README.md

Progressive Confident Masking Attention Network for Audio-Visual Segmentation

This is the official PyTorch implementation for the paper Progressive Confident Masking Attention Network for Audio-Visual Segmentation ([arXiv]). This paper proposes the Audio-Visual Segmentation (AVS) and Audio-Visual Semantic Segmentation (AVSS) problem.

Acknowledge

The code is based on the AVSBench.

Citation

@article{wang2024progressive,
  title={Progressive Confident Masking Attention Network for Audio-Visual Segmentation},
  author={Wang, Yuxuan and Dong, Feng and Zhu, Jinchao},
  journal={arXiv preprint arXiv:2406.02345},
  year={2024}
}