IEEE TPAMI - arXivDaily 期刊&会议

2506.13678 2025-10-27 cs.LG

A Gravity-informed Spatiotemporal Transformer for Human Activity Intensity Prediction

Yi Wang, Zhenghong Wang, Fan Zhang, Chaogui Kang, Sijie Ruan, Di Zhu, Chengling Tang, Zhongfu Ma, Weiyu Zhang, Yu Zheng, Philip S. Yu, Yu Liu

Comments IEEE TPAMI 2025. 18 pages, 14 figures

2306.07032 2025-10-22 cs.LG cs.AI

Mitigating Prior Errors in Causal Structure Learning: A Resilient Approach via Bayesian Networks

Lyuzhou Chen, Taiyu Ban, Xiangyu Wang, Derui Lyu, Huanhuan Chen

Comments 12 pages, 4 figures

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

2510.17685 2025-10-21 cs.CV cs.AI

Multilingual Text-to-Image Person Retrieval via Bidirectional Relation Reasoning and Aligning

Min Cao, Xinyu Zhou, Ding Jiang, Bo Du, Mang Ye, Min Zhang

机构 * School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院）； School of Computer Science, Wuhan University（武汉大学计算机学院）； Key Laboratory of New Generation Artificial Intelligence Technology & Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（新 generation 人工智能技术及交叉应用重点实验室（东南大学），教育部，中国）

Comments Final version published in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). Xplore link: https://ieeexplore.ieee.org/document/11199360

2403.11111 2025-10-20 cs.CV

Diffusion Models are Efficient Data Generators for Human Mesh Recovery

Yongtao Ge, Wenjia Wang, Yongfan Chen, Fanzhou Wang, Lei Yang, Hao Chen, Chunhua Shen

机构 * The University of Adelaide（阿德莱德大学）； Zhejiang University（浙江大学）； Zhejiang University of Technology（浙江工业大学）； The University of Hong Kong（香港大学）； SenseTime（秒针科技）

Comments Accepted by TPAMI, project page: https://yongtaoge.github.io/projects/humanwild

2309.15755 2025-10-20 cs.CV

CAIT: Triple-Win Compression towards High Accuracy, Fast Inference, and Favorable Transferability For ViTs

Ao Wang, Hui Chen, Zijia Lin, Sicheng Zhao, Jungong Han, Guiguang Ding

机构 * BNRist, Tsinghua University（清华大学北京人工智能研究院）； School of Software, Tsinghua University（清华大学软件学院）； Department of Automation, Tsinghua University（清华大学自动化系）

Comments TPAMI 2025 Camera-ready Version

2510.13694 2025-10-16 cs.LG

Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking

Yuchun Miao, Liang Ding, Sen Zhang, Rong Bao, Lefei Zhang, Dacheng Tao

Comments 46 pages, 36 figures, submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence

2510.12123 2025-10-15 cs.CV

Hardware-aware Coding Function Design for Compressive Single-Photon 3D Cameras

David Parra, Felipe Gutierrez-Barragan, Trevor Seets, Andreas Velten

机构 * University of Wisconsin-Madison（威斯康星大学麦迪逊分校）

Comments IEEE TPAMI Special Issue

2310.05108 2025-10-15 cs.CV

Enhancing Representations through Heterogeneous Self-Supervised Learning

Zhong-Yu Li, Bo-Wen Yin, Yongxiang Liu, Li Liu, Ming-Ming Cheng

机构 * VCIP & TBI Center, Nankai University（秦滨中心与神经生物学中心，南开大学）； NKIARI, Futian, Shenzhen, China（国家免疫疾病与传染病研究中心，福田，深圳，中国）； College of Electronic Science and Technology, National University of Defense Technology (NUDT)（电子科学与技术学院，国防科技大学（NUDT））

Journal ref Published in: IEEE Transactions on Pattern Analysis and Machine Intelligence (Volume: 47, Issue: 7, July 2025)

2506.17925 2025-10-14 cs.SI cs.GT

Dynamic Evolution of Complex Networks: A Reinforcement Learning Approach Applying Evolutionary Games to Community Structure

Bin Pi, Liang-Jian Deng, Minyu Feng, Matjaž Perc, Jürgen Kurths

Journal ref IEEE Trans. Pattern Anal. Mach. Intell. 47, 8563-8582 (2025)

