Text-to-Video Retrieval on ActivityNet Captions (val1)
48.9R@1SINGULARITY-temporal
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| SINGULARITY-temporal#PT=17M, #Train Frame=42022.06 | 48.9 | 77 | 86.3 | — | — | — | — | |
| DiffusionRetQB-Norm=true2023.03 | 48.1 | 75.6 | 85.7 | 2 | — | 6.8 | 209.4 | |
| SINGULARITY#PT=17M, #Train Frame=12022.06 | 47.1 | 75.5 | 85.5 | — | — | — | — | |
| NeighborRetr2025.03 | 46 | 75.9 | 86.5 | 2 | — | 6.1 | — | |
| SINGULARITY-temporal#PT=5M, #Train Frame=42022.06 | 45.9 | 73.3 | 83.8 | — | — | — | — | |
| DiffusionRet2023.03 | 45.8 | 75.6 | 86.3 | 2 | — | 6.5 | 207.7 | |
| SINGULARITY#PT=5M, #Train Frame=12022.06 | 43 | 70.6 | 81.3 | — | — | — | — | |
| HBI2023.03 | 42.2 | 73 | 84.6 | 2 | — | 6.6 | — | |
| HBI2023.03 | 42.2 | 73 | 84.6 | 2 | — | 6.6 | 199.8 | |
| HBI2025.03 | 42.2 | 73 | 84.6 | 2 | — | 6.6 | — | |
| DICOSA2023.03 | 42.1 | 73.6 | 84.6 | 2 | — | 6.8 | 200.3 | |
| DiCoSA2025.03 | 42.1 | 73.6 | 84.6 | 2 | — | 6.8 | — | |
| MPT2025.03 | 41.4 | 70.9 | 82.9 | — | — | 7.8 | — | |
| EMCL-Net2023.03 | 41.2 | 72.7 | — | 2 | — | — | — | |
| EMCL-Net2023.03 | 41.2 | 72.7 | 83.6 | 2 | — | 8.6 | 197.5 | |
| TS2-Net2023.03 | 41 | 73.6 | 84.5 | 2 | — | 8.4 | — | |
| TS2-Net2023.03 | 41 | 73.6 | 84.5 | 2 | — | 8.4 | 199.1 | |
| TS2-Net2025.03 | 41 | 73.6 | 84.5 | 2 | — | 8.4 | — | |
| CLIP4Clip#PT=400M, #Train Frame=12/64/642022.06 | 40.5 | 72.4 | 98.2 | — | — | — | — | |
| CLIP4Clip2023.03 | 40.5 | 72.4 | 83.6 | 2 | — | 7.5 | — | |
| CLIP4Clip2023.03 | 40.5 | 72.4 | 83.6 | 2 | — | 7.5 | 196.5 | |
| CLIP4Clip2025.03 | 40.5 | 72.4 | 83.6 | 2 | — | 7.5 | — | |
| SupportSetE2E=false, VT=false, PT=HowTo2021.04 | 29.2 | 61.6 | — | 3 | — | — | — | |
| Support Set2021.11 | 29.2 | 61.6 | — | 3 | 94.7 | — | — | |
| Support-Set2023.03 | 29.2 | 61.6 | — | 3 | — | — | — | |
| Frozen in TimeE2E=true, VT=true, PT=CC,WebVid-2M2021.04 | 28.8 | 60.9 | — | 3 | — | — | — | |
| MMTE2E=false, VT=false, PT=HowTo2021.04 | 28.7 | 61.4 | — | 3 | — | — | — | |
| MMT#PT=136M, #Train Frame=1K/-/3K2022.06 | 28.7 | 61.4 | 94.5 | — | — | — | — | |
| MMT2021.11 | 28.7 | 61.4 | — | 3.3 | 94.5 | — | — | |
| MMT2023.03 | 28.7 | 61.4 | — | 3.3 | — | 16 | — | |
| HD-VILA2021.11 | 28.5 | 57.4 | — | 4 | 94 | — | — | |
| SupportSetE2E=false, VT=false2021.04 | 26.8 | 58.1 | — | 3 | — | — | — | |
| T2VLAD2023.03 | 23.7 | 55.5 | — | 4 | — | — | — | |
| MMTE2E=true, VT=false2021.04 | 22.7 | 54.2 | — | 5 | — | — | — | |
| All-in-one-BFrames=3 x 32022.03 | 22.4 | 53.7 | 67.7 | 5 | — | — | — | |
| All-in-one-BFrames=32022.03 | 21.5 | 50.3 | 65.5 | 6 | — | — | — | |
| CLIPBERTE2E=true, VT=false2021.04 | 21.3 | 49 | — | 6 | — | — | — | |
| ClipBERT#PT=0.2M, #Train Frame=16/16/82022.06 | 21.3 | 49 | 63.5 | — | — | — | — | |
| ClipBERT2021.11 | 21.3 | 49 | — | 6 | — | — | — | |
| ClipBERT2023.03 | 21.3 | 49 | 63.5 | 6 | — | — | — | |
| ClipBERT2023.03 | 21.3 | 49 | 63.5 | 6 | — | — | 133.8 | |
| ClipBERTFrames=4 x 22022.03 | 20.9 | 48.6 | 62.8 | 6 | — | — | — | |
| HSEFrames=82022.03 | 20.5 | 49.3 | — | — | — | — | — | |
| HSE2021.11 | 20.5 | 49.3 | — | — | — | — | — | |
| FSEFrames=162022.03 | 18.2 | 44.8 | — | 7 | — | — | — | |
| FSEE2E=false, VT=false2021.04 | 18.2 | 44.8 | — | 8.3 | — | — | — | |
| CEE2E=false, VT=false2021.04 | 18.2 | 47.7 | — | 13 | — | — | — | |
| FSE2021.11 | 18.2 | 44.8 | — | 7 | 89.1 | — | — | |
| CE2021.11 | 18.2 | 47.7 | — | 6 | 91.4 | — | — | |
| DenseFrames=322022.03 | 14 | 32 | — | 34 | — | — | — | |
| MMTPre-trained (PT)=true2021.02 | 0.287 | 0.614 | 0.945 | 3.3 | — | — | — | |
| MMTPre-trained (PT)=false2021.02 | 0.227 | 0.542 | 0.932 | 5 | — | — | — | |
| CLIPBERTInput sampling (N_train x T)=4x2, Clip duration=2s, Number of test clips (N_test)=202021.02 | 0.213 | 0.49 | 0.635 | 6 | — | — | — | |
| CLIPBERTInput sampling (N_train x T)=4x2, Clip duration=2s, Number of test clips (N_test)=162021.02 | 0.209 | 0.486 | 0.628 | 6 | — | — | — | |
| HSE2021.02 | 0.205 | 0.493 | — | — | — | — | — | |
| CE2021.02 | 0.182 | 0.477 | — | 6 | — | — | — | |
| FSE2021.02 | 0.182 | 0.448 | — | 7 | — | — | — | |
| Dense2021.02 | 0.14 | 0.32 | — | 34 | — | — | — |