Our research interests include pose estimation, human parsing and skeleton-base action recognition.
@article{wang2021amanet,
title={AMANet: Adaptive Multi-Path Aggregation for Learning Human 2D-3D Correspondences},
author={Wang, Xuanhan and Gao, Lianli and Song, Jingkuan and Guo, Yuyu and Shen, Heng Tao},
journal={IEEE Transactions on Multimedia},
year={2021},
publisher={IEEE}
}
@inproceedings{wang2021semantic,
title={Semantic-aware Transfer with Instance-adaptive Parsing for Crowded Scenes Pose Estimation},
author={Wang, Xuanhan and Gao, Lianli and Dai, Yan and Zhou, Yixuan and Song, Jingkuan},
booktitle={Proceedings of the 29th ACM International Conference on Multimedia},
pages={686--694},
year={2021}
}
@inproceedings{dai2021rsgnet,
title={RSGNet: Relation based Skeleton Graph Network for Crowded Scenes Pose Estimation},
author={Dai, Yan and Wang, Xuanhan and Gao, Lianli and Song, Jingkuan and Shen, Heng Tao},
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
volume={35},
number={2},
pages={1193--1200},
year={2021}
}
@inproceedings{wang2020ktn,
title={KTN: Knowledge Transfer Network for Multi-person DensePose Estimation},
author={Wang, Xuanhan and Gao, Lianli and Song, Jingkuan and Shen, Heng Tao},
booktitle={Proceedings of the 28th ACM International Conference on Multimedia},
pages={3780--3788},
year={2020}
}
@inproceedings{WangACFL,
title = {Skeleton-based Action Recognition via Adaptive Cross-Form Learning},
author={Xuanhan Wang and Yan Dai and Lianli Gao and Jingkuan Song},
booktitle = {ACM MM},
year={2022}
}