Progressive Cross-Stream Cooperation in Spatial and Temporal Domain for Action Localization
机构 * School of Electrical and Information Engineering, The University of Sydney（电气与信息工程学院，悉尼大学）
Comments TPAMI
期刊&会议
IEEE TPAMI
IEEE Transactions on Pattern Analysis and Machine Intelligence · 期刊 · Computer Vision
Event Cameras Meet SPADs for High-Speed, Low-Bandwidth Imaging
机构 * Robotics and Perception Group, University of Zurich, Switzerland（苏黎世大学机器人与感知组） ； Camera Culture Group, MIT Media Lab, USA（MIT媒体实验室相机文化组） ； EPFL, Lausanne, Switzerland（日内瓦联邦理工学院）
Comments IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025
Demystify Transformers & Convolutions in Modern Image Deep Networks
机构 * South China University of Technology（南方科技大学） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Huazhong University of Science and Technology（华中科技大学） ； Fudan University（复旦大学） ； The Chinese University of Hong Kong（香港中文大学） ； Tsinghua University（清华大学） ； SenseTime Research（商汤科技研究院）
Comments This paper was accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI). All models and codes used in this study are publicly available at https://github.com/OpenGVLab/STM-Evaluation
Journal ref IEEE Trans Pattern Anal Mach Intell, 47, 2025, pp. 2416-2428
PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenes
机构 * Zhejiang University, China（浙江大学） ； Autonomous Vision Group (AVG) at the University of Tübingen and Tübingen AI Center, Germany（图宾根大学自主视觉组（AVG）及图宾根人工智能中心）
Comments TPAMI 2025. Project page: http://fuxiao0719.github.io/projects/panopticnerf360/ Code: https://github.com/fuxiao0719/PanopticNeRF/tree/panopticnerf360
MOL: Joint Estimation of Micro-Expression, Optical Flow, and Landmark via Transformer-Graph-Style Convolution
机构 * School of Computer Science and Technology, China University of Mining and Technology（中国矿业大学（北京）计算机科学与技术学院） ； Mine Digitization Engineering Research Center of the Ministry of Education（教育部矿山数字化工程研究中心） ； Department of Computer Science and Engineering, The Hong Kong University of Science and Technology（香港科技大学计算机科学与工程系） ； School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院） ； Department of Computer Science and Software Engineering, The University of Western Australia（西澳大学计算机科学与软件工程系） ； School of Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院） ； MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能教育部重点实验室）
Comments This paper has been accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence
Low-Resolution Self-Attention for Semantic Segmentation
机构 * Nankai University（南开大学） ； Institute of High Performance Computing（高性能计算研究所） ； A*STAR（科技研究局） ； NKIARI ； Shenzhen Futian（深圳福田） ； VCIP ； University of Electronic Science and Technology of China（电子科技大学） ； Udeer AI ； School of Electronic and Computer Engineering（电子与计算机工程学院） ； Peking University（北京大学） ； Bytedance Inc.（字节跳动）
Comments Accepted by IEEE TPAMI; 14 pages, 6 figures, 14 tables
Segment Concealed Objects with Incomplete Supervision
机构 * Department of Biomedical Engineering, Duke University（生物医学工程系，杜克大学） ； Meta ； Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院） ； School of Information and Communication Engineering, Dalian University of Technology（信息与通信工程学院，大连理工大学） ； Shanghai Jiao Tong University（上海交通大学）
Comments IEEE TPAMI
Journal ref 10.1109/TPAMI.2025.3576209
New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration
机构 * University of Electronic Science and Technology of China（电子科技大学） ； Tongji University（同济大学）
Comments Accepted by TPAMI 2025
Text to Image for Multi-Label Image Recognition with Joint Prompt-Adapter Learning
机构 * Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR)（高性能计算研究所，科技研究局） ； University of Minnesota（明尼苏达大学） ； Microsoft Research Asia Singapore（微软亚洲研究院新加坡分部） ； Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（Mohamed bin Zayed人工智能大学） ； Australian National University（澳大利亚国立大学） ； Harbin Institute of Technology（哈尔滨工业大学）
Journal ref TPAMI-2024-04-1021
YOND: Practical Blind Raw Image Denoising Free from Camera-Specific Data Dependency
机构 * School of Computer Science and Technology, Beijing Institute of Technology（计算机科学与技术学院，北京理工大学） ； School of Artificial Intelligence, Beijing Normal University（人工智能学院，北京师范大学）
Comments 17 pages, 19 figures, TPAMI under review
Sensitivity-Aware Density Estimation in Multiple Dimensions
Journal ref IEEE Transactions on Pattern Analysis and Machine Intelligence ( Volume: 46, Issue: 11, November 2024)
MoBluRF: Motion Deblurring Neural Radiance Fields for Blurry Monocular Video
机构 * School of Electrical Engineering, Korea Advanced Institute of Science and Technology（韩国科学技术院电子工程学院） ； Department of Imaging Science, GSAIM, Chung-Ang University（Chung-Ang大学成像科学系）
Comments Accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025. The first two authors contributed equally to this work (equal contribution). The last two authors are co-corresponding authors. Please visit our project page at https://kaist-viclab.github.io/moblurf-site/
Self-supervised Latent Space Optimization with Nebula Variational Coding
Journal ref IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 3, pp. 1397-1411, March 2024
Monge-Ampere Regularization for Learning Arbitrary Shapes from Point Clouds
机构 * School of Software, Shandong University（山东大学软件学院） ； Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系） ； College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院） ； Department of Computer Science and Engineering, Texas A&M University（德克萨斯大学阿姆斯特朗分校计算机科学与工程系）