2406.04765 2025-10-14 cs.CV cs.MM

SMC++: Masked Learning of Unsupervised Video Semantic Compression

Yuan Tian, Xiaoyue Ling, Cong Geng, Qiang Hu, Guo Lu, Guangtao Zhai

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； JIUTIAN Research（JIUTIAN研究）； Cooperative Medianet Innovation Center（协作中继创新中心）； Shanghai Jiao Tong University（上海交通大学）； Institute of Image Communication and Network Engineering（图像通信与网络工程研究所）

Comments Accepted to TPAMI; Substantial Extension of ICCV 2023 paper

2405.15495 2025-10-13 cs.LG

Towards Natural Machine Unlearning

Zhengbao He, Tao Li, Xinwen Cheng, Zhehao Huang, Xiaolin Huang

Comments Accepted by IEEE TPAMI

2407.15212 2025-10-10 cs.CV cs.GR

Surfel-based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction from Monocular Video

Yiqun Zhao, Chenming Wu, Binbin Huang, Yihao Zhi, Chen Zhao, Jingdong Wang, Shenghua Gao

机构 * University of Hong Kong（香港大学）； Baidu Inc.（百度公司）； Department of Computer Vision Technology (VIS)（计算机视觉技术系）； School of Science and Engineering（科学与工程学院）； The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））

Comments Accepted by TPAMI 2025; Project Page: https://GS-IA.github.io

2208.12510 2025-10-10 cs.CV cs.MM

PRVR: Partially Relevant Video Retrieval

Xianke Chen, Daizong Liu, Xun Yang, Xirong Li, Jianfeng Dong, Meng Wang, Xun Wang

机构 * School of Computer Science and Technology（计算机科学与技术学院）； School of Statistics and Mathematics（统计学与数学学院）； Zhejiang Gongshang University（浙江工商大学）； Zhejiang Key Laboratory of Big Data and Future E-Commerce Technology（大数据与未来电子商务技术重点实验室）； Wangxuan Institute of Computer Technology（王萱计算机技术研究所）； School of Information Science and Technology（信息科学与技术学院）； University of Science and Technology of China（中国科学技术大学）； School of Information（信息学院）； Renmin University of China（中国人民大学）； School of Computer Science and Information Engineering（计算机科学与信息工程学院）

Comments Accepted by TPAMI. The paper's homepage is https://github.com/HuiGuanLab/ms-sl-pp

2410.19378 2025-10-08 cs.CV cs.LG eess.IV

Unified Cross-Modal Medical Image Synthesis with Hierarchical Mixture of Product-of-Experts

Reuben Dorent, Nazim Haouchine, Alexandra Golby, Sarah Frisken, Tina Kapur, William Wells

机构 * Harvard Medical School and the Brigham and Women’s Hospital（哈佛医学院和布里洛妇产科医院）； MIND Team, Inria Saclay, Université Paris-Saclay, Palaiseau, France and Sorbonne Université, Institut du Cerveau - Paris Brain Institute - ICM, CNRS, Inria, Inserm, AP-HP, Hôpital de la Pitié Salpêtrière（MIND团队、Inria Saclay、巴黎萨克雷大学、Palaiseau，法国以及索邦大学、巴黎脑研究所-ICM、CNRS、Inria、Inserm、AP-HP、皮蒂埃萨勒普蒂耶医院）； Massachusetts Institute of Technology（麻省理工学院）

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

2510.04939 2025-10-07 cs.CV cs.AI cs.LG

Unsupervised Active Learning via Natural Feature Progressive Framework

Yuxi Liu, Catherine Lalman, Yimin Yang

机构 * Department of Electrical and Computer Engineering, Western University（电气与计算机工程系，西部大学）； Department of Pathology and Genomic Medicine, Thomas Jefferson University（病理与基因组医学系，托马斯·杰弗逊大学）； Vector Institute（向量研究所）

Comments Under review at IEEE TPAMI

2510.04111 2025-10-07 cs.CV

Learning Efficient Meshflow and Optical Flow from Event Cameras

Xinglong Luo, Ao Luo, Kunming Luo, Zhengning Wang, Ping Tan, Bing Zeng, Shuaicheng Liu

机构 * Institute of Image Processing, School of Information and Communication Engineering, University of Electronic Science and Technology of China（图像处理研究所，信息与通信工程学院，电子科学与技术大学）； Yibin Institute of UESTC（UESTC宜宾研究所）； School of Computing and Artificial Intelligence, Southwest Jiaotong University（计算与人工智能学院，西南交通大学）； Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology（电子与计算机工程系，香港科技大学）

