| temporal-relation-extraction-on-vinoground | LanguageBind | #15 | Text Score: 10.6Video Score: 5Group Score: 1.2 |
| zero-shot-action-recognition-on-kinetics | LanguageBind | #8 | Top-1 Accuracy: 64.1Top-5 Accuracy: 85.7 |
| zero-shot-video-retrieval-on-activitynet | LanguageBind(ViT-H/14) | #6 | text-to-video R@1: 41.0text-to-video R@5: 68.4… |
| zero-shot-video-retrieval-on-activitynet | LanguageBind(ViT-L/14) | #7 | text-to-video R@1: 38.4text-to-video R@5: 66.6… |
| zero-shot-video-retrieval-on-didemo | LanguageBind(ViT-H/14) | #8 | text-to-video R@1: 39.9text-to-video R@5: 66.1… |
| zero-shot-video-retrieval-on-didemo | LanguageBind(ViT-L/14) | #9 | text-to-video R@1: 39.7text-to-video R@5: 65.5… |
| zero-shot-video-retrieval-on-msr-vtt | LanguageBind(ViT-H/14) | #9 | text-to-video R@1: 44.8text-to-video R@5: 70.0… |
| zero-shot-video-retrieval-on-msr-vtt | LanguageBind(ViT-L/14) | #10 | text-to-video R@1: 42.8text-to-video R@5: 67.5… |
| zero-shot-video-retrieval-on-msvd | LanguageBind(ViT-L/14) | #4 | text-to-video R@1: 54.1text-to-video R@5: 81.1… |
| zero-shot-video-retrieval-on-msvd | LanguageBind(ViT-H/14) | #5 | text-to-video R@1: 53.9text-to-video R@5: 80.4… |