HybridFormer: Bridging Local and Global Spatio-Temporal Dynamics for Efficient Skeleton-Based Action Recognition

Zhong et al. "HybridFormer: Bridging Local and Global Spatio-Temporal Dynamics for Efficient Skeleton-Based Action Recognition." European Conference on Computer Vision Workshops, 2024. doi:10.1007/978-3-031-91575-8_2

[Zhong et al. "HybridFormer: Bridging Local and Global Spatio-Temporal Dynamics for Efficient Skeleton-Based Action Recognition." European Conference on Computer Vision Workshops, 2024.](https://mlanthology.org/eccvw/2024/zhong2024eccvw-hybridformer/) doi:10.1007/978-3-031-91575-8_2

@inproceedings{zhong2024eccvw-hybridformer,
  title     = {{HybridFormer: Bridging Local and Global Spatio-Temporal Dynamics for Efficient Skeleton-Based Action Recognition}},
  author    = {Zhong, Zeyun and Li, Tianrui and Martin, Manuel and Cormier, Mickael and Wu, Chengzhi and Diederichs, Frederik and Beyerer, Juergen},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2024},
  pages     = {19-35},
  doi       = {10.1007/978-3-031-91575-8_2},
  url       = {https://mlanthology.org/eccvw/2024/zhong2024eccvw-hybridformer/}
}