Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
133 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Multi-Dimensional Refinement Graph Convolutional Network with Robust Decouple Loss for Fine-Grained Skeleton-Based Action Recognition (2306.15321v1)

Published 27 Jun 2023 in cs.CV

Abstract: Graph convolutional networks have been widely used in skeleton-based action recognition. However, existing approaches are limited in fine-grained action recognition due to the similarity of inter-class data. Moreover, the noisy data from pose extraction increases the challenge of fine-grained recognition. In this work, we propose a flexible attention block called Channel-Variable Spatial-Temporal Attention (CVSTA) to enhance the discriminative power of spatial-temporal joints and obtain a more compact intra-class feature distribution. Based on CVSTA, we construct a Multi-Dimensional Refinement Graph Convolutional Network (MDR-GCN), which can improve the discrimination among channel-, joint- and frame-level features for fine-grained actions. Furthermore, we propose a Robust Decouple Loss (RDL), which significantly boosts the effect of the CVSTA and reduces the impact of noise. The proposed method combining MDR-GCN with RDL outperforms the known state-of-the-art skeleton-based approaches on fine-grained datasets, FineGym99 and FSD-10, and also on the coarse dataset NTU-RGB+D X-view version.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (59)
  1. C. Zhong, L. Hu, Z. Zhang, Y. Ye, and S. Xia, “Spatio-temporal gating-adjacency gcn for human motion prediction,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 6447–6456.
  2. Y. Du, W. Wang, and L. Wang, “Hierarchical recurrent neural network for skeleton based action recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 1110–1118.
  3. J. Liu, A. Shahroudy, D. Xu, and G. Wang, “Spatio-temporal lstm with trust gates for 3d human action recognition,” in European conference on computer vision.   Springer, 2016, pp. 816–833.
  4. S. Song, C. Lan, J. Xing, W. Zeng, and J. Liu, “An end-to-end spatio-temporal attention model for human action recognition from skeleton data,” in Proceedings of the AAAI conference on artificial intelligence, vol. 31, no. 1, 2017.
  5. H. Liu, J. Tu, and M. Liu, “Two-stream 3d convolutional neural network for skeleton-based action recognition,” arXiv preprint arXiv:1705.08106, 2017.
  6. Y. Hou, Z. Li, P. Wang, and W. Li, “Skeleton optical spectra-based action recognition using convolutional neural networks,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 28, no. 3, pp. 807–811, 2016.
  7. S. Yan, Y. Xiong, and D. Lin, “Spatial temporal graph convolutional networks for skeleton-based action recognition,” in Thirty-second AAAI conference on artificial intelligence, 2018.
  8. L. Shi, Y. Zhang, J. Cheng, and H. Lu, “Two-stream adaptive graph convolutional networks for skeleton-based action recognition,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 12 026–12 035.
  9. Y.-F. Song, Z. Zhang, C. Shan, and L. Wang, “Richly activated graph convolutional network for robust skeleton-based action recognition,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 31, no. 5, pp. 1915–1925, 2020.
  10. J. Gao, T. He, X. Zhou, and S. Ge, “Skeleton-based action recognition with focusing-diffusion graph convolutional networks,” IEEE Signal Processing Letters, vol. 28, pp. 2058–2062, 2021.
  11. Y. Chen, Z. Zhang, C. Yuan, B. Li, Y. Deng, and W. Hu, “Channel-wise topology refinement graph convolution for skeleton-based action recognition,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 13 359–13 368.
  12. X. Shu, J. Yang, R. Yan, and Y. Song, “Expansion-squeeze-excitation fusion network for elderly activity recognition,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 8, pp. 5281–5292, 2022.
  13. H.-g. Chi, M. H. Ha, S. Chi, S. W. Lee, Q. Huang, and K. Ramani, “Infogcn: Representation learning for human skeleton-based action recognition,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 20 186–20 196.
  14. D. Ahn, S. Kim, H. Hong, and B. C. Ko, “Star-transformer: A spatio-temporal cross attention transformer for human action recognition,” in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023, pp. 3330–3339.
  15. Y.-F. Song, Z. Zhang, C. Shan, and L. Wang, “Constructing stronger and faster baselines for skeleton-based action recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022.
  16. D. Chang, Y. Ding, J. Xie, A. K. Bhunia, X. Li, Z. Ma, M. Wu, J. Guo, and Y.-Z. Song, “The devil is in the channels: Mutual-channel loss for fine-grained image classification,” IEEE Transactions on Image Processing, vol. 29, pp. 4683–4695, 2020.
  17. S. Li, T. Liu, J. Tan, D. Zeng, and S. Ge, “Trustable co-label learning from multiple noisy annotators,” IEEE Transactions on Multimedia, 2021.
  18. S. Li, X. Xia, S. Ge, and T. Liu, “Selective-supervised contrastive learning with noisy labels,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 316–325.
  19. Y. Wen, K. Zhang, Z. Li, and Y. Qiao, “A discriminative feature learning approach for deep face recognition,” in European conference on computer vision.   Springer, 2016, pp. 499–515.
  20. X. He, Y. Zhou, Z. Zhou, S. Bai