List your company

Audio-visual Segmentation on AVS-Semantic (J&Fm, J, Fm)

63.4Jaccard Index (J)DDESEG
28.45637.52846.655.672Mar 17, 2025

Evaluation results

MethodLinks
DDESEGVisual Backbone=Transformer-based architecture, Audio Backbone=HTSAT2025.0363.467.972.3
DDESEGVisual Backbone=Transformer-based architecture, Audio Backbone=VGGish2025.0362.36771.6
DDESEGVisual Backbone=PVT-V2-B5, Audio Backbone=VGGish2025.0360.865.770.6
AVSStoneVisual Backbone=Swin-Base, Audio Backbone=VGGish2025.0356.861.566.2
QDFormerVisual Backbone=Swin-Tiny, Audio Backbone=VGGish2025.0353.4——
CAVPVisual Backbone=PVT-V2-B5, Audio Backbone=VGGish2025.0348.655.362
BiasAVSVisual Backbone=Swin-Base, Audio Backbone=VGGish2025.0344.447.249.9
COMBOVisual Backbone=PVT-V2-B5, Audio Backbone=VGGish2025.0342.144.146.1
AVSegFormerVisual Backbone=PVT-V2-B5, Audio Backbone=VGGish2025.0337.340.142.8
BAVSVisual Backbone=Swin-Base, Audio Backbone=Beats2025.0333.635.637.5
CATRVisual Backbone=PVT-V2-B5, Audio Backbone=VGGish2025.0332.835.738.5
TPAVIVisual Backbone=PVT-V2-B5, Audio Backbone=VGGish2025.0329.832.535.2