IEEE TPAMI

Heatmap Pooling Network for Action Recognition from RGB Videos

用于RGB视频中动作识别的热图池化网络

Mengyuan Liu, Jinfu Liu, Yongkang Jiang, Bin He

机构 * State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School（国家通用人工智能重点实验室，北京大学深圳研究生院） ； Imaging Department, DJI Technology Co., Ltd（大疆技术创新有限公司影像部） ； TongJi University（同济大学） 纠错

AI总结 本文提出了一种用于视频中动作识别的热图池化网络，通过反馈池化模块提取稳健且简洁的人体特征，并结合多模态数据提升识别性能。

Comments Final Version of IEEE Transactions on Pattern Analysis and Machine Intelligence

Journal ref IEEE Transactions on Pattern Analysis and Machine Intelligence (2025)

LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving

LargeAD: 大规模跨传感器数据预训练用于自动驾驶

Lingdong Kong, Xiang Xu, Youquan Liu, Jun Cen, Runnan Chen, Wenwei Zhang, Liang Pan, Kai Chen, Ziwei Liu

机构 * WorldBench Team（WorldBench团队） 纠错

AI总结 LargeAD通过跨传感器数据预训练提升自动驾驶中的三维场景理解，结合多模态对比学习和时间一致性，实现更鲁棒的感知性能。

Comments IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models

文本到图像扩散模型中后门检测的动态注意力分析

Zhongqi Wang, Jie Zhang, Shiguang Shan, Xilin Chen

机构 * Key Laboratory of AI Safety of CAS, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing 100190, China, and also with the University of Chinese Academy of Sciences (UCAS), Beijing 100049, China（中国科学院人工智能安全重点实验室，计算技术研究所（ICT），中国科学院（CAS），北京100190，中国，以及中国科学院大学（UCAS），北京100049，中国） 纠错

AI总结 本研究提出动态注意力分析方法，通过分析扩散模型中注意力图的动态演变，有效检测文本到图像扩散模型中的后门攻击。

Comments Accepted by TPAMI

A Perceptually Inspired Variational Framework for Color Enhancement

基于视觉感知的变分框架用于颜色增强

Rodrigo Palma-Amestoy, Edoardo Provenzi, Marcelo Bertalmío, Vicent Caselles

机构 * Department of Electrical Engineering, Universidad de Chile（智利大学电气工程系） ； Dipartimento di Tecnologia dell’Informazione, Università di Milano（米兰大学信息科技技术系） ； Departament de Tecnologia, Universitat Pompeu Fabra（庞培法布拉大学技术系） 纠错

AI总结 本文提出了一种基于视觉感知的变分框架，用于改进颜色增强，通过梯度下降计算极小值并优化计算效率。

Journal ref IEEE Transactions on Pattern Analysis and Machine Intelligence, 31 (3), 458-474, March 2009

Demystifying Higher-Order Graph Neural Networks

解开高阶图神经网络的谜团

Maciej Besta, Florian Scheidl, Lukas Gianinazzi, Grzegorz Kwasniewski, Shachar Klaiman, Jürgen Müller, Torsten Hoefler

机构 * ETH Zurich（苏黎世联邦理工学院） ； BASF SE（巴斯夫股份有限公司） 纠错

AI总结 本文提出了一种HOGNN的分类法和蓝图，分析现有模型并提供选择指南及未来研究方向。

Journal ref IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025

PointAD+: Learning Hierarchical Representations for Zero-shot 3D Anomaly Detection

PointAD+: 学习层次化表示用于零样本3D异常检测

Qihang Zhou, Shibo He, Jiangtao Yan, Wenchao Meng, Jiming Chen

机构 * State Key Laboratory of Industrial Control Technology（工业控制技术国家重点实验室） ； Zhejiang University（浙江大学） 纠错

AI总结 PointAD+通过层次化表示学习，结合隐式和显式异常语义，提升零样本3D异常检测性能。

Comments Submitted to TPAMI

Evolving Graph Learning for Out-of-Distribution Generalization in Non-stationary Environments

演化图学习用于非平稳环境中的分布外泛化

Qingyun Sun, Jiayi Luo, Haonan Yuan, Xingcheng Fu, Hao Peng, Jianxin Li, Philip S. Yu

