Event Localization (A → V) on VGGSound AVEL 90K
70.4Segment-level AccuracyCoDAAR
Evaluation results
| Method | Links | |
|---|---|---|
| CoDAARSetting=AVT2026.05 | 70.4 | |
| CoDAARModality Setting=AV2026.05 | 67.2 | |
| DCIDModality Setting=AV2026.05 | 64.8 | |
| DCIDSetting=AVT2026.05 | 64.2 | |
| MICUSetting=AVT2026.05 | 47.1 | |
| MICUModality Setting=AV2026.05 | 46.1 | |
| CMCMModality Setting=AV2026.05 | 43.9 | |
| TURNModality Setting=AV2026.05 | 37.6 | |
| CODISModality Setting=AV2026.05 | 36.4 | |
| BaselineSetting=AVT2026.05 | 9.4 | |
| BaselineModality Setting=AV2026.05 | 7.6 |