README.md

---
license: apache-2.0
tags:
  - saliency
  - gaze-prediction
  - video-understanding
---

# DiffSal Weights (Mirror)

Pretrained weights for [DiffSal](https://github.com/junwenxiong/diff_sal) (CVPR 2024).

Mirrored from Google Drive for reliable Docker builds.

## Files
- `best.pth`: 1102.0 MB


## Citation
```bibtex
@inproceedings{xiong2024diffsal,
  title={DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction},
  author={Xiong, Junwen and Zhang, Peng and You, Tao and Li, Chengyu and Huang, Wei and Zha, Yongfei},
  booktitle={CVPR},
  year={2024}
}
```