List your company

Audio-Visual Segmentation on VPO-SS 1.0 (test)

74.97J & FB ScoreRAVS
43.416451.608259.867.9918Mar 17, 2025May 2, 2025Jun 18, 2025Aug 4, 2025Sep 20, 2025Nov 6, 2025Dec 23, 2025

Evaluation results

MethodLinks
RAVS2025.1274.9768.0381.9
DDAVSVisual Backbone=MiT-B5, Audio Encoder=HTSAT2025.1274.867.8281.77
DDESegVisual Backbone=Trans., Audio Backbone=HTSAT, Trainable Params=103.84M, Input Resolution=224 x 2242025.0374.3867.5581.2
DDESeg2025.1274.3867.5581.2
DDESegVisual Backbone=Trans., Audio Backbone=VGGish, Trainable Params=103.84M, Input Resolution=224 x 2242025.0373.7867.0280.54
CPM*Visual Backbone=ResNet50, Audio Backbone=VGGish, Input Resolution=Original2025.0373.4967.0979.88
AVSStoneVisual Backbone=SwinBase, Audio Backbone=VGGish, Trainable Params=114.63M, Input Resolution=224 x 2242025.0368.5459.7277.35
AAVS2025.1268.5459.7277.35
BiasAVSVisual Backbone=SwinBase, Audio Backbone=VGGish, Trainable Params=107.12M, Input Resolution=224 x 2242025.0367.4659.1475.78
BiasAVS2025.1267.4659.1475.78
CAVPVisual Backbone=ResNet50, Audio Backbone=VGGish, Trainable Params=119.79M, Input Resolution=224 x 2242025.0367.0258.8175.23
CAVP2025.1267.0258.8175.23
AVSegFormerVisual Backbone=PVT-V2-B5, Audio Backbone=VGGish, Trainable Params=186.05M, Input Resolution=224 x 2242025.0345.9443.8148.06
AVSegFormer2025.1245.9443.8148.06
TPAVIVisual Backbone=PVT-V2-B5, Audio Backbone=VGGish, Trainable Params=101.32M, Input Resolution=224 x 2242025.0344.6341.6447.62
TPAVI2025.1244.6341.6447.62