机构 * Beijing Advanced Innovation Center for Big Data and Brain Computing, School of Computer Science and Engineering, Beihang University（北京大数据与脑计算先进创新中心，计算机科学与工程学院，北京航空航天大学） ； Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University（教育区块链与智能技术重点实验室，教育部，广西师范大学） ； Department of Computer Science, University of Illinois at Chicago（计算机科学系，伊利诺伊大学芝加哥分校） 纠错

AI总结 本文提出EvoOOD框架，通过环境感知的不变模式识别提升动态图在非平稳环境中的分布外泛化能力。

Comments Accepted by TPAMI

Sparse-PGD: A Unified Framework for Sparse Adversarial Perturbations Generation

稀疏PGD：一种生成稀疏对抗扰动的统一框架

Xuyang Zhong, Chen Liu

机构 * City University of Hong Kong（香港城市大学） 纠错

AI总结 稀疏PGD框架通过高效生成稀疏对抗扰动并提升模型鲁棒性，实现对不同场景下的强性能表现。

Comments Accepted by TPAMI

UniAV: Unified Audio-Visual Perception for Multi-Task Video Event Localization

Tiantian Geng, Teng Wang, Jinming Duan, Yanfu Zhang, Weili Guan, Feng Zheng, Ling shao

机构 * Department of Computer Science and Engineering, Southern University of Science and Technology（计算机科学与工程系，南方科技大学） ； School of Computer Science, University of Birmingham（计算机科学学院，伯明翰大学） ； Department of Computer Science, University of Hong Kong（计算机科学系，香港大学） ； Division of Informatics, Imaging and Data Sciences, University of Manchester（信息学、成像与数据科学系，曼彻斯特大学） ； William and Mary（威廉与玛丽学院） ； Harbin Institute of Technology（哈尔滨工业大学） ； UCAS-Terminus AI Lab, University of Chinese Academy of Sciences（中国科学院大学-Terminus AI实验室） 纠错

Comments Published on IEEE TPAMI

Journal ref IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 11, pp. 10280-10294, August 2025

Wonder3D++: Cross-domain Diffusion for High-fidelity 3D Generation from a Single Image

Yuxiao Yang, Xiao-Xiao Long, Zhiyang Dou, Cheng Lin, Yuan Liu, Qingsong Yan, Yuexin Ma, Haoqian Wang, Zhiqiang Wu, Wei Yin

机构 * Tsinghua University（清华大学） ； Nanjing University（南京大学） ； Wright State University（威斯汀大学） ； Horizon Robotics ； University of Hong Kong（香港大学） ； Macau University of Science and Technology（澳门科技大学） ； Hong Kong University of Science and Technology（香港科学大学） ； Wuhan University（武汉大学） ； ShanghaiTech University（上海科技大学） 纠错

Comments 21 pages, 19 figures, accepted by TPAMI

UniVST: A Unified Framework for Training-free Localized Video Style Transfer

Quanjian Song, Mingbao Lin, Wengyi Zhan, Shuicheng Yan, Liujuan Cao, Rongrong Ji

机构 * Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, China（中国教育部多媒体可信感知与高效计算重点实验室，厦门大学，中国） ； Rakuten Asia Pte. Ltd. ； School of Computing, National University of Singapore（新加坡国立大学计算机学院） ； Institute of Artificial Intelligence, Xiamen University（厦门大学人工智能研究院） 纠错

Comments Accepted by TPAMI 2025; Project Page: https://quanjiansong.github.io/projects/UniVST

FlexPara: Flexible Neural Surface Parameterization

Yuming Zhao, Qijian Zhang, Junhui Hou, Jiazhi Xia, Wenping Wang, Ying He

Comments Accepted by IEEE TPAMI

CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition

Jongseo Lee, Joohyun Chang, Dongho Lee, Jinwoo Choi

Comments Our paper has been accepted to IEEE TPAMI

Language-Guided Graph Representation Learning for Video Summarization

Wenrui Li, Wei Han, Hengyu Man, Wangmeng Zuo, Xiaopeng Fan, Yonghong Tian

机构 * Department of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术系） ； Harbin Institute of Technology Suzhou Research Institute（哈尔滨工业大学苏州研究所） ； School of AI for Science, the Shenzhen Graduate School, Peking University（北京大学人工智能科学学院、深圳研究生院） ； Peng Cheng Laboratory（鹏城实验室） ； School of Computer Science, Peking University（北京大学计算机学院） 纠错

