Audio-guided Video Object Segmentation on Audio-Guided-VOS
59J&F ScoreEPCFormer
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| EPCFormerVisual Backbone=ViT-H, Audio Backbone=HUBERT2023.08 | 59 | 58.9 | 59.1 | |
| EPCFormerVisual Backbone=ResNet-50, Audio Backbone=HUBERT2023.08 | 54.3 | 54.3 | 54.2 | |
| WnetVisual Backbone=ResNet-50, Audio Backbone=MFCC2023.08 | 44 | 43 | 45 | |
| RAM+Visual Backbone=I3D, Audio Backbone=MFCC2023.08 | 38.8 | 38.6 | 38.9 | |
| VisTR+Visual Backbone=ResNet-50, Audio Backbone=MFCC2023.08 | 38.8 | 38 | 39.5 | |
| URVOS+Visual Backbone=ResNet-50, Audio Backbone=MFCC2023.08 | 38.2 | 37.1 | 39.2 |