Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning
Open paper
Benchmark
Model
Rank
Results
zero-shot-action-recognition-on-kinetics-400-zero-shot-action-classification
PE-AV Large (30 fps, zero-shot) (extra data)
#1
Accuracy: 78.9
Rank counts only results with a code link.