Text-to-Video-Audio Retrieval on YouCook2
51.3Recall@1MiCo
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| MiCo2024.06 | 51.3 | — | — | — | |
| SOTA2024.06 | 31.3 | — | — | — | |
| HowToCaptionVision Encoder=S3D, Input Modality=Text-video+audio, Evaluation Protocol=Zero-shot2023.10 | 25.5 | 51.1 | 63.6 | 5 | |
| EAOVision Encoder=S3D, Input Modality=Text-video+audio, Evaluation Protocol=Zero-shot2023.10 | 24.6 | 48.3 | 60.4 | 6 | |
| TANVision Encoder=S3D, Input Modality=Text-video only, Evaluation Protocol=Zero-shot2023.10 | 20.1 | 45.5 | 59.5 | 7 | |
| AVLNetVision Encoder=ResNet-152+ResNeXt101, Input Modality=Text-video+audio, Evaluation Protocol=Zero-shot2023.10 | 19.9 | 36.1 | 44.3 | 16 | |
| MCNVision Encoder=ResNet-152+ResNeXt101, Input Modality=Text-video+audio, Evaluation Protocol=Zero-shot2023.10 | 18.1 | 35.5 | 45.2 | — | |
| MIL-NCEVision Encoder=S3D, Input Modality=Text-video only, Evaluation Protocol=Zero-shot2023.10 | 15.1 | 38 | 51.2 | 10 |