Text-to-Video Retrieval on VALOR-32K
80Recall@1VAST
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| VASTModality=Audio/Subtitle2023.05 | 80 | 93.7 | 96.6 | |
| VASTmodality track=Multi-modal2023.05 | 80 | — | — | |
| VALOR-LModality=Audio/Subtitle2023.05 | 73.2 | 91.6 | 95.4 | |
| Method [7]modality track=Multi-modal2023.05 | 73.2 | — | — | |
| PEAV BA-Enc Params.=0.2B, Data (M)=124, Sampling=30 FPS2025.12 | 71.2 | — | — | |
| PEAV LA-Enc Params.=1.1B, Data (M)=124, Sampling=16 Frames2025.12 | 70.9 | — | — | |
| PEAV SA-Enc Params.=.09B, Data (M)=124, Sampling=30 FPS2025.12 | 70.9 | — | — | |
| PEAV LA-Enc Params.=1.1B, Data (M)=124, Sampling=30 FPS2025.12 | 70.9 | — | — | |
| PEAV L-OODA-Enc Params.=1.1B, Data (M)=114, Sampling=30 FPS, OOD=true2025.12 | 70.2 | — | — | |
| PEAV SA-Enc Params.=.09B, Data (M)=124, Sampling=16 Frames2025.12 | 70.1 | — | — | |
| PEAV BA-Enc Params.=.2B, Data (M)=124, Sampling=16 Frames2025.12 | 70 | — | — | |
| PEAV L (PT)A-Enc Params.=1.1B, Data (M)=92, Sampling=30 FPS, PT=true2025.12 | 57.1 | — | — | |
| LangBindA-Enc Params.=0.3B, Data (M)=102025.12 | 46.8 | — | — | |
| CLIP4ClipModality=Vision-only2023.05 | 43.4 | 69.9 | 79.7 | |
| Method [56]modality track=Vision-only2023.05 | 43.4 | — | — | |
| ImageBindA-Enc Params.=.09B, Data (M)=32025.12 | 36.1 | — | — | |
| FrozenModality=Vision-only2023.05 | 32.9 | 60.4 | 71.2 | |
| AVLNetModality=Audio/Subtitle2023.05 | 21.6 | 47.2 | 59.8 |