Video understanding has largely relied on deep spatiotemporal architectures, including 3D convolutional networks and optical flow (OF) based models. While effective, these methods are often computationally expensive and depend on heuristic motion representations that are sensitive to illumination, scale, and structural changes. To address these limitations, we propose ReynoldsFlow, a physics-inspired representation grounded in the Reynolds transport theorem (RTT) and Helmholtz-Hodge decomposition (HHD). ReynoldsFlow decomposes motion into curl-free (CF) and divergence-free (DF) components, providing a principled and interpretable characterization of scene dynamics. By coupling intensity information with decomposed motion cues, it produces dynamics-aware, texture-preserving features that boost downstream tasks such as pose estimation, action recognition, and tiny object detection. Lightweight and modular, ReynoldsFlow can be readily integrated into existing architectures. Experiments across diverse benchmarks show that ReynoldsFlow consistently matches or surpasses existing approaches, offering improved generalizability and computational efficiency.
Learning Transferable Spatiotemporal Representations from Natural Script Knowledge
Tsinghua University(清华大学);The University of Hong Kong(香港大学);Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));Applied Research Center (ARC), Tencent PCG(腾讯平台与内容事业群应用研究中心)
Beihang University(北京航空航天大学);Beijing Institute of Technology(北京理工大学);King Abdullah University of Science and Technology(阿卜杜拉国王科技大学);City University of Hong Kong(香港城市大学);University of Cambridge(剑桥大学);Tsinghua University(清华大学);Beijing Tongren Hospital, Capital Medical University(首都医科大学附属北京同仁医院);Shandong University(山东大学);Northeastern University(东北大学)
Deepfake Video Detection with Spatiotemporal Dropout Transformer
Institute of Information Engineering, Chinese Academy of Science(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);School of Communication and Information Engineering, Shanghai University(上海大学通信与信息工程学院)
Minimal Solvers for Full-DoF Motion Estimation from Asynchronous Differential SfM
College of Aerospace Science and Engineering, National University of Defense Technology(国防科技大学空天科学学院);The Hunan Provincial Key Laboratory of Image Measurement and Vision Navigation(湖南省图像测量与视觉导航重点实验室)
Schrödinger-Inspired Time-Evolution for 4D Deformation Forecasting
Department of Mathematics, University of Innsbruck(数学系,因斯布鲁克大学);Department of Radiology, Medical University of Innsbruck(放射学系,因斯布鲁克医学院);Neuroimaging Research Core Facility, Medical University of Innsbruck(神经影像研究核心设施,因斯布鲁克医学院)
Video-Arena: A Scalable Agentic Video Benchmark for Spatiotemporal Capability
miHoYo Honkai AI R&D Team(米哈游崩坏AI研发团队);College AI, Tsinghua University(清华大学人工智能学院);University of Chinese Academy of Sciences(中国科学院大学);MMLab, The University of Hong Kong(香港大学多媒体实验室);National University of Singapore(新加坡国立大学)
StabStitch++: Unsupervised Online Video Stitching with Spatiotemporal Bidirectional Warps
Institute of Information Science, Beijing Jiaotong University(北京交通大学信息科学学院);Visual Intelligence +X International Cooperation Joint Laboratory of MOE, Beijing(教育部视觉智能+X国际合作联合实验室);School of Computing and Data Science, Nanyang Technological University(南洋理工大学计算机与数据科学学院);School of Media Engineering, Communication University of Zhejiang(浙江传媒学院媒体工程学院);School of Information and Communication Engineering, University of Electronic Science and Technology of China(电子科技大学信息与通信工程学院)
Learning Natural Consistency Representation for Face Forgery Video Detection
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);University of Chinese Academy of Sciences(中国科学院大学);Tsinghua University(清华大学);RealAI
Spatiotemporal Attention Learning Framework for Event-Driven Object Recognition
City University of Hong Kong(香港城市大学);Shenzhen Research Institute, City University of Hong Kong(香港城市大学深圳研究院);State Key Laboratory of Terahertz and Millimeter Waves, City University of Hong Kong(香港城市大学太赫兹与毫米波国家重点实验室)
Chaos in Motion: Unveiling Robustness in Remote Heart Rate Measurement through Brain-Inspired Skin Tracking
School of Information Science and Engineering, Lanzhou University(兰州大学信息科学与工程学院);School of Electronics and Information Engineering, Lanzhou Jiaotong University(兰州交通大学电子与信息工程学院);The First Hospital of Lanzhou University(兰州大学第一医院);School of Artificial Intelligence, Nanjing University of Information Science and Technology(南京信息工程大学人工智能学院)