Action Classification On Charades
평가 지표
MAP
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | MAP |
|---|---|
| assemblenet-assembling-modality | 59.8 |
| slowfast-networks-for-video-recognition | 45.2 |
| tokenlearner-what-can-8-learned-tokens-do-for | 66.3 |
| asynchronous-temporal-fields-for-action | 22.4 |
| pose-and-joint-aware-action-recognition | 16.2 |
| potion-pose-motion-representation-for-action | 40.8 |
| victr-video-conditioned-text-representations | 57.6 |
| revisiting-spatio-temporal-layouts-for | 38.5 |
| long-term-feature-banks-for-detailed-video | 42.5 |
| adafocus-towards-end-to-end-weakly-supervised | 41.4 |
| bidirectional-cross-modal-knowledge | 50.7 |
| hallucinating-statistical-moment-and-subspace | 50.16 |
| movinets-mobile-video-networks-for-efficient | 32.5 |
| actionclip-a-new-paradigm-for-video-action | 44.3 |
| multiscale-vision-transformers | 44.3 |
| pose-and-joint-aware-action-recognition | 43.23 |
| rethinking-video-vits-sparse-video-tubes-for | 66.2 |
| multiscale-vision-transformers | 47.7 |
| hallucinating-bag-of-words-and-fisher-vector | 43.1 |
| quo-vadis-action-recognition-a-new-model-and | 32.9 |
| videos-as-space-time-region-graphs | 39.7 |
| compressed-video-action-recognition | 21.9 |
| adafocus-towards-end-to-end-weakly-supervised | 47.8 |
| adafocus-towards-end-to-end-weakly-supervised | 39.3 |
| pa3d-pose-action-3d-machine-for-video | 41 |
| movinets-mobile-video-networks-for-efficient | 63.2 |
| vidtr-video-transformer-without-convolutions | 43.5 |
| evolving-space-time-neural-architectures-for | 38.1 |
| adafocus-towards-end-to-end-weakly-supervised | 41.2 |
| multiscale-vision-transformers | 47.1 |
| continual-3d-convolutional-neural-networks | 25.2 |
| vidtr-video-transformer-without-convolutions | 47.3 |
| assemblenet-searching-for-multi-stream-neural | 58.6 |
| multiscale-vision-transformers | 43.9 |
| assemblenet-assembling-modality | 54.98 |
| continual-3d-convolutional-neural-networks | 21.5 |
| timeception-for-complex-action-recognition | 37.2 |
| slowfast-networks-for-video-recognition | 42.1 |
| slowfast-networks-for-video-recognition | 42.5 |
| temporal-relational-reasoning-in-videos | 25.2 |
| timeception-for-complex-action-recognition | 31.6 |
| timeception-for-complex-action-recognition | 41.1 |
| hallucinating-statistical-moment-and-subspace | 62.29 |
| assemblenet-searching-for-multi-stream-neural | 58.6 |
| multiscale-vision-transformers | 46.3 |
| two-stream-convolutional-networks-for-action | 18.6 |
| movinets-mobile-video-networks-for-efficient | 48.5 |
| continual-3d-convolutional-neural-networks | 24.1 |
| multiscale-vision-transformers | 40 |