README.md

---
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{wen2024chase,
    title={CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition},
    author={Yuhang Wen and Mengyuan Liu and Songtao Wu and Beichen Ding},
    booktitle={Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS)},
    year={2024},
}
```