3D Detection | 3D Face Modeling | 3D Human Reconstruction | 3D Object Detection | 3D Shape Correspondence | 3D Shape Generation | 3D Shape Reconstruction | Activity Recognition | Agentic AI | Application | Biometrics | Body Matching | Camera Calibration | Camera+LiDAR+Radar | Data Imputation | Database | Dataset | Deepfake | Depth Completion | Depth Estimation | Depth Prediction | Domain Adaptation | Expression Recognition | Face Alignment | Face Antispoofing | Face Deidentification | Face Recognition | Face Reconstruction | Face Relighting | Face Synthesis | Forecasting | Gait Recognition | Generic Object 3D Reconstruction | Human Motion | Human Recognition | Image Alignment | Image Manipulation | Image Segmentation | Low-level Vision | Medical Imaging | Motion Compensation | Multi-modality | Multimedia Retrieval | Object Detection | Object Re-Identification | Pedestrian Detection | Person Re-identification | Plant Vision | Semantic Segmentation | Surveillance | Tracking | Typing Behavior | Vision-language

Human Motion

2026

  • H-Flow: Self-supervised Human Scene Flow via Physics-inspired Joint Multi-modal Learning
    Zhanbo Huang, Xiaoming Liu, Yu Kong
    Proceeding of Fortieth Conference on Neural Information Processing Systems (NeurIPS 2026), Atlanta, GA, Dec. 2026
    Bibtex | arXiv
    • @inproceedings{ h-flow-self-supervised-human-scene-flow-via-physics-inspired-joint-multi-modal-learning,
      author = { Zhanbo Huang and Xiaoming Liu and Yu Kong },
      title = { H-Flow: Self-supervised Human Scene Flow via Physics-inspired Joint Multi-modal Learning },
      booktitle = { Proceeding of Fortieth Conference on Neural Information Processing Systems },
      address = { Atlanta, GA },
      month = { December },
      year = { 2026 },
    }