Text-to-Video Retrieval on VATEX (standard)
83Recall@1VAST
Evaluation results
| Method | Links | |
|---|---|---|
| VASTmodality track=Multi-modal2023.05 | 83 | |
| Method [7]modality track=Multi-modal2023.05 | 76.9 | |
| InternVideoBackbone=ViT-L/142022.12 | 71.1 | |
| Method [57]modality track=Vision-only2023.05 | 71.1 | |
| CLIP4Clip2022.12 | 63 | |
| TS2Net2022.12 | 59.1 |