Comments Accepted by IEEE TPAMI

MADiff: Motion-Aware Mamba Diffusion Models for Hand Trajectory Prediction on Egocentric Videos

Junyi Ma, Xieyuanli Chen, Wentao Bao, Jingyi Xu, Hesheng Wang

机构 * IRMV Lab, School of Automation and Intelligent Sensing, Shanghai Jiao Tong University and State Key Laboratory of Avionics Integration and Aviation System-of-Systems Synthesis, Shanghai Key Laboratory of Navigation and Location Based Services（IRMV实验室，自动化与智能感知学院，上海交通大学，航空集成与航空系统-of-Systems综合国家重点实验室，导航与定位服务重点实验室） ； College of Intelligence Science and Technology, National University of Defense Technology（智能科学与技术学院，国防科技大学） ； Department of Electronic Engineering, Shanghai Jiao Tong University（电子工程学院，上海交通大学） 纠错

Comments Accepted to TPAMI 2025

Hierarchical Spatial-Frequency Aggregation for Spectral Deconvolution Imaging

Tao Lv, Daoming Zhou, Chenglong Huang, Chongde Zi, Linsen Chen, Xun Cao

机构 * Nanjing University（南京大学） 纠错

Comments Under Review at TPAMI

High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Network

Feng Zhang, Haoyou Deng, Zhiqiang Li, Lida Li, Bin Xu, Qingbo Lu, Zisheng Cao, Minchen Wei, Changxin Gao, Nong Sang, Xiang Bai

机构 * National Key Laboratory of Multispectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（国家多谱段信息智能处理技术重点实验室，人工智能与自动化学院，华中科技大学） ； DJI Technology Co., Ltd.（大疆技术创新有限公司） ； Color, Imaging, and Illumination Laboratory, The Hong Kong Polytechnic University（色彩、成像与照明实验室，香港理工大学） ； School of Software Engineering, Huazhong University of Science and Technology（软件工程学院，华中科技大学） 纠错

Comments accepted by TPAMI 2025

SelaVPR++: Towards Seamless Adaptation of Foundation Models for Efficient Place Recognition

Feng Lu, Tong Jin, Xiangyuan Lan, Lijun Zhang, Yunpeng Liu, Yaowei Wang, Chun Yuan

机构 * Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China（清华大学深圳国际研究生院，清华大学，深圳，中国） ； Pengcheng Laboratory, Shenzhen, China（鹏城实验室，深圳，中国） ； Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China（沈阳自动化研究所，中国科学院，沈阳，中国） ； Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China（重庆绿色智能技术研究所，中国科学院，重庆，中国） ； Pazhou Laboratory (Huangpu), Guangzhou, China（琶洲实验室（黄埔），广州，中国） 纠错

Comments accepted by T-PAMI

Journal ref IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025

A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challenges

Wei Ju, Siyu Yi, Yifan Wang, Zhiping Xiao, Zhengyang Mao, Hourun Li, Yiyang Gu, Yifang Qin, Nan Yin, Senzhang Wang, Xinwang Liu, Philip S. Yu, Ming Zhang

Comments Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI 2025)

UniSOT: A Unified Framework for Multi-Modality Single Object Tracking

Yinchao Ma, Yuyang Tang, Wenfei Yang, Tianzhu Zhang, Xu Zhou, Feng Wu

机构 * School of Information Science, University of Science and Technology of China（信息科学学院，中国科学技术大学） 纠错

Comments The paper has been accepted by TPAMI

Dynamic Context-Aware Scene Reasoning Using Vision-Language Alignment in Zero-Shot Real-World Scenarios

Manjunath Prasad Holenarasipura Rajiv, B. M. Vidyavathi

Comments Preprint under review at IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025

Vision-Language Integration for Zero-Shot Scene Understanding in Real-World Environments

Manjunath Prasad Holenarasipura Rajiv, B. M. Vidyavathi

Comments Preprint under review at IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025

MECD+: Unlocking Event-Level Causal Graph Discovery for Video Reasoning

Tieyuan Chen, Huabin Liu, Yi Wang, Yihang Chen, Tianyao He, Chaofan Gan, Huanyu He, Weiyao Lin

机构 * Shanghai Jiao Tong University（上海交通大学） ； Monash University（墨尔本大学） ； Zhongguancun Academy（中关村academy） ； Shanghai AI Laboratory（上海人工智能实验室） 纠错

