Text-to-Video Retrieval on ActivityNet (val1)
44.4R@1EERCF
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| EERCF2024.01 | 44.4 | 74.6 | 85.1 | — | — | 68 | |
| X-CLIP2024.01 | 44.2 | 74.5 | 86.1 | — | — | 68.3 | |
| Query-scoringmode=q-score2022.05 | 44 | 74.9 | 86.1 | 2 | 5.8 | — | |
| CenterCLIP2024.01 | 43.5 | 75.1 | 85.4 | — | — | 68 | |
| DRL2024.01 | 43.1 | 74.5 | 86 | — | — | 67.9 | |
| Clip4clipaggregation=mean2022.05 | 40.5 | 72.4 | — | 2 | 7.4 | — | |
| Clip4clipaggregation=seqTransf2022.05 | 40.5 | 72.4 | — | 2 | 7.5 | — | |
| CLIP4Clip2024.01 | 39.7 | 71 | 83.4 | — | — | 64.7 | |
| TS2Net2024.01 | 37.3 | 69.9 | 83.2 | — | — | 63.5 | |
| Frozen2022.05 | 28.8 | — | 60.9 | 3 | — | — | |
| TeachText2022.05 | 25 | 58.7 | — | 4 | — | — | |
| TeachText2024.01 | 23.5 | 57.2 | 96.1 | — | — | 58.9 | |
| CenterCLIPBackbone=ViT-B/16, Token Clustering Strategy=k-medoids++, Clustering Settings (Ba - S, K)=15, 160, MeM. (GB)=23, Speed (ms)=4192022.05 | 0.462 | 0.77 | 0.876 | 2 | 5.7 | — | |
| CenterCLIPBackbone=ViT-B/32, Token Clustering Strategy=k-medoids++, Clustering Settings (Ba - S, K)=15, 49, MeM. (GB)=16.8, Speed (ms)=71.32022.05 | 0.439 | 0.753 | 0.852 | 2 | 7 | — | |
| CenterCLIPBackbone=ViT-B/32, Token Clustering Strategy=spectral, Clustering Settings (Ba - S, K)=15, 49, MeM. (GB)=16.8, Speed (ms)=1742022.05 | 0.439 | 0.746 | 0.858 | 2 | 6.7 | — | |
| CenterCLIPBackbone=ViT-B/32, Token Clustering Strategy=k-medoids++, Clustering Settings (Ba - S, K)=12, 49, MeM. (GB)=16.2, Speed (ms)=70.42022.05 | 0.435 | 0.75 | 0.859 | 2 | 6.9 | — | |
| CenterCLIPBackbone=ViT-B/32, Token Clustering Strategy=spectral, Clustering Settings (Ba - S, K)=20, 49, MeM. (GB)=17.7, Speed (ms)=1622022.05 | 0.435 | 0.751 | 0.854 | 2 | 6.9 | — | |
| CLIP4clip (meanP) baselineBackbone=ViT-B/32, MeM. (GB)=25, Speed (ms)=822022.05 | 0.418 | 0.739 | 0.847 | 2 | 7.3 | — | |
| CLIP4clip (meanP)MeM. (GB)=25, Speed (ms)=822022.05 | 0.405 | 0.724 | — | 2 | 7.4 | — | |
| CLIP4clip (seqTransf)2022.05 | 0.405 | 0.724 | — | 2 | 7.5 | — | |
| SSB2022.05 | 0.292 | 0.616 | — | 3 | — | — | |
| MMT2022.05 | 0.287 | 0.614 | — | 3.3 | 16 | — | |
| CMGSD2022.05 | 0.242 | 0.563 | — | 4 | — | — | |
| T2VLAD2022.05 | 0.237 | 0.555 | — | 4 | — | — | |
| TT-CE+2022.05 | 0.235 | 0.572 | — | 4 | — | — | |
| CLIPzero-shot=true2022.05 | 0.217 | 0.46 | 0.596 | 7 | 39.7 | — | |
| FSE2022.05 | 0.182 | 0.448 | — | 7 | — | — | |
| CE2022.05 | 0.182 | 0.477 | — | 6 | 12.1 | — |