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 },
}
• Unlocking Motion from Large Vision Models with a Semantic and Kinematic Duality for Gait Recognition
  Zhanbo Huang, Dingqiang Ye, Xiaoming Liu, Yu Kong
  In Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR 2026), Denver CO, Jun. 2026
  Bibtex | PDF | Code
@inproceedings{ unlocking-motion-from-large-vision-models-with-a-semantic-and-kinematic-duality-for-gait-recognition,
  author = { Zhanbo Huang and Dingqiang Ye and Xiaoming Liu and Yu Kong },
  title = { Unlocking Motion from Large Vision Models with a Semantic and Kinematic Duality for Gait Recognition },
  booktitle = { In Proceeding of IEEE Computer Vision and Pattern Recognition },
  address = { Denver CO },
  month = { June },
  year = { 2026 },
}

2025

• H-MoRe: Learning Human-centric Motion Representation for Action Analysis
  Zhanbo Huang, Xiaoming Liu, Yu Kong
  In Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR 2025), Nashville, TN, Jun. 2025
  Bibtex | arXiv
@inproceedings{ h-more-learning-human-centric-motion-representation-for-action-analysis,
  author = { Zhanbo Huang and Xiaoming Liu and Yu Kong },
  title = { H-MoRe: Learning Human-centric Motion Representation for Action Analysis },
  booktitle = { In Proceeding of IEEE Computer Vision and Pattern Recognition },
  address = { Nashville, TN },
  month = { June },
  year = { 2025 },
}