| A Dense-Sparse Complementary Network for Human Action Recognition based on RGB and Skeleton Modalities | ✓ Link | 99.1 | | DSCNet (RGB + Pose) | 2023-12-28 |
| SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition | ✓ Link | 98.3 | | SkateFormer | 2024-03-14 |
| Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition | ✓ Link | 97.6 | | LA-GCN | 2023-05-21 |
| Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition | ✓ Link | 97.5 | | MMCL | 2024-07-22 |
| Temporal Decoupling Graph Convolutional Network for Skeleton-based Gesture Recognition | ✓ Link | 97.4 | | TD-GCN | 2023-05-01 |
| Action Capsules: Human Skeleton Action Recognition | | 97.3 | | Action Capsules | 2023-01-30 |
| Generative Action Description Prompts for Skeleton-based Action Recognition | ✓ Link | 97.2 | | LST | 2022-08-10 |
| Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition | ✓ Link | 97.2 | | HD-GCN | 2022-08-23 |
| InfoGCN: Representation Learning for Human Skeleton-Based Action Recognition | ✓ Link | 97.0 | | InfoGCN | 2022-01-01 |
| Skeleton-based Action Recognition via Temporal-Channel Aggregation | ✓ Link | 97.0 | | TCA-GCN | 2022-05-31 |
| DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling | ✓ Link | 96.98 | | DSTSA-GCN | 2025-01-21 |
| Joint-Partition Group Attention for skeleton-based action recognition | ✓ Link | 96.7 | | JPFormer | 2024-07-30 |
| Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition | ✓ Link | 96.5 | | CTR-GCN | 2021-07-26 |
| Action Recognition in Real-World Ambient Assisted Living Environment | ✓ Link | 96.34% | Joint | RE-TCN | 2025-03-29 |
| Action Recognition for Privacy-Preserving Ambient Assisted Living | ✓ Link | 95.69 | Joint | TD-GDSCN | 2024-08-15 |
| Multi-scale spatial–temporal convolutional neural network for skeleton-based action recognition | ✓ Link | 95.3 | | MSSTNet | 2023-05-12 |
| Hierarchical Action Classification with Network Pruning | | 93.99 | | Hierarchical Action Classification (RGB + Pose) | 2020-07-30 |
| MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos | ✓ Link | 93.7 | | MMNet (RGB + Pose) | 2022-05-26 |
| VPN: Learning Video-Pose Embedding for Activities of Daily Living | ✓ Link | 93.5 | | VPN (RGB + Pose) | 2020-07-06 |
| VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living | ✓ Link | 93.5 | | VPN++ (RGB + Pose) | 2021-05-17 |
| Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition | ✓ Link | 92.5% | | SGN | 2019-04-02 |
| Action Machine: Rethinking Action Recognition in Trimmed Videos | | 92.3% | | Action Machine | 2018-12-14 |
| EleAtt-RNN: Adding Attentiveness to Neurons in Recurrent Neural Networks | | 90.7% | | EleAtt-GRU (aug.) | 2019-09-03 |
| View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition | ✓ Link | 88.1% | | VA-fusion (aug.) | 2018-04-20 |
| Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points | ✓ Link | 87.6% | | Glimpse Clouds | 2018-02-22 |