ResearchBenchmarksAudiovisual Captioning on VALOR-32KFollow9.6B@4VALORL5.2326.3667.58.634Apr 17, 2023Evaluation ResultsMethodMethodLinksB@4MRCVALORL#Example=33.5M, Mod=V+A#Example=33.5M, Mod=V+A2023.049.615.431.861.5VALORB#Example=6.5M, Mod=V+A#Example=6.5M, Mod=V+A2023.048.914.830.855.7VALOR#Example=5.5M, Mod=V#Example=5.5M, Mod=V2023.04813.529.444.3SMPFFMod=V+AMod=V+A2023.047.512.628.637.1SwinBERTMod=VMod=V2023.045.410.727.227.3