Progressive Confident Masking Attention Network for Audio-Visual Segmentation
Paper
•
2406.02345
•
Published
YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Model Card for PCMANet
This modelcard contains checkpoints of PCMANet for Audio-Visual Segmentation (AVS) task.
Model Sources [optional]
- Repository: [https://github.com/PrettyPlate/PCMANet]
- Paper [optional]: [https://arxiv.org/abs/2406.02345]
Training Details
Training Data
We use public AVSBench datasets for training. Details can be found at AVSBench.
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support