Comments Accepted by TPAMI 2025

2410.01534 2025-10-06 cs.CV

Toward a Holistic Evaluation of Robustness in CLIP Models

Weijie Tu, Weijian Deng, Tom Gedeon

Comments Accepted to IEEE TPAMI, extension of NeurIPS'23 work: A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)

2311.13254 2025-10-06 cs.CV cs.AI eess.IV

Unified Domain Adaptive Semantic Segmentation

Zhe Zhang, Gaochang Wu, Jing Zhang, Xiatian Zhu, Dacheng Tao, Tianyou Chai

机构 * State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China（合成自动化过程工业国家重点实验室，东北大学，沈阳，中国）； School of Computer Science, Wuhan University（武汉大学计算机学院）； Surrey Institute for People-Centred Artificial Intelligence, and Centre for Vision, Speech and Signal Processing, University of Surrey（以人为中心的人工智能 Surrey 院，以及视觉、语音和信号处理中心， Surrey 大学）； College of Computing & Data Science, Nanyang Technological University（计算与数据科学学院，南洋理工大学）

Comments 34 pages (main paper and supplementary material), 25 figures, 19 tables. Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025

Journal ref IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 8, pp. 6731-6748, Aug. 2025

2302.11354 2025-10-02 cs.LG cs.AI

Learning Dynamic Graph Embeddings with Neural Controlled Differential Equations

Tiexin Qin, Benjamin Walker, Terry Lyons, Hong Yan, Haoliang Li

机构 * Department of Electrical and Engineering, City University of Hong Kong（电子工程系，香港城市大学）； Mathematical Institute, University of Oxford（数学研究所，牛津大学）

Comments Accepted by TPAMI 2025

2509.25996 2025-10-01 cs.LG cs.CL

CAST: Continuous and Differentiable Semi-Structured Sparsity-Aware Training for Large Language Models

Weiyu Huang, Yuezhou Hu, Jun Zhu, Jianfei Chen

机构 * Department of Computer Science and Technology, Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint ML Center, Tsinghua University（计算机科学与技术系、人工智能研究院、BNRist中心、THBI实验室、清华大学-博世联合机器学习中心、清华大学）

Comments Submitted to IEEE TPAMI

2405.20188 2025-10-01 cs.CV cs.GR

SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid 3D Registration

Yuxin Yao, Bailin Deng, Junhui Hou, Juyong Zhang

机构 * University of Science and Technology of China（中国科学技术大学）； City University of Hong Kong（香港城市大学）； Cardiff University（卡迪夫大学）

Comments Accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence

2307.03017 2025-10-01 cs.CV

RealLiFe: Real-Time Light Field Reconstruction via Hierarchical Sparse Gradient Descent

Yijie Deng, Lei Han, Tianpeng Lin, Lin Li, Jinzhi Zhang, Lu Fang

机构 * Dept. of Electrical Engineering, Tsinghua University, Beijing, China（电子工程系，清华大学，北京，中国）； Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）； Huawei Technologies（华为技术）

Comments Submitted to IEEE TPAMI

2410.08473 2025-09-30 cs.LG cs.AI stat.ML

Deeper Insights into Deep Graph Convolutional Networks: Stability and Generalization

Guangrui Yang, Ming Li, Han Feng, Xiaosheng Zhuang

机构 * Department of Mathematics, College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China（数学系，数学与信息学学院，华南农业大学，广州，中国）； Zhejiang Key Laboratory of Intelligent Education Technology and Application, Zhejiang Normal University, Jinhua, China（智能教育技术与应用浙江省重点实验室，浙江师范大学，金华，中国）； Department of Mathematics, City University of Hong Kong, Hong Kong, China（数学系，香港城市大学，香港，中国）

Comments 50 pages, 3 figures, published in IEEE Trans. Pattern Anal. Mach. Intell. 2025

2409.15395 2025-09-30 cs.CL cs.AI

Parse Trees Guided LLM Prompt Compression

Wenhao Mao, Chengbin Hou, Tianyu Zhang, Xinyu Lin, Ke Tang, Hairong Lv

机构 * Ministry of Education Key Laboratory of Bioinformatics, BNRIST Bioinformatics Division, Department of Automation, Tsinghua University（教育部生物信息学重点实验室、BNRIST生物信息学分部、自动化系、清华大学）； School of Computing and Artificial Intelligence, Fuyao University of Science and Technology（计算与人工智能学院、福耀科技大学）； 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）

