Text-to-Video Retrieval on MSRVTT 1K-A (test)
54.2R@1CLIP-ViP
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| CLIP-ViP#Data=500M, #Frames=1-12, Time=984*2022.12 | 54.2 | 77.2 | 84.8 | 72.1 | — | |
| VINDLU-L#Data=25M, #Frames=4, Time=1782022.12 | 48.8 | 72.4 | 82.2 | 67.8 | — | |
| OmniVL#Data=17M, #Frames=1-8, Time=169*2022.12 | 47.8 | 74.2 | 83.8 | 68.6 | — | |
| CLIP-Hhiker#Data=400M, #Frames=1, Time=768*2022.12 | 47.7 | 74.1 | 82.9 | 68.6 | — | |
| HBI2023.03 | 46.8 | 74.3 | 84.3 | 8.9 | 2 | |
| VINDLU#Data=25M, #Frames=4, Time=822022.12 | 46.5 | 71.5 | 80.4 | 66.1 | — | |
| ECLIPSE#Data=400M, #Frames=1, Time=768*2022.12 | 45.3 | 75.7 | 86.2 | 69.1 | — | |
| VINDLU#Data=17M, #Frames=4, Time=382022.12 | 45.3 | 69.9 | 79.6 | 64.9 | — | |
| TS2-Net2023.03 | 45.3 | 74.1 | 83.7 | 9.2 | 2 | |
| CLIP4Clip#Data=400M, #Frames=1, Time=768*2022.12 | 44.5 | 71.4 | 81.6 | 65.8 | — | |
| X-Pool2023.03 | 44.4 | 73.3 | 84 | 9 | 2 | |
| VINDLU#Data=5M, #Frames=4, Time=152022.12 | 43.8 | 70.3 | 79.5 | 64.5 | — | |
| Singularity#Data=17M, #Frames=1-4, Time=292022.12 | 42.7 | 69.5 | 78.1 | 63.4 | — | |
| CLIP4Clip2023.03 | 42.7 | 70.9 | 80.6 | 11.6 | 2 | |
| LAVENDER#Data=30M, #Frames=4, Time=6402022.12 | 40.7 | 66.9 | 77.6 | 61.7 | — | |
| All-in-one#Data=138M, #Frames=3, Time=4482022.12 | 37.9 | 68.1 | 77.1 | 61 | — | |
| VIOLET#Data=138M, #Frames=4, Time=832022.12 | 34.5 | 63 | 73.4 | 57 | — | |
| ALPRO#Data=5M, #Frames=8, Time=24*2022.12 | 33.9 | 60.7 | 73.2 | 55.9 | — | |
| HiT2023.03 | 32.1 | 62.7 | 74.1 | — | 3 | |
| T2VLAD2023.03 | 31.8 | 60 | 71.1 | — | 3 | |
| Frozen#Data=5M, #Frames=1-4, Time=35*2022.12 | 31 | 59.5 | 70.5 | 53.7 | — | |
| VideoCLIP#Data=136M, #Frames=960, Time=82022.12 | 30.9 | 55.4 | 66.8 | 51 | — | |
| ClipBERT#Data=5.4M, #Frames=1, Time=322022.12 | 22 | 46.8 | 59.9 | 42.9 | — |