Skeleton Based Action Recognition On N Ucla
평가 지표
Accuracy
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | Accuracy |
|---|---|
| semantics-guided-neural-networks-for | 92.5% |
| hierarchically-decomposed-graph-convolutional | 97.2 |
| infogcn-representation-learning-for-human | 97.0 |
| mmnet-a-model-based-multimodal-network-for | 93.7 |
| vpn-learning-video-pose-embedding-for | 93.5 |
| skateformer-skeletal-temporal-transformer-for | 98.3 |
| vpn-rethinking-video-pose-embeddings-for | 93.5 |
| language-knowledge-assisted-representation | 97.6 |
| skeleton-based-action-recognition-via | 97.0 |
| action-recognition-for-privacy-preserving | 95.69 |
| action-capsules-human-skeleton-action | 97.3 |
| multi-scale-spatial-temporal-convolutional | 95.3 |
| view-adaptive-neural-networks-for-high | 88.1% |
| hierarchical-action-classification-with | 93.99 |
| channel-wise-topology-refinement-graph | 96.5 |
| temporal-decoupling-graph-convolutional | 97.4 |
| action-machine-rethinking-action-recognition | 92.3% |
| glimpse-clouds-human-activity-recognition | 87.6% |
| multi-modality-co-learning-for-efficient-1 | 97.5 |
| language-supervised-training-for-skeleton | 97.2 |
| eleatt-rnn-adding-attentiveness-to-neurons-in | 90.7% |
| a-dense-sparse-complementary-network-for | 99.1 |