Skeleton-Based Action Recognition Using Graph Convolutional Network with Pose Correction and Channel Topology Refinement
Source abstract
Abstract
Graph convolutional network (GCN) as an essential tool in human action recognition tasks have achieved excellent performance in previous studies. However, most current skeleton-based action recognition using GCN methods use a... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Human Pose and Action Recognition · Anomaly Detection Techniques and Applications · Gait Recognition and Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (55)
Show source-provided references
1. Hierarchical recurrent neural network for skeleton based action recognition
2. Modeling video evolution for action recognition
3. Human action recognition by representing 3D skeletons as points in a lie group
4. Interpretable 3D human action analysis with temporal convolutional networks
5. Skeleton-based action recognition with convolutional neural networks
6. Liu H, Tu J, Liu M. Two-stream 3D convolutional neural network for skeleton-based action recognition. 2017. doi:10.48550/arXiv.1705.08106.
7. NTU RGB+D: a large scale dataset for 3D human activity analysis
8. View adaptive recurrent neural networks for high performance human action recognition from skeleton data
9. Relational network for skeleton-based action recognition
10. Spatial temporal graph convolutional networks for skeleton-based action recognition
11. An attention enhanced graph convolutional LSTM network for skeleton-based action recognition
12. Graph CNNs with motif and variable temporal block for skeleton-based action recognition
13. Two-stream adaptive graph convolutional networks for skeleton-based action recognition
14. Semantics-guided neural networks for efficient skeleton-based human action recognition
15. Dynamic GCN: context-enriched topology learning for skeleton-based action recognition
16. HaredNet: a deep learning based architecture for autonomous video surveillance by recognizing human actions10.1016/j.compeleceng.2022.107805 ↗
17. IMiGUE: an identity-free video dataset for micro-gesture understanding and emotion analysis
18. Kay W, Carreira J, Simonyan K, Zhang B, Hillier C, Vijayanarasimhan S, et al. The kinetics human action video dataset. 2017. doi:10.48550/arXiv.1705.06950.
19. Learning convolutional neural networks for graphs
20. Geometric deep learning on graphs and manifolds using mixture model CNNs
21. Inductive representation learning on large graphs
22. Bruna J, Zaremba W, Szlam A, LeCun Y. Spectral networks and locally connected networks on graphs. 2013. doi:10.48550/arXiv.1312.6203.
23. Convolutional networks on graphs for learning molecular fingerprints
24. Convolutional neural networks on graphs with fast localized spectral filtering
25. Kipf TN, Welling M. Semi-supervised classification with graph convolutional networks. 2016. doi:10.48550/arXiv.1609.02907.
26. Graph attention networks
27. Large-scale learnable graph convolutional networks
28. Multi-scale mixed dense graph convolution network for skeleton-based action recognition10.1109/ACCESS.2020.3049029 ↗
29. Bayesian graph convolution LSTM for skeleton based action recognition
30. Deep progressive reinforcement learning for skeleton-based action recognition
31. Skeleton-based action recognition with shift graph convolutional network
32. Pose refinement graph convolutional network for skeleton-based action recognition10.1109/LRA.2021.3056361 ↗
33. Channel-wise topology refinement graph convolution for skeleton-based action recognition
34. Decoupling GCN with dropgraph module for skeleton-based action recognition
35. Skeleton-based action recognition through contrasting two-stream spatial-temporal networks10.1109/TMM.2023.3239751 ↗
36. Hierarchically decomposed graph convolutional networks for skeleton-based action recognition
37. ICE-GCN: an interactional channel excitation-enhanced graph convolutional network for skeleton-based action recognition10.1007/s00138-023-01386-2 ↗
38. Skeleton-based human action recognition via large-kernel attention graph convolutional network10.1109/TVCG.2023.3247075 ↗
39. Realtime multi-person 2D pose estimation using part affinity fields
40. Bidirectional long short-term memory variational autoencoder
41. Learning graph convolutional network for skeleton-based human action recognition by neural searching
42. Disentangling and unifying graph convolutions for skeleton-based action recognition
43. Duan H, Wang J, Chen K, Lin D. DG-STGCN: dynamic spatial-temporal modeling for skeleton-based action recognition. 2022. doi:10.48550/arXiv.2210.05895.10.1109/CAC57257.2022.10055641 ↗
44. PYSKL: towards good practices for skeleton action recognition
45. Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and imagenet?
46. Quo vadis, action recognition? a new model and the kinetics dataset
47. Learning spatiotemporal features with 3D convolutional networks
48. Self-attention network for skeleton-based human action recognition
49. Actional-structural graph convolutional networks for skeleton-based action recognition
50. Topology-learnable graph convolution for skeleton-based action recognition10.1016/j.patrec.2020.05.005 ↗
51. An end-to-end spatio-temporal attention model for human action recognition from skeleton data
52. A new representation of skeleton sequences for 3D action recognition
53. EleAtt-RNN: adding attentiveness to neurons in recurrent neural networks10.1109/TIP.2019.2937724 ↗
54. Enhanced skeleton visualization for view invariant human action recognition10.1016/j.patcog.2017.02.030 ↗
55. Richly activated graph convolutional network for action recognition with incomplete skeletons