Text-to-Video Retrieval on DiDeMo (zero-shot)
57R@1InternVideo2-1B
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| InternVideo2-1BSetting=ZS2026.05 | 57 | — | — | |
| Gemini Embedding 2Setting=ZS2026.05 | 55.6 | — | — | |
| InternVideo2-1BSetting=ZS2026.05 | 54.3 | — | — | |
| Gemini Embedding 2Setting=ZS2026.05 | 53.3 | — | — | |
| UMT-L#Pairs=25M, Zero-shot=true2023.03 | 48.6 | — | — | |
| X-CLIPSetting=FT2026.05 | 47.8 | — | — | |
| X-CLIPSetting=FT2026.05 | 47.8 | — | — | |
| UMT-L#Pairs=17M, Zero-shot=true2023.03 | 46.4 | — | — | |
| OmniRetriever-7BSetting=ZS2026.05 | 46 | — | — | |
| OmniRetriever-7BSetting=ZS2026.05 | 45.1 | — | — | |
| CLIP4ClipSetting=FT2026.05 | 43.4 | — | — | |
| CLIP4ClipSetting=FT2026.05 | 42.5 | — | — | |
| UMT-B#Pairs=17M, Zero-shot=true2023.03 | 41.9 | — | — | |
| Omni-Embed-NemotronSetting=ZS2026.05 | 41.9 | — | — | |
| UMT-B#Pairs=25M, Zero-shot=true2023.03 | 41.2 | — | — | |
| LanguageBind (CLIP-H/14)Setting=ZS2026.05 | 39.9 | — | — | |
| LanguageBind (CLIP-H/14)Setting=ZS2026.05 | 39.8 | — | — | |
| Singularity#Pairs=17M, Zero-shot=true2023.03 | 37.1 | — | — | |
| SingularityPretraining Scale=17M, Backbone=Non-CLIP, Zero-shot=true2023.09 | 37.1 | 61.7 | 69.9 | |
| VINDLU#Pairs=25M, Zero-shot=true2023.03 | 36.9 | — | — | |
| Omni-Embed-NemotronSetting=ZS2026.05 | 36.5 | — | — | |
| HiTeAPretraining Scale=5M, Backbone=Non-CLIP, Zero-shot=true2023.09 | 36.1 | 60.1 | 70.3 | |
| BT-AdapterPretraining Scale=2M, Backbone=CLIP-L/14, Zero-shot=true2023.09 | 35.6 | 61.9 | 72.6 | |
| TVTSv2Pretraining Scale=8.5M, Backbone=CLIP-L/14, Zero-shot=true2023.09 | 34.6 | 61.9 | 71.5 | |
| UMT-L#Pairs=5M, Zero-shot=true2023.03 | 34 | — | — | |
| UMT-LPretraining Scale=5M, Backbone=CLIP-L/14, Zero-shot=true2023.09 | 34 | 60.4 | 68.7 | |
| UMT-B#Pairs=5M, Zero-shot=true2023.03 | 33.4 | — | — | |
| OmniVL#Pairs=17M, Zero-shot=true2023.03 | 33.3 | — | — | |
| OmniVLPretraining Scale=14M, Backbone=Non-CLIP, Zero-shot=true2023.09 | 33.3 | 58.7 | 68.5 | |
| InternVideo#Pairs=646M, Zero-shot=true2023.03 | 31.5 | — | — | |
| InternVideoPretraining Scale=12.8M, Backbone=CLIP-L/14, Zero-shot=true2023.09 | 31.5 | — | — | |
| CLIPBackbone=CLIP-L/14, Zero-shot=true2023.09 | 30.3 | 54.9 | 65.4 | |
| CloverPretraining Scale=5M, Backbone=Non-CLIP, Zero-shot=true2023.09 | 29.5 | 55.2 | 66.3 | |
| VIOLET#Pairs=138M, Zero-shot=true2023.03 | 23.5 | — | — | |
| FrozenPretraining Scale=5M, Backbone=Non-CLIP, Zero-shot=true2023.09 | 21.1 | 46 | 56.2 | |
| Frozen#Pairs=5M, Zero-shot=true2023.03 | 20.2 | — | — |