Audio-Visual Sound Segmentation on AVISeg (test)
44.12FSLASeaVIS
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| SeaVISOrigin Task=AVIS, Venue=-, Audio Modality=true, Backbone=ResNet-502026.03 | 44.12 | 63.71 | 41.23 | 34.26 | 31.15 | 53.66 | 72.36 | 57.67 | |
| AVISMOrigin Task=AVIS, Venue=CVPR’ 25, Audio Modality=true, Backbone=ResNet-502026.03 | 42.78 | 61.73 | 40.57 | 32.22 | 29.83 | 52.4 | 71.15 | 54.97 | |
| COMBOVenue=CVPR' 24, Audio=true2023.10 | 39.49 | 57.39 | 37.84 | 21.91 | 27.18 | 49.63 | 68.87 | 50.12 | |
| COMBOOrigin Task=AVSS, Venue=CVPR’ 24, Audio Modality=true, Backbone=ResNet-502026.03 | 39.49 | 57.39 | 37.84 | 21.91 | 27.18 | 49.63 | 68.87 | 50.12 | |
| VITAOrigin Task=VIS, Venue=NeurIPS’ 22, Audio Modality=false, Backbone=ResNet-502026.03 | 38.04 | 57.48 | 36.25 | 15.04 | 27.98 | 47.45 | 69.86 | 48.96 | |
| AVSegFormerVenue=AAAI' 24, Audio=true2023.10 | 35.66 | 55.74 | 35.72 | 18.58 | 27.51 | 43.08 | 67.13 | 48.51 | |
| AVSegFormerOrigin Task=AVSS, Venue=AAAI’ 24, Audio Modality=true, Backbone=ResNet-502026.03 | 35.66 | 55.74 | 35.72 | 18.58 | 27.51 | 43.08 | 67.13 | 48.51 | |
| LBVQOrigin Task=VIS, Venue=TCSVT’ 24, Audio Modality=false, Backbone=ResNet-502026.03 | 34.73 | 56.97 | 36.58 | 27.71 | 29.52 | 38.96 | 68.34 | 48.83 | |
| TeViTOrigin Task=VIS, Venue=CVPR’ 22, Audio Modality=false, Backbone=ResNet-502026.03 | 32.28 | 53.67 | 31.52 | 0 | 28.07 | 39.18 | 65.27 | 45.1 | |
| SeqFormerOrigin Task=VIS, Venue=ECCV’ 22, Audio Modality=false, Backbone=ResNet-502026.03 | 30.32 | 54.32 | 32.79 | 25.03 | 21.76 | 36.46 | 67.25 | 45.23 | |
| Mask2Former-VISOrigin Task=VIS, Venue=CVPR’ 22, Audio Modality=false, Backbone=ResNet-502026.03 | 29.75 | 52.03 | 28.66 | 0 | 25.47 | 36.37 | 64.49 | 43.33 | |
| DAVISOrigin Task=VIS, Venue=ICCV’ 23, Audio Modality=false, Backbone=ResNet-502026.03 | 23.99 | 49.12 | 19.83 | 14.61 | 24.83 | 24.69 | 63.51 | 40.11 |