SOTAVerified

audio-visual event localization

Papers

Showing 2126 of 26 papers

TitleStatusHype
AVE-CLIP: AudioCLIP-based Multi-window Temporal Transformer for Audio Visual Event Localization0
Past and Future Motion Guided Network for Audio Visual Event Localization0
Multi-Modulation Network for Audio-Visual Event Localization0
MPN: Multimodal Parallel Network for Audio-Visual Event Localization0
Audio-Visual Event Localization via Recursive Fusion by Joint Co-Attention0
Dual Attention Matching for Audio-Visual Event Localization0
Show:102550
← PrevPage 3 of 3Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1UnAV mAP47.8Unverified
2ActionFormer mAP42.2Unverified