Comments Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Project Page: https://chuanxiang-yang.github.io/S2DF/, Code: https://github.com/chuanxiang-yang/S2DF
Accelerated Training of Federated Learning via Second-Order Methods
机构 * Department of Artificial Intelligence, Indian Institute of Technology Hyderabad, India（人工智能系，印度理工学院海得拉尔分校） ； Department of Computing Technologies, Swinburne University of Technology, Hawthorn, australia（计算技术系，斯威本科技大学 Hawthorn 分校） ； Department of Mechanical Engineering , Indian Institute of Technology Delhi, India（机械工程系，印度理工学院德里分校） ； Department of Computer Science and Engineering, Indian Institute of Technology Hyderabad, India（计算机科学与工程系，印度理工学院海得拉尔分校）
Comments 17 pages, 1 figure, 4 tables, submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI)
A Reverse Causal Framework to Mitigate Spurious Correlations for Debiasing Scene Graph Generation
机构 * 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） ； Department of Computer Science & Technology, Tsinghua University（计算机科学与技术系，清华大学） ； Center for Machine Vision and Signal Analysis (CMVS), University of Oulu（机器视觉与信号分析中心，奥卢大学） ； TKLNDST, College of Computer Science, Nankai University（TKLNDST，南开大学计算机学院）
Comments Accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 21 pages, 11 figures, 12 tables
Understanding Adversarial Training with Energy-based Models
机构 * OmnAI Lab research group（OmnAI实验室研究组） ； Sapienza University of Rome（罗马萨皮恩扎大学） ； CVLab（计算机视觉实验室） ； University of Bologna（博洛尼亚大学） ； Eustema S.p.A.（Eustema公司）
Comments Under review for TPAMI
Variational Positive-incentive Noise: How Noise Benefits Models
机构 * Institute of Artificial Intelligence (TeleAI), China Telecom（人工智能研究院（TeleAI），中国电信） ； The University of Hong Kong（香港大学） ； School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University（人工智能学院（iOPEN），西北工业大学）
Comments Acceptted by IEEE Transactions on Pattern Analysis and Machine Intelligence
Compositional Physical Reasoning of Objects and Events from Videos
机构 * MIT-IBM Watson AI lab（MIT-IBM沃森人工智能实验室） ； New York University（纽约大学） ； Harvard University（哈佛大学） ； UIUC（伊利诺伊大学） ； UC Berkeley（加州大学伯克利分校） ； MIT（麻省理工学院） ； UMass Amherst（马萨诸塞大学阿姆赫斯特分校）
Comments Accepted by TPAMI 2025. arXiv admin note: text overlap with arXiv:2205.01089
Towards Understanding the Generalizability of Delayed Stochastic Gradient Descent
机构 * Intelligent Game and Decision Lab（智能游戏与决策实验室） ； College of Computer Science and Technology（计算机科学与技术学院） ； National University of Defense Technology（国防科技大学） ； Sun Yat-sen University（中山大学） ； JD Explore Academy（京东探索研究院）
Comments Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025
Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior
机构 * Department of Statistics and Actuarial Science, University of Hong Kong（统计与精算科学系，香港大学）
Comments To appear in TPAMI
SceneTracker: Long-term Scene Flow Estimation Network
Journal ref IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025
Graph Network for Sign Language Tasks
机构 * 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） ； Department of Computer Science, University of Warwick（计算机科学系，沃里克大学）
Comments 17 pages, 9 figures, submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI). This is a regular paper submission
DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection
机构 * Institute of Trustworthy Embodied AI, Fudan University（复旦大学可信具身人工智能研究院） ； School of Computer Science, Zhejiang University of Technology（浙江工业大学计算机学院） ； School of Communication & Information Engineering, Shanghai University（上海大学通信与信息工程学院）
Comments Accepted by TPAMI
IMPACT: A Generic Semantic Loss for Multimodal Medical Image Registration
机构 * Univ. Rennes, CLCC Eugene Marquis, INSERM, LTSI - UMR 1099（里昂大学、CLCC Eugene Marquis、INSERM、LTSI - UMR 1099） ； CSIRO Australian e-Health Research Centre（澳大利亚e-Health研究中心） ； CHU Rennes, Department of Cardio-Thoracic and Vascular Surgery（里昂大学医院、心胸和血管外科部门）
Comments Submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). This is a preprint version and has not been peer-reviewed
Fair Representation Learning for Continuous Sensitive Attributes using Expectation of Integral Probability Metrics
机构 * Department of Applied Mathematics, University of Twente（应用数学系，特文特大学） ； Department of Statistics, Seoul National University（统计系，首尔国立大学）
Comments 42 pages, 30 figures. IEEE Transactions on Pattern Analysis and Machine Intelligence (2025)
IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching
机构 * 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） ； HiScene Information Technology Co., Ltd.（HiScene信息技术有限公司）
Comments Accepted by TPAMI 2025
USTEP: Spatio-Temporal Predictive Learning under A Unified View
机构 * Zhejiang University（浙江大学） ； AI Lab, Research Center for Industries of the Future（人工智能实验室、未来产业研究中心） ； Westlake University（西湖大学）
Comments Accepted by TPAMI
MOWA: Multiple-in-One Image Warping Model
机构 * S-Lab, Nanyang Technological University (NTU), Singapore（南洋理工大学S实验室） ； SenseTime Research（商汤科技研究院）
Comments Accepted to TPAMI. Project page: https://kangliao929.github.io/projects/mowa/
Joint Modeling of Feature, Correspondence, and a Compressed Memory for Video Object Segmentation
机构 * State Key Laboratory for Novel Software Technology, Nanjing University（新型软件技术国家重点实验室）
Comments Accepted by TPAMI. Code and trained models are available at \url{https://github.com/MCG-NJU/JointFormer}