Comments Accepted by IEEE TPAMI (IEEE Transactions on Pattern Analysis and Machine Intelligence). arXiv admin note: substantial text overlap with arXiv:2409.17647

Improving Model Fusion by Training-time Neuron Alignment with Fixed Neuron Anchors

Zexi Li, Zhiqi Li, Jie Lin, Tao Shen, Jun Xiao, Yike Guo, Tao Lin, Chao Wu

机构 * Zhejiang University（浙江大学） ； Georgia Institute of Technology（佐治亚理工学院） ； Westlake University（西湖大学） ； Hong Kong University of Science and Technology（香港科技大学） 纠错

Comments IEEE Transactions on Pattern Analysis and Machine Intelligence

NVS-SQA: Exploring Self-Supervised Quality Representation Learning for Neurally Synthesized Scenes without References

Qiang Qu, Yiran Shen, Xiaoming Chen, Yuk Ying Chung, Weidong Cai, Tongliang Liu

机构 * School of Computer Science, the University of Sydney（悉尼大学计算机科学学院） ； School of Software, Shandong University（山东大学软件学院） ； School of Computer and Artificial Intelligence, Beijing Technology and Business University（北京科技与商业大学计算机与人工智能学院） 纠错

Comments Accepted by TPAMI

FaceTracer: Unveiling Source Identities from Swapped Face Images and Videos for Fraud Prevention

Zhongyi Zhang, Jie Zhang, Wenbo Zhou, Xinghui Zhou, Qing Guo, Weiming Zhang, Tianwei Zhang, Nenghai Yu

机构 * School of Cyber Science and Technology, University of Science and Technology of China（中国科学技术大学信息科学与技术学院） ； Centre for Frontier AI Research, Agency for Science, Technology and Research (A*STAR)（科技研究局前沿人工智能研究中心） ； College of Computing and Data Science at Nanyang Technological University（南洋理工大学计算与数据科学学院） 纠错

Comments 17 pages, 16 figures, TPAMI version

RealCustom++: Representing Images as Real Textual Word for Real-Time Customization

Zhendong Mao, Mengqi Huang, Fei Ding, Mingcong Liu, Qian He, Yongdong Zhang

机构 * University of Science and Technology of China（中国科学技术大学） ； ByteDance Inc（字节跳动公司） 纠错

Comments 18 pages

Journal ref IEEE Transactions on Pattern Analysis and Machine Intelligence (2025)

Revisiting Transformation Invariant Geometric Deep Learning: An Initial Representation Perspective

Ziwei Zhang, Xin Wang, Zeyang Zhang, Peng Cui, Wenwu Zhu

机构 * Department of Computer Science and Technology（计算机科学与技术系） 纠错

Comments 13 pages; accepted by IEEE TPAMI

Learning Knowledge-based Prompts for Robust 3D Mask Presentation Attack Detection

Fangling Jiang, Qi Li, Bing Liu, Weining Wang, Caifeng Shan, Zhenan Sun, Ming-Hsuan Yang

机构 * School of Computer Science, University of South China（南方大学计算机科学学院） ； New Laboratory of Pattern Recognition, MAIS, CASIA（模式识别新实验室，MAIS，CASIA） ； School of Intelligence Science and Technology, Nanjing University（智能科学与技术学院，南京大学） ； Department of Computer Science and Engineering, University of California, Merced（加州大学默塞德分校计算机科学与工程系） ； Department of Computer Science and Engineering, Yonsei University（延世大学计算机科学与工程系） 纠错

Comments Accepted by TPAMI

TransFace++: Rethinking the Face Recognition Paradigm with a Focus on Accuracy, Efficiency, and Security

Jun Dan, Yang Liu, Baigui Sun, Jiankang Deng, Shan Luo

机构 * Zhejiang University（浙江大学） ； Wolf 1069 b Lab, Sany Group（沃尔夫1069b实验室，三一集团） ； Department of Computing, Imperial College London（计算系，帝国理工学院伦敦分校） ； Department of Engineering, King’s College London（工程系，国王学院伦敦分校） 纠错

Comments This is an extended version of our previous ICCV paper "TransFace", with significant new experiments, ablation studies, and improvements published in IEEE TPAMI as "TransFace++"