Text-to-Video Retrieval on ActivityNet-Captions (val)
55.9R@1VINDLU-L
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| VINDLU-L#Data=25M, #Frames=4, Time=1782022.12 | 55.9 | 82.3 | 90.9 | 76.4 | |
| VINDLU#Data=25M, #Frames=4, Time=822022.12 | 55 | 81.4 | 89.7 | 75.4 | |
| VINDLU#Data=17M, #Frames=4, Time=382022.12 | 54.4 | 80.7 | 89 | 74.7 | |
| CLIP-ViP#Data=500M, #Frames=1-12, Time=984*2022.12 | 53.4 | 81.4 | 90 | 74.9 | |
| VINDLU#Data=5M, #Frames=4, Time=152022.12 | 51.1 | 79.2 | 88.4 | 72.9 | |
| Singularity#Data=17M, #Frames=1-4, Time=292022.12 | 48.9 | 77 | 86.3 | 70.7 | |
| ECLIPSE#Data=400M, #Frames=1, Time=768*2022.12 | 45.3 | 75.7 | 86.2 | 69.1 | |
| CLIP-Hhiker#Data=400M, #Frames=1, Time=768*2022.12 | 44 | 74.9 | 86.1 | 68.3 | |
| CLIP4Clip#Data=400M, #Frames=1, Time=768*2022.12 | 40.5 | 72.4 | 83.4 | 65.4 | |
| All-in-one#Data=138M, #Frames=3, Time=4482022.12 | 22.4 | 53.7 | 67.7 | 47.9 | |
| ClipBERT#Data=5.4M, #Frames=1, Time=322022.12 | 21.3 | 49 | 63.5 | 44.6 |