Action Recognition on Kinetics-700 (val)
85.9Top-1 AccInternVideo2_s1-6B
Evaluation results
| Method | Links | ||
|---|---|---|---|
| InternVideo2_s1-6BTraining Data=IV-2M, Setting=16 x 224, Inference Mode=End-to-end finetuning2024.03 | 85.9 | — | |
| InternVideo2_s1-6BTraining Data=IV-2M, Setting=8 x 224, Inference Mode=End-to-end finetuning2024.03 | 85.7 | — | |
| InternVideo2_s1-1BTraining Data=IV-1.1M, Setting=16 x 224, Inference Mode=End-to-end finetuning2024.03 | 85.4 | — | |
| InternVideo2_s1-1BTraining Data=IV-1.1M, Setting=8 x 224, Inference Mode=End-to-end finetuning2024.03 | 85 | — | |
| InternVideoTraining Data=V-12M, Setting=ensemble, Inference Mode=End-to-end finetuning2024.03 | 84 | — | |
| MTV-HTraining Data=IV-370M, Setting=32 x 280, Inference Mode=End-to-end finetuning2024.03 | 83.4 | — | |
| CoCa-gTraining Data=I-3B, Setting=16 x 576, Inference Mode=End-to-end finetuning2024.03 | 82.7 | — | |
| UniFormerV2-LTraining Data=IV-401M, Setting=64 x 336, Inference Mode=End-to-end finetuning2024.03 | 82.7 | — | |
| Hiera-HTraining Data=V-0.25M, Setting=16 x 224, Inference Mode=End-to-end finetuning2024.03 | 81.1 | — | |
| CoVeRTraining Data=IV-3B, Setting=16 x 448, Inference Mode=End-to-end finetuning2024.03 | 79.8 | — | |
| SF r3d-101Backbone=r3d, Depth=1012020.06 | 57.326 | 77.194 | |
| SRTG r(2+1)d-101Backbone=r(2+1)d, Depth=1012020.06 | 56.826 | 77.439 | |
| SRTG r3d-101Backbone=r3d, Depth=1012020.06 | 56.462 | 76.819 | |
| SF r3d-50Backbone=r3d, Depth=502020.06 | 56.167 | 75.569 | |
| ir-CSN-101Backbone=ir-CSN, Depth=1012020.06 | 54.665 | 73.784 | |
| MF-Net2020.06 | 54.249 | 73.378 | |
| SRTG r(2+1)d-50Backbone=r(2+1)d, Depth=502020.06 | 54.174 | 74.62 | |
| TSM2020.06 | 54.032 | 72.216 | |
| SRTG r3d-50Backbone=r3d, Depth=502020.06 | 53.522 | 74.171 | |
| I3D2020.06 | 53.015 | 69.193 | |
| r3d-101Backbone=r3d, Depth=1012020.06 | 52.583 | 74.631 | |
| r(2+1)d-101Backbone=r(2+1)d, Depth=1012020.06 | 52.536 | 75.177 | |
| r(2+1)d-50Backbone=r(2+1)d, Depth=502020.06 | 49.927 | 73.396 | |
| SRTG r(2+1)d-34Backbone=r(2+1)d, Depth=342020.06 | 49.427 | 73.233 | |
| SRTG r3d-34Backbone=r3d, Depth=342020.06 | 49.153 | 72.682 | |
| r3d-50Backbone=r3d, Depth=502020.06 | 49.083 | 72.541 | |
| r(2+1)d-34Backbone=r(2+1)d, Depth=342020.06 | 46.625 | 68.229 | |
| r3d-34Backbone=r3d, Depth=342020.06 | 46.138 | 67.108 |