SOTAVerified

Audio-visual Question Answering

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–27 of 27 papers

TitleStatusHype
CAD -- Contextual Multi-modal Alignment for Dynamic AVQA—0
Target-Aware Spatio-Temporal Reasoning via Answering Questions in Dynamics Audio-Visual ScenariosCode0
Show:102550
← PrevPage 2 of 2Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1VASTAcc80.7—Unverified
2CoQo(Internvideo2)Acc79.6—Unverified
3VALORAcc78.9—Unverified
4CADAcc78.26—Unverified
5LAVISHAcc77.08—Unverified
6ST-AVQAAcc71.52—Unverified