Action Classification On Moments In Time
Metrics
Top 1 Accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Top 1 Accuracy |
|---|---|
| movinets-mobile-video-networks-for-efficient | 39.1 |
| movinets-mobile-video-networks-for-efficient | 37.9 |
| unmasked-teacher-towards-training-efficient | 48.7 |
| quo-vadis-action-recognition-a-new-model-and | 29.51% |
| temporal-segment-networks-for-action | - |
| learn-to-cycle-time-consistent-feature | 28.55 |
| movinets-mobile-video-networks-for-efficient | 27.5 |
| uniformerv2-spatiotemporal-learning-by-arming | 47.8 |
| temporal-relational-reasoning-in-videos | 28.27 |
| learn-to-cycle-time-consistent-feature | 33.56 |
| assemblenet-searching-for-multi-stream-neural | 34.27% |
| learn-to-cycle-time-consistent-feature | 30.72 |
| co-training-transformer-with-videos-and | 46.1 |
| evolving-space-time-neural-architectures-for | 31.8% |
| internvideo2-scaling-video-foundation-models | 50.9 |
| co-training-transformer-with-videos-and | 45.0 |
| collaborative-spatiotemporal-feature-learning | 32.4% |
| omnivec2-a-novel-transformer-based-network | 53.1 |
| attention-bottlenecks-for-multimodal-fusion | 37.3 |
| 2103-15691 | - |
| learn-to-cycle-time-consistent-feature | 31.60 |
| video-transformer-network | 37.4 |
| movinets-mobile-video-networks-for-efficient | 34.3 |
| vatt-transformers-for-multimodal-self | 41.1 |
| learn-to-cycle-time-consistent-feature | 28.97 |
| multiview-transformers-for-video-recognition | 47.2 |
| movinets-mobile-video-networks-for-efficient | 40.2 |
| movinets-mobile-video-networks-for-efficient | 32.0 |
| movinets-mobile-video-networks-for-efficient | 35.6 |