfactual analysis. This work bridges the gap between RL and xAI, paving the way for safer and more interpretable RL systems.

Lijun Wu, Dong Hao, Zhiyi Fan

Graph Neural Networks (GNNs) have achieved outstanding performance across a wide range of graph-related tasks. However, their "black-box" nature poses significant challenges to their explainability, and existing methods often fail to effectively capture the intricate interaction patterns among nodes within the network. In this work, we propose a novel explainability framework, GraphEXT, which leverages cooperative game theory and the concept of social externalities. GraphEXT partitions graph nodes into coalitions, decomposing the original graph into independent subgraphs. By integrating graph structure as an externality and incorporating the Shapley value under externalities, GraphEXT quantifies node importance through their marginal contributions to GNN predictions as the nodes transition between coalitions. Unlike traditional Shapley value-based methods that primarily focus on node attributes, our GraphEXT places greater emphasis on the interactions among nodes and the impact of structural changes on GNN predictions. Experimental studies on both synthetic and real-world datasets show that GraphEXT outperforms existing baseline methods in terms of fidelity across diverse GNN architectures , significantly enhancing the explainability of GNN models.

Chunjiang Wang, Kun Zhang, Yandong Liu, Zhiyang He, Xiaodong Tao, S. Kevin Zhou

The concept bottleneck model (CBM), as a technique improving interpretability via linking predictions to human-understandable concepts, makes high-risk and life-critical medical image classification credible. Typically, existing CBM methods associate the final layer of visual encoders with concepts to explain the model’s predictions. However, we empirically discover the phenomenon of concept preference variation, that is, the concepts are preferably associated with the features at different layers than those only at the final layer; yet a blind last-layer-based association neglects such a preference variation and thus weakens the accurate correspondences between features and concepts, impairing model interpretability. To address this issue, we propose a novel Multi-layer Visual Preference-enhanced Concept Bottleneck Model (MVP-CBM), which comprises two key novel modules: (1) intra-layer concept preference modeling, which captures the preferred association of different concepts with features at various visual layers, and (2) multi-layer concept sparse activation fusion, which sparsely aggregates concept activations from multiple layers to enhance performance. Thus, by explicitly modeling concept preferences, MVP-CBM can comprehensively leverage multi-layer visual information to provide a more nuanced and accurate explanation of model decisions. Extensive experiments on several public medical classification benchmarks demonstrate that MVP-CBM achieves state-of-the-art accuracy and interoperability, verifying its superiority. Code is available at https://github.com/wcj6/MVP-CBM.

Sanchit Sinha, Guangzhi Xiong, Aidong Zhang

As Vision Transformers (ViTs) are increasingly adopted in sensitive vision applications, there is a growing demand for improved interpretability. This has led to efforts to forward-align these models with carefully annotated abstract, human-understandable semantic entities - concepts. Concepts provide global rationales to the model predictions and can be quickly understood/intervened on by domain experts. Most current research focuses on designing model-agnostic, plug-and-play generic concept-based explainability modules that do not incorporate the inner workings of foundation models (e.g., inductive biases, scale invariance, etc.) during training. To alleviate this issue for ViTs, in this paper, we propose ASCENT-ViT, an attention-based, concept learning framework that effectively composes scale and position-aware representations from multiscale feature pyramids and ViT patch representations, respectively. Further, these representations are aligned with concept annotations through attention matrices - which incorporate spatial and global (semantic) concepts. ASCENT-ViT can be utilized as a classification head on top of standard ViT backbones for improved predictive performance and accurate and robust concept explanations as demonstrated on five datasets, including three widely used benchmarks (CUB, Pascal APY, Concept-MNIST) and two real-world datasets (AWA2, KITS). An appendix of the paper with more comprehensive results is available at https://arxiv.org/abs/2501.09221.

