List your company

Audio-Visual Action Recognition on HD-EPIC-SOUNDS

31.9Top-1 AccuracyTIM
24.82826.66428.530.336Mar 30, 2025

Evaluation results

MethodLinks
TIMModality=A+V, Param.=435M, GFLOPs=460172025.0331.9
CAVAModality=A+V, Param.=216M, GFLOPs=2362025.0328.6
CA2STModality=A+V, Param.=320M, GFLOPs=4542025.0328.1
Auditory SlowFastModality=A, Param.=26M, GFLOPs=42025.0327.9
CASTModality=V, Param.=217M, GFLOPs=3912025.0327.8
TIMModality=A, Param.=64M, GFLOPs=1162025.0326.9
SSASTModality=A2025.0325.1