List your company

Audio-visual Recognition on EPIC-SOUNDS (test val)

61AccuracyCA2ST
30.63238.51646.454.284Mar 30, 2025

Evaluation results

MethodLinks
CA2STParam.=320M, Throughput (V/s)=30, Latency (ms)=54.8, GFLOPs=4542025.0361
CAVAParam.=216M, Throughput (V/s)=65, Latency (ms)=36.6, GFLOPs=2362025.0360.3
CASTParam.=217M, Throughput (V/s)=37, Latency (ms)=38.5, GFLOPs=3912025.0347.8
CLIP-BParam.=86M, Throughput (V/s)=81, Latency (ms)=14.7, GFLOPs=1522025.0331.9
VideoMAE-BParam.=87M, Throughput (V/s)=67, Latency (ms)=17.6, GFLOPs=1922025.0331.8