杨棣，特任副研究员，博士毕业于法国国家信息与自动化研究所（Inria），后于Inria从事博士后研究工作，2025年加入中国科学技术大学人工智能与数据科学学院（苏州）。研究方向聚焦于解决复杂场景下人体姿态估计、运动建模与生成、行为感知的关键问题，其研究成果在安全监控、智慧医疗、具身智能等多个行业中广泛应用。曾参与承担法国ANR国家级科研项目，并主导与丰田汽车比利时欧洲总公司（Toyota Europe）跨国产研合作项目。已在IEEE T-PAMI、IJCV、ICCV、ICLR、AAAI等顶级国际会议和期刊上发表多篇论文，申请多项专利，担任IEEE T-PAMI、IEEE T-IP、CVPR、ICCV、AAAI、ICRA等多个顶级刊物审稿人。与法国国家信息与自动化研究所、上海人工智能实验室、英特灵达人工智能实验室等国内外前沿科研团队长期密切合作。

邮箱：di.yang@ustc.edu.cn

个人主页：https://walker1126.github.io

联系地址：中国科学技术大学苏州高等研究院，思贤楼324

主要研究方向：计算机视觉、视频生成与理解、运动建模与行为感知、健康监测等

主要学术论文：

Di Yang, Yaohui Wang, Antitza Dantcheva, Lorenzo Garattoni, Gianpiero Francesca, Francois Bremond. View-Invariant Skeleton Action Representation Learning via Motion Retargeting. International Journal of Computer Vision (IJCV), 2024.

Di Yang, Yaohui Wang, Antitza Dantcheva, Quan Kong, Lorenzo, Garattoni, Gianpiero Francesca, Francois Bremond. LAC - Latent Action Composition for Skeleton-based Action Segmentation. IEEE/CVF International Conference on Computer Vision (ICCV), 2023.

Di Yang, Yaohui Wang, Quan Kong, Antitza Dantcheva, Lorenzo Garattoni, Gianpiero Francesca, Francois Bremond. Self-Supervised Video Representation Learning via Latent Time Navigation. AAAI Conference on Artificial Intelligence (AAAI), 2023.

Di Yang, Yaohui Wang, Antitza Dantcheva, Lorenzo Garattoni, Gianpiero Francesca, Francois Bremond. UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition. British Machine Vision Conference (BMVC Oral), 2021.

Di Yang, Rui Dai, Yaohui Wang, Rupayan Mallick, Luca Minciullo, Gianpiero Francesca, Francois Bremond. Selective Spatio-Temporal Aggregation Based Pose Refinement System: Towards Understanding Human Activities in Real-World Videos. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV Oral), 2021.

Di Yang, Yaohui Wang, Antitza Dantcheva, Lorenzo Garattoni, Gianpiero Francesca, Francois Bremond. Self-Supervised Video Pose Representation Learning for Occlusion-Robust Action Recognition. IEEE International Conference on Automatic Face and Gesture Recognition (FG Oral), 2021.

Yaohui Wang, Di Yang, Francois Bremond, Antitza Dantcheva. Latent Image Animator. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2024. 

Yaohui Wang, Di Yang, Francois Bremond, Antitza Dantcheva. Latent Image Animator: Learning to animate Image via Latent Space Navigation. International Conference on Learning Representations (ICLR), 2022.

Srijan Das, Rui Dai, Di Yang, Francois Bremond. VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2021. 

Mahmoud ALI; Di Yang*; Francois Bremond; Are Visual-Language Models Effective in Action Recognition? A Comparative Study. European Conference on Computer Vision (ECCV), 2024.

Mahmoud ALI; Di Yang; Arkaprava Sinha; Dominick Reilly; Srijan Das; Gianpiero Francesca; François Brémond; Quo Vadis, Video Understanding with Vision-Language Foundation Models?, Conference on Neural Information Processing Systems Workshops (NeurIPSW), 2024.

Arnab Dey; Di Yang; Antitza Dantcheva; Jean Martinet; HFNeRF: Learning Human Biomechanic Features with Neural Radiance Fields, IEEE Conference on Artificial Intelligence (CAI), 2024.

Arnab Dey; Di Yang; Rohith Agaram; Antitza Dantcheva; Andrew I. Comport; Srinath Sridhar; Jean Martinet; GHNeRF: Learning Generalizable Human Features with Efficient Neural Radiance Fields, IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2024.