Deng Pan, Nuno Moniz, Nitesh V. Chawla

The challenge of delivering efficient explanations is a critical barrier that prevents the adoption of model explanations in real-world applications. Existing approaches often depend on extensive model queries for sample-level explanations or rely on expert's knowledge of specific model structures that trade general applicability for efficiency. To address these limitations, this paper introduces a novel framework Fast EXplanation (FEX) that represents attribution-based explanations via probability distributions, which are optimized by leveraging the policy gradient method. The proposed framework offers a robust, scalable solution for real-time, large-scale model explanations, bridging the gap between efficiency and applicability. We validate our framework on image and text classification tasks and the experiments demonstrate that our method reduces inference time by over 97 percent and memory usage by 70 percent compared to traditional model-agnostic approaches while maintaining high-quality explanations and broad applicability.

Fan Li, Tiancheng Zhang, Yifang Yin, Minghe Yu, Mengxiang Wang, Ge Yu

Knowledge tracing plays a pivotal role in enabling personalized learning on online platforms. While deep learning-based approaches have achieved impressive predictive performance, their limited interpretability poses a significant barrier to practical adoption. Existing explanation methods primarily focus on specific model architectures and fall short in 1) explicitly prioritizing critical interactions to generate fine-grained explanations, and 2) maintaining similarity consistency across interaction importance. These limitations hinder actionable insights for improving student outcomes. To bridge the gap, we propose a model-agnostic approach that provides enhanced explanations applicable to diverse knowledge tracing methods. Specifically, we propose a novel ranking loss designed to explicitly optimize the importance ranking of past interactions by comparing their corresponding perturbed outputs. Furthermore, we introduce a similarity loss to capture temporal dependencies, ensuring consistency in the assigned importance scores for conceptually similar interactions. Extensive experiments conducted on various knowledge tracing models and benchmark datasets demonstrate substantial enhancements in explanation quality.

Paul Kobialka, Lina Gerlach, Francesco Leofante, Erika Ábrahám, Silvia Lizeth Tapia Tarifa, Einar Broch Johnsen

Counterfactuals are widely used in AI to explain how minimal changes to a model’s input can lead to a different output. However, established methods for computing counterfactuals typically focus on one-step decision-making, and are not directly applicable to sequential decision-making tasks. This paper fills this gap by introducing counterfactual strategies for Markov Decision Processes (MDPs). During MDP execution, a strategy decides which of the enabled actions (with known probabilistic effects) to execute next. Given an initial strategy that reaches an undesired outcome with a probability above some limit, we identify minimal changes to the initial strategy to reduce that probability below the limit. We encode such counterfactual strategies as solutions to non-linear optimization problems, and further extend our encoding to synthesize diverse counterfactual strategies. We evaluate our approach on four real-world datasets and demonstrate its practical viability in sophisticated sequential decision-making tasks.

David Ing, Said Jabbour, Lakhdar Saïs

Random Forests (RFs) are one of the most popular classifiers in machine learning. RF is an ensemble learning method that combines multiple Decision Trees (DTs), providing a more robust and accurate model than a single DT. However, one of the main step of RFs is the random selection of many different features during the construction phase of DTs, resulting in a forest with various features, which makes it difficult to extract short and concise explanations. In this paper, we propose integrating Logical Analysis of Data (LAD) into RFs. LAD is a pattern learning framework that combines optimization, Boolean functions, and combinatorial theory. One of its main goals is to generate minimal support sets (MSSes) that discriminate between different groups of data. More precisely, we show how to enhance the classical RF algorithm by randomly choosing MSSes rather than randomly choosing feature subsets that potentially contain irrelevant features for constructing DTs. Experiments on benchmark datasets reveal that integrating LAD into classical RFs using MSSes can maintain similar performance in terms of accuracy, produce forests of similar size, reduce the set of used features, and enable the extraction of significantly shorter explanations compared to classical RFs.

