Action Recognition In Videos On Ntu Rgbd 120
Metrics
Accuracy (Cross-Setup)
Accuracy (Cross-Subject)
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Accuracy (Cross-Setup) | Accuracy (Cross-Subject) |
|---|---|---|
| a-dense-sparse-complementary-network-for | 96.7 | 95.6 |
| recognizing-human-actions-as-the-evolution-of | 64.6 | 66.9 |
| cross-modal-learning-with-3d-deformable | 91.4 | 90.5 |
| gimme-signals-discriminative-signal-encoding | 70.8 | 71.59 |
| skelemotion-a-new-representation-of-skeleton | 66.9 | 67.7 |
| just-add-p-pose-induced-video-transformers | 91.9 | 92.9 |
| vpn-rethinking-video-pose-embeddings-for | 90.7 | 92.5 |
| just-add-p-pose-induced-video-transformers | 96.1 | 95.1 |
| dvanet-disentangling-view-and-action-features | 90.4 | 91.6 |
| skeleton-image-representation-for-3d-action | 67.9 | 62.8 |
| vertex-feature-encoding-and-hierarchical | 78.3 | 79.2 |
| vpn-learning-video-pose-embedding-for | 86.3 | 87.8 |
| explore-human-parsing-modality-for-action-1 | 92.8 | 91.1 |
| multi-view-action-recognition-using | 87.5 | 85.6 |
| integrating-human-parsing-and-pose-network | 91.7 | 90.0 |
| star-transformer-a-spatio-temporal-cross-1 | 92.7 | 90.3 |
| mmnet-a-model-based-multimodal-network-for | 94.4 | 92.9 |
| revisiting-skeleton-based-action-recognition | 96.4 | 95.3 |