Publications

2026

1. 

   TACD: Distilling Efficient Text-to-Motion Models via Terminal Amplification Control

   arXiv 2026

   Wei-Jin Huang, Yuan-Ming Li, Kun-Yu Lin, Wang Luo, Yinlin Zhu, Yue Yu, Shenghao Ye, Junbin Yuan, Fa-Ting Hong, Qing Zhang, and Wei-Shi Zheng

   arXiv preprint arXiv:2610.02867, 2026

   arXiv Code Project BibTeX

   @article{huang2026tacd,
     title = {TACD: Distilling Efficient Text-to-Motion Models via Terminal Amplification Control},
     author = {Huang, Wei-Jin and Li, Yuan-Ming and Lin, Kun-Yu and Luo, Wang and Zhu, Yinlin and Yu, Yue and Ye, Shenghao and Yuan, Junbin and Hong, Fa-Ting and Zhang, Qing and Zheng, Wei-Shi},
     journal = {arXiv preprint arXiv:2610.02867},
     year = {2026},
   }

2. 

   ChoreoPlan: Hybrid Phrase Planning and Execution-Grounded Selection for Music-to-Humanoid Dance

   ACM MM 2026

   Wei-Jin Huang, Jianhong Fan, Hao Huang, Zhi-Wei Xia, Jun-Yi Deng, Yuan-Ming Li, Kun-Yu Lin, and Wei-Shi Zheng

   In Proceedings of the ACM International Conference on Multimedia, 2026

   Project BibTeX

   @inproceedings{huang2026choreoplan,
     title = {ChoreoPlan: Hybrid Phrase Planning and Execution-Grounded Selection for Music-to-Humanoid Dance},
     author = {Huang, Wei-Jin and Fan, Jianhong and Huang, Hao and Xia, Zhi-Wei and Deng, Jun-Yi and Li, Yuan-Ming and Lin, Kun-Yu and Zheng, Wei-Shi},
     booktitle = {Proceedings of the ACM International Conference on Multimedia},
     year = {2026},
   }

3. 

   Beyond Mimicry: Learning Whole-Body Human-Humanoid Interaction from Human-Human Demonstrations

   CVPR 2026

   Wei-Jin Huang, Yue-Yi Zhang, Yi-Lin Wei, Zhi-Wei Xia, Juantao Tan, Yuan-Ming Li, Zhilin Zhao, and Wei-Shi Zheng

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2026

   Paper arXiv BibTeX

   @inproceedings{huang2026learning,
     title = {Beyond Mimicry: Learning Whole-Body Human-Humanoid Interaction from Human-Human Demonstrations},
     author = {Huang, Wei-Jin and Zhang, Yue-Yi and Wei, Yi-Lin and Xia, Zhi-Wei and Tan, Juantao and Li, Yuan-Ming and Zhao, Zhilin and Zheng, Wei-Shi},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     pages = {30740--30749},
     month = jun,
     year = {2026},
   }

2025

1. 

   Less Static, More Private: Towards Transferable Privacy-Preserving Action Recognition by Generative Decoupled Learning

   ICCV 2025

   Zhi-Wei Xia, Kun-Yu Lin, Yuan-Ming Li, Wei-Jin Huang, Xian-Tuo Tan, and Wei-Shi Zheng

   In Proceedings of the IEEE/CVF International Conference on Computer Vision, Oct 2025

   Paper BibTeX

   @inproceedings{xia2025less,
     title = {Less Static, More Private: Towards Transferable Privacy-Preserving Action Recognition by Generative Decoupled Learning},
     author = {Xia, Zhi-Wei and Lin, Kun-Yu and Li, Yuan-Ming and Huang, Wei-Jin and Tan, Xian-Tuo and Zheng, Wei-Shi},
     booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
     pages = {12894--12903},
     month = oct,
     year = {2025},
   }

2. 

   Modeling Multiple Normal Action Representations for Error Detection in Procedural Tasks

   CVPR 2025

   Wei-Jin Huang, Yuan-Ming Li, Zhi-Wei Xia, Yu-Ming Tang, Kun-Yu Lin, Jian-Fang Hu, and Wei-Shi Zheng

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2025

   Paper arXiv BibTeX

   @inproceedings{huang2025modeling,
     title = {Modeling Multiple Normal Action Representations for Error Detection in Procedural Tasks},
     author = {Huang, Wei-Jin and Li, Yuan-Ming and Xia, Zhi-Wei and Tang, Yu-Ming and Lin, Kun-Yu and Hu, Jian-Fang and Zheng, Wei-Shi},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     pages = {27794--27804},
     month = jun,
     year = {2025},
   }

2024

1. 

   EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding

   ECCV 2024

   Yuan-Ming Li, Wei-Jin Huang(Co-First), An-Lan Wang, Ling-An Zeng, Jing-Ke Meng, and Wei-Shi Zheng

   In European Conference on Computer Vision, Jun 2024

   Paper arXiv BibTeX

   @inproceedings{li2024egoexo,
     title = {EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding},
     author = {Li, Yuan-Ming and Huang, Wei-Jin and Wang, An-Lan and Zeng, Ling-An and Meng, Jing-Ke and Zheng, Wei-Shi},
     booktitle = {European Conference on Computer Vision},
     pages = {363--382},
     year = {2024},
     organization = {Springer},
   }