Publications

Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences
Yujie Zhou, Haodong Duan, Anyi Rao, Bing Su, Jiaqi Wang
AAAI Conference on Artificial Intelligence, 2023
[Paper] [Code]

PYSKL: Towards Good Practices for Skeleton Action Recognition
Haodong Duan, Jiaqi Wang, Kai Chen, Dahua Lin
ACM International Conference on Multimedia, 2022
Demonstrate a frustratingly simple and extremely strong baseline ST-GCN++ for skeleton action recognition.
[Paper] [Code]

TransRank: Self-supervised Video Representation Learning via Ranking-based Transformation Recognition
Haodong Duan, Nanxuan Zhao, Kai Chen, Dahua Lin
The Conference on Computer Vision and Pattern Recognition, 2022
[Paper]

OCSampler: Compressing Videos to One Clip with Single-step Sampling
Jintao Lin, Haodong Duan, Kai Chen, Dahua Lin, Limin Wang
The Conference on Computer Vision and Pattern Recognition, 2022
[Paper]

Revisiting skeleton-based action recognition
Haodong Duan, Yue Zhao, Kai Chen, Dahua Lin, Bo Dai
The Conference on Computer Vision and Pattern Recognition, 2022
The state-of-the-art on NTURGB+D and Kinetics skeleton action recognition, as well as a novel solution.
[Paper] [Code] [Dataset]

Omni-sourced webly-supervised learning for video recognition
Haodong Duan, Yue Zhao, Yuanjun Xiong, Wentao Liu, Dahua Lin
The European Conference on Computer Vision, 2020
The state-of-the-art on Kinetics-400 action recognition.
[Paper] [Code] [Dataset]

TRB: a novel triplet representation for understanding 2d human body
Haodong Duan, Kwan-Yee Lin, Sheng Jin, Wentao Liu, Chen Qian, Wanli Ouyang
The International Conference on Computer Vision, 2019
[Paper] [Dataset]