Video-to-Text Retrieval on MSR-VTT (Full)
64.7Recall@1VideoCoCa
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| VideoCoCaZero-shot=true2022.12 | 64.7 | 85.2 | 91.4 | — | — | |
| VideoCoCaZero-shot=true, w.o. videos=true2022.12 | 59.7 | 81.8 | 89.3 | — | — | |
| CLIP2VideoCategory=Finetuned, Audio=no2022.04 | 54.6 | 82.1 | 90.8 | 1 | — | |
| CLIP2VideoTest-set=Full2021.06 | 54.6 | 82.1 | 90.8 | 1 | 5.3 | |
| CoCaZero-shot=true2022.12 | 49.9 | 73.4 | 81.4 | — | — | |
| UCOFIAType=CLIP-based2023.09 | 47.1 | 74.3 | — | — | — | |
| Socratic ModelsZero-shot=true2022.12 | 46.9 | 73.5 | 81.3 | — | — | |
| X-CLIPType=CLIP-based2023.09 | 46.8 | 73.3 | — | — | — | |
| TS2-NetType=CLIP-based2023.09 | 45.3 | 74.1 | — | — | — | |
| SMsCategory=Zero-shot, Audio=yes2022.04 | 44.7 | 71.2 | 80 | 2 | — | |
| CLIPZero-shot=true2022.12 | 43.3 | 73.3 | 81.8 | — | — | |
| CLIP4ClipType=CLIP-based2023.09 | 42.7 | 70.9 | — | — | — | |
| CLIPTraining=WIT2021.02 | 40.3 | 69.7 | 79.2 | 2 | — | |
| CLIP via [67]Category=Zero-shot, Audio=no2022.04 | 40.3 | 69.7 | 79.2 | 2 | — | |
| CLIPTest-set=Full2021.06 | 40.3 | 69.7 | 79.2 | 2 | — | |
| VideoMatch2021.10 | 37.8 | 72 | — | 2 | — | |
| HSE2021.10 | 32.5 | 63.7 | — | 3 | — | |
| HiTType=Non-CLIP2023.09 | 32.1 | 62.7 | — | — | — | |
| TT-CEType=Non-CLIP2023.09 | 32.1 | 62.7 | — | — | — | |
| MMTType=Non-CLIP2023.09 | 27 | 57.5 | — | — | — | |
| Support setType=Non-CLIP2023.09 | 26.6 | 55.1 | — | — | — | |
| CEType=Non-CLIP2023.09 | 20.6 | 50.3 | — | — | — | |
| CETest-set=Full2019.07 | 15.6 | 40.9 | 55.2 | 8.3 | 38.1 | |
| CETraining=MSR-VTT2021.02 | 15.6 | 40.9 | 55.2 | 8.3 | — | |
| Collab. ExpertsCategory=Finetuned, Audio=yes2022.04 | 15.6 | 40.9 | 55.2 | 8.3 | — | |
| CETest-set=Full2021.06 | 15.6 | 40.9 | 55.2 | 8.3 | 38.1 | |
| Dual Enc.Test-set=Full2019.07 | 13 | 30.8 | 43.3 | 15 | — | |
| Dual Enc.Training=MSR-VTT2021.02 | 13 | 30.8 | 43.3 | 15 | — | |
| Dual Enc.Test-set=Full2021.06 | 13 | 30.8 | 43.3 | 15 | — | |
| Mithun et al.Test-set=Full2019.07 | 12.5 | 32.1 | 42.4 | 16 | 134 | |
| Multi CuesTraining=MSR-VTT2021.02 | 12.5 | 32.1 | 42.4 | 16 | — | |
| JEMCCategory=Finetuned, Audio=yes2022.04 | 12.5 | 32.1 | 42.4 | 16 | — | |
| W2VVTest-set=Full2019.07 | 11.8 | 28.9 | 39.1 | 21 | — | |
| W2VVTraining=MSR-VTT2021.02 | 11.8 | 28.9 | 39.1 | 21 | — | |
| VSE++Test-set=Full2019.07 | 10.2 | 25.4 | 35.1 | 25 | 228.1 | |
| VSE++Training=MSR-VTT2021.02 | 10.2 | 25.4 | 35.1 | 25 | — | |
| VSETest-set=Full2019.07 | 7.7 | 20.3 | 31.2 | 28 | 185.8 | |
| VSETraining=MSR-VTT2021.02 | 7.7 | 20.3 | 31.2 | 28 | — |