Comments Accepted by IEEE TPAMI

2010.14343 2025-09-30 cs.CV

Learning to Infer Unseen Single-/Multi-Attribute-Object Compositions with Graph Networks

Hui Chen, Jingjing Jiang, Nanning Zheng

机构 * Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University（人工智能与机器人研究所，西安交通大学）

Comments Acceptted by IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI)

2407.01016 2025-09-26 cs.CV

SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection

Dingkang Liang, Wei Hua, Chunsheng Shi, Zhikang Zou, Xiaoqing Ye, Xiang Bai

机构 * School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（人工智能与自动化学院，华中科技大学）； School of Electronic Information and Communications, Huazhong University of Science and Technology（电子信息与通信学院，华中科技大学）； Baidu Inc., China（百度公司，中国）； School of Software Engineering, Huazhong University of Science and Technology（软件工程学院，华中科技大学）

Comments Accepted by IEEE TPAMI. The project page is at https://dk-liang.github.io/SOODv2/

2409.01522 2025-09-25 cs.CV

Lagrangian Motion Fields for Long-term Motion Generation

Yifei Yang, Zikai Huang, Chenshu Xu, Shengfeng He

机构 * School of Computing and Information Systems, Singapore Management University（计算与信息系统学院，新加坡管理大学）； School of Computer Science and Engineering, South China University of Technology（计算机科学与工程学院，华南理工大学）

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

2506.17968 2025-09-23 cs.LG cs.AI cs.CV math.PR stat.ML

h-calibration: Rethinking Classifier Recalibration with Probabilistic Error-Bounded Objective

Wenjian Huang, Guiping Cao, Jiahao Xia, Jingkun Chen, Hao Wang, Jianguo Zhang

机构 * Research Inst. of Trustworthy Autonomous Systems & Dept. of Computer Science and Engineering, SUSTech, China（可信自主系统研究所及计算机科学与工程系，深圳技术大学，中国）； Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation, Dept. of Computer Science and Engineering, SUSTech, and Peng Cheng Lab, China（脑启发智能计算广东省重点实验室、计算机科学与工程系，深圳技术大学，以及鹏城实验室，中国）； Faculty of Engineering and Information Technology, University of Technology Sydney, Australia（工程与信息技术学院，悉尼大学，澳大利亚）； Inst. of Biomedical Engineering, Dept. of Engineering Science, University of Oxford, UK（生物医学工程研究所、工程科学系，牛津大学，英国）

Journal ref IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 10, pp. 9023-9042, 2025

2509.16678 2025-09-23 cs.CV

IPF-RDA: An Information-Preserving Framework for Robust Data Augmentation

Suorong Yang, Hongchao Yang, Suhan Guo, Furao Shen, Jian Zhao

机构 * State Key Laboratory for Novel Software Technology, Department of Computer Science and Technology, Nanjing University（新型软件技术国家重点实验室，计算机科学与技术系，南京大学）； State Key Laboratory for Novel Software Technology, Nanjing University（新型软件技术国家重点实验室，南京大学）； School of Artificial Intelligence, Nanjing University（人工智能学院，南京大学）； School of Electronic Science and Engineering, Nanjing University（电子科学与工程学院，南京大学）

Comments IEEE Transactions on Pattern Analysis and Machine Intelligence

2408.09397 2025-09-22 cs.CV

Combo: Co-speech holistic 3D human motion generation and efficient customizable adaptation in harmony

Chao Xu, Mingze Sun, Zhi-Qi Cheng, Fei Wang, Yang Liu, Baigui Sun, Ruqi Huang, Alexander Hauptmann

机构 * Wolf 1069B Lab, Sany Group（沃尔夫1069B实验室，三一集团）； Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）； School of Engineering and Technology, University of Washington, Tacoma（华盛顿大学塔科姆分校工程与科技学院）； Alibaba Group（阿里巴巴集团）； Department of Engineering, King’s College London（伦敦大学国王学院工程系）； Language Technologies Institute, Carnegie Mellon University（卡内基梅隆大学语言技术研究所）

Comments Accepted to TPAMI