Yingying Fang, Zihao Jin, Shaojie Guo, Jinda Liu, Zhiling Yue, Yijian Gao, Junzhi Ning, Zhi Li, Simon Walsh, Guang Yang

Despite significant advancements in automated report generation, the opaqueness of text interpretability continues to cast doubt on the reliability of the content produced. This paper introduces a novel approach to identify specific image features in X-ray images that influence the outputs of report generation models. Specifically, we propose Cyclic Vision-Language Manipulator (CVLM), a module to generate a manipulated X-ray from an original X-ray and its report from a designated report generator. The essence of CVLM is that cycling manipulated X-rays to the report generator produces altered reports aligned with the alterations pre-injected into the reports for X-ray generation, achieving the term ``cyclic manipulation''. This process allows direct comparison between original and manipulated X-rays, clarifying the critical image features driving changes in reports and enabling model users to assess the reliability of the generated texts. Empirical evaluations demonstrate that CVLM can identify more precise and reliable features compared to existing explanation methods, significantly enhancing the transparency and applicability of AI-generated reports.

Yi Zhan, Qi Liu, Weibo Gao, Zheng Zhang, Tianfu Wang, Shuanghong Shen, Junyu Lu, Zhenya Huang

Personalized programming tutoring, such as exercise recommendation, can enhance learners' efficiency, motivation, and outcomes, which is increasingly important in modern digital education. However, the lack of sufficient and high-quality programming data, combined with the mismatch between offline evaluation and real-world learning, hinders the practical deployment of such systems. To address this challenge, many approaches attempt to simulate learner practice data, yet they often overlook the fine-grained, iterative nature of programming learning, resulting in a lack of interpretability and granularity. To fill this gap, we propose a LLM-based agent, CoderAgent, to simulate students' programming processes in a fine-grained manner without relying on real data. Specifically, we equip each human learner with an intelligent agent, the core of which lies in capturing the cognitive states of the human programming practice process. Inspired by ACT-R, a cognitive architecture framework, we design the structure of CoderAgent to align with human cognitive architecture by focusing on the mastery of programming knowledge and the application of coding ability. Recognizing the inherent patterns in multi-layered cognitive reasoning, we introduce the Programming Tree of Thought (PTOT), which breaks down the process into four steps: why, how, where, and what. This approach enables a detailed analysis of iterative problem-solving strategies. Finally, experimental evaluations on real-world datasets demonstrate that CoderAgent provides interpretable insights into learning trajectories and achieves accurate simulations, paving the way for personalized programming education.

Yongheng Liang, Hejun Wu, Haitao Wang, Hao Cai

Credit assignment is a critical problem in multi-agent reinforcement learning (MARL), aiming to identify agents' marginal contributions for optimizing cooperative policies. Current credit assignment methods typically assume synchronous decision-making among agents. However, many real-world scenarios require agents to act asynchronously without waiting for others. This asynchrony introduces conditional dependencies between actions, which pose great challenges to current methods. To address this issue, we propose an asynchronous credit assignment framework, incorporating a Virtual Synchrony Proxy (VSP) mechanism and a Multiplicative Value Decomposition (MVD) algorithm. VSP enables physically asynchronous actions to be virtually synchronized during credit assignment. We theoretically prove that VSP preserves both task equilibrium and algorithm convergence. Furthermore, MVD leverages multiplicative interactions to effectively model dependencies among asynchronous actions, offering theoretical advantages in handling asynchronous tasks. Extensive experiments show that our framework consistently outperforms state-of-the-art MARL methods on challenging tasks while providing improved interpretability for asynchronous cooperation.

Derek Palmer, Yifan Zhu, Kenneth Lai, Hannah VanderHoeven, Mariah Bradford, Ibrahim Khebour, Carlos Mabrey, Jack Fitzgerald, Nikhil Krishnaswamy, Martha Palmer 等

Our goal is to develop an AI Partner that can provide support for group problem solving and social dynamics. In multi-party working group environments, multimodal analytics is crucial for identifying non-verbal interactions of group members. In conjunction with their verbal participation, this creates an holistic understanding of collaboration and engagement that provides necessary context for the AI Partner. In this demo, we illustrate our present capabilities at detecting and tracking nonverbal behavior in student task-oriented interactions in the classroom, and the implications for tracking common ground and engagement.