Audio-Visual Video Parsing on LLP 1.0 (test)
68.1Segment-level AudioVALOR++
Evaluation Results
| Method | Links | ||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VALOR++Feature extractors=CLIP and CLAP2023.05 | 68.1 | 68.4 | 61.9 | 66.2 | 66.8 | 61.2 | 64.7 | 55.5 | 60.4 | 59 | — | — | — | — | — | — | — | — | — | — | |
| VALOR+Architecture=thinner yet deeper HAN2023.05 | 62.8 | 66.7 | 60 | 63.2 | 62.3 | 57.1 | 63.9 | 54.4 | 58.5 | 55.9 | — | — | — | — | — | — | — | — | — | — | |
| VALORArchitecture=HAN2023.05 | 61.8 | 65.9 | 58.4 | 62 | 61.5 | 55.4 | 62.6 | 52.2 | 56.7 | 54.2 | — | — | — | — | — | — | — | — | — | — | |
| DHHN2023.05 | 61.3 | 58.3 | 52.9 | 57.5 | 58.1 | 54 | 55.1 | 47.3 | 51.5 | 51.5 | — | — | — | — | — | — | — | — | — | — | |
| JoMOLD2023.05 | 61.3 | 63.8 | 57.2 | 60.8 | 59.9 | 53.9 | 59.9 | 49.6 | 54.5 | 52.5 | — | — | — | — | — | — | — | — | — | — | |
| MM-Pyr2023.05 | 60.9 | 54.4 | 50 | 55.1 | 57.6 | 52.7 | 51.8 | 44.4 | 49.9 | 50.5 | — | — | — | — | — | — | — | — | — | — | |
| MGN2023.05 | 60.8 | 55.4 | 50.4 | 55.5 | 57.2 | 51.1 | 52.4 | 44.4 | 49.3 | 49.1 | — | — | — | — | — | — | — | — | — | — | |
| VPLANpseudo label denoising=not applied2023.05 | 60.5 | 64.8 | 58.3 | 61.2 | 59.4 | 51.4 | 61.5 | 51.2 | 54.7 | 50.8 | — | — | — | — | — | — | — | — | — | — | |
| MA2023.05 | 60.3 | 60 | 55.1 | 58.9 | 57.9 | 53.6 | 56.4 | 49 | 53 | 50.6 | — | — | — | — | — | — | — | — | — | — | |
| HAN2023.05 | 60.1 | 52.9 | 48.9 | 54 | 55.4 | 51.3 | 48.9 | 43 | 47.7 | 48 | — | — | — | — | — | — | — | — | — | — | |
| CVCMS2023.05 | 59.2 | 59.9 | 53.4 | 57.5 | 58.1 | 51.3 | 55.5 | 46.2 | 51 | 49.7 | — | — | — | — | — | — | — | — | — | — | |
| AVSDN2023.05 | 47.8 | 52 | 37.1 | 45.7 | 50.8 | 34.1 | 46.3 | 26.5 | 35.6 | 37.7 | — | — | — | — | — | — | — | — | — | — | |
| AVE2023.05 | 47.2 | 37.1 | 35.4 | 39.9 | 41.6 | 40.4 | 34.7 | 31.6 | 35.5 | 36.5 | — | — | — | — | — | — | — | — | — | — | |
| AVE2023.06 | — | — | — | — | — | — | — | — | — | — | 47.2 | 37.1 | 35.4 | 39.9 | 41.6 | 40.4 | 34.7 | 31.6 | 35.5 | 36.5 | |
| AVSDN2023.06 | — | — | — | — | — | — | — | — | — | — | 47.8 | 52 | 37.1 | 45.7 | 50.8 | 34.1 | 46.3 | 26.5 | 35.6 | 37.7 | |
| CMPAE2023.06 | — | — | — | — | — | — | — | — | — | — | 64.2 | 66.4 | 59.2 | 63.3 | 62.8 | 56.6 | 63.7 | 51.8 | 57.4 | 55.7 | |
| CVCMS2023.06 | — | — | — | — | — | — | — | — | — | — | 60.8 | 63.5 | 57 | 60.5 | 59.5 | 53.8 | 58.9 | 49.5 | 54 | 52.1 | |
| DHHN2023.06 | — | — | — | — | — | — | — | — | — | — | 61.4 | 63.4 | 56.8 | 60.5 | 59.5 | 54.6 | 60.8 | 51.1 | 55.5 | 53.3 | |
| HANbaseline_framework=true2023.06 | — | — | — | — | — | — | — | — | — | — | 60.1 | 52.9 | 48.9 | 54 | 55.4 | 51.3 | 48.9 | 43 | 47.7 | 48 | |
| JoMOLD2023.06 | — | — | — | — | — | — | — | — | — | — | 61.3 | 63.8 | 57.2 | 60.8 | 59.9 | 53.9 | 59.9 | 49.6 | 54.5 | 52.5 | |
| LSLD2023.06 | — | — | — | — | — | — | — | — | — | — | 62.7 | 67.1 | 59.4 | 63.1 | 62.2 | 55.7 | 64.3 | 52.6 | 57.6 | 55.2 | |
| LSLD+CLAP+CLIPaudio_features=CLAP, visual_features=CLIP2023.06 | — | — | — | — | — | — | — | — | — | — | 68.7 | 71.3 | 63.4 | 67.8 | 68.2 | 61.5 | 67.4 | 55.9 | 61.6 | 60.6 | |
| MA2023.06 | — | — | — | — | — | — | — | — | — | — | 60.3 | 60 | 55.1 | 58.9 | 57.9 | 53.6 | 56.4 | 49 | 53 | 50.6 | |
| MGN2023.06 | — | — | — | — | — | — | — | — | — | — | 60.8 | 55.4 | 50.4 | 55.5 | 57.2 | 51.1 | 52.4 | 44.4 | 49.3 | 49.1 | |
| MM-Pyramid2023.06 | — | — | — | — | — | — | — | — | — | — | 61.1 | 60.3 | 55.8 | 59.7 | 59.1 | 53.8 | 56.7 | 49.4 | 54.1 | 51.2 |