Action Recognition On Epic Kitchens 100
Metriken
Action@1
GFLOPs
Noun@1
Verb@1
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Action@1 | GFLOPs | Noun@1 | Verb@1 |
|---|---|---|---|---|
| movinets-mobile-video-networks-for-efficient | 44.5 | 74.9x1 | 55.1 | 69.1 |
| training-a-large-video-model-on-a-single | 54.4 | - | 65.4 | 73.0 |
| memvit-memory-augmented-multiscale-vision | 48.4 | - | 60.3 | 71.4 |
| rescaling-egocentric-vision | 36.81 | - | - | - |
| movinets-mobile-video-networks-for-efficient | 41.2 | 7.59x1 | 52.3 | 67.1 |
| rescaling-egocentric-vision | 33.57 | - | - | - |
| gate-shift-fuse-for-video-action-recognition | 44.48 | - | 53.18 | 69.06 |
| 2103-15691 | 44.0 | - | 56.8 | 66.4 |
| temporally-adaptive-models-for-efficient | 48.9 | - | 60.2 | 71.0 |
| object-region-video-transformers-1 | 45.7 | - | 58.7 | 68.4 |
| cast-cross-attention-in-space-and-time-for-1 | 49.3 | - | 60.9 | 72.5 |
| keeping-your-eye-on-the-ball-trajectory | 44.5 | - | 58.5 | 67.0 |
| technical-report-temporal-aggregate | 45.26 | - | 53.35 | 66 |
| learning-video-representations-from-large | 51 | - | 62.9 | 72 |
| multiscale-multimodal-transformer-for | 47.8 | - | 61.0 | 70.1 |
| attention-bottlenecks-for-multimodal-fusion | 43.4 | - | 58 | 64.8 |
| keeping-your-eye-on-the-ball-trajectory | 44.1 | - | 57.6 | 67.1 |
| keeping-your-eye-on-the-ball-trajectory | 43.1 | - | 56.5 | 66.7 |
| m-m-mix-a-multimodal-multiview-transformer | 53.6 | - | 66.3 | 72.0 |
| omnivore-a-single-model-for-many-visual | 49.9 | - | 61.7 | 69.5 |
| multiview-transformers-for-video-recognition | 50.5 | - | 63.9 | 69.9 |
| rescaling-egocentric-vision | 35.55 | - | - | - |
| rescaling-egocentric-vision | 35.28 | - | - | - |
| temporally-adaptive-models-for-efficient | 51.8 | - | 64.1 | 71.7 |
| rescaling-egocentric-vision | 37.39 | - | - | - |
| movinets-mobile-video-networks-for-efficient | 47.7 | 117x1 | 57.3 | 72.2 |
| avt-audio-video-transformer-for-multimodal | 47.2 | - | 59.3 | 70.4 |
| movinets-mobile-video-networks-for-efficient | 44.4 | 42.2x1 | 56.2 | 68.8 |
| movinets-mobile-video-networks-for-efficient | 36.8 | 1.74x1 | 47.4 | 64.8 |
| extending-video-masked-autoencoders-to-128-1 | 52.1 | - | 61.8 | 75.0 |