---
license: apache-2.0
language:
- en
metrics:
- accuracy
---

# \[NeurIPS 2024\] CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition

ArXiv: https://arxiv.org/abs/2410.07153

Github: https://github.com/Necolizer/CHASE

Checkpoints of best backbone (+CHASE) for each benchmark:
- NTU Mutual 11 (XSub): STSA-Net (+CHASE)
- NTU Mutual 11 (XView): CTR-GCN (+CHASE)
- NTU Mutual 26 (XSub): InfoGCN (+CHASE)
- NTU Mutual 26 (XSet): InfoGCN (+CHASE)
- H2O: STSA-Net (+CHASE)
- Assembly101 (Action): CTR-GCN (+CHASE)
- Collective Activity: CTR-GCN (+CHASE)
- Volleyball (Original): CTR-GCN (+CHASE)

## Citation
```
@inproceedings{NEURIPS2024_wen2024chase,
    author = {Wen, Yuhang and Liu, Mengyuan and Wu, Songtao and Ding, Beichen},
    booktitle = {Advances in Neural Information Processing Systems},
    editor = {A. Globerson and L. Mackey and D. Belgrave and A. Fan and U. Paquet and J. Tomczak and C. Zhang},
    pages = {9388--9420},
    publisher = {Curran Associates, Inc.},
    title = {CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition},
    url = {https://proceedings.neurips.cc/paper_files/paper/2024/file/11f5520daf9132775e8604e89f53925a-Paper-Conference.pdf},
    volume = {37},
    year = {2024}
}
```