Action Recognition In Videos On Ntu Rgbd
Metrics
Accuracy (CS)
Accuracy (CV)
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Accuracy (CS) | Accuracy (CV) |
|---|---|---|
| mmnet-a-model-based-multimodal-network-for | 96.0 | 98.8 |
| infrared-and-3d-skeleton-feature-fusion-for | 91.8 | 94.9 |
| vpn-learning-video-pose-embedding-for | 95.5 | 98.0 |
| star-transformer-a-spatio-temporal-cross-1 | 92.0 | 96.5 |
| revisiting-skeleton-based-action-recognition | 97.0 | 99.6 |
| multi-view-action-recognition-using | 93.7 | 98.9 |
| dvanet-disentangling-view-and-action-features | 93.4 | 98.1 |
| cross-modal-learning-with-3d-deformable | 94.3 | 97.9 |
| recognizing-human-actions-as-the-evolution-of | 91.7 | 95.2 |
| part-based-graph-convolutional-network-for | 87.5 | 93.2 |
| deep-multimodal-feature-analysis-for-action | 74.9 | - |
| a-unified-multimodal-de-and-re-coupling | 96.2 | 98.0 |
| a-dense-sparse-complementary-network-for | 97.4 | 99.4 |
| multimodal-fusion-via-teacher-student-network | 92.5 | 97.4 |
| just-add-p-pose-induced-video-transformers | 96.3 | 99.0 |
| glimpse-clouds-human-activity-recognition | 86.6 | 93.2 |
| mmtm-multimodal-transfer-module-for-cnn | 91.99 | - |
| b2c-afm-bi-directional-co-temporal-and-cross | 91.7 | - |
| explore-human-parsing-modality-for-action-1 | 94.7 | 97.7 |
| hierarchical-action-classification-with | 95.66 | 98.79 |
| msaf-multimodal-split-attention-fusion | 92.24 | - |
| integrating-human-parsing-and-pose-network | 93.8 | 97.1 |
| just-add-p-pose-induced-video-transformers | 94.0 | 97.9 |
| skelemotion-a-new-representation-of-skeleton | 76.5 | 84.7 |
| action-machine-rethinking-action-recognition | 94.3 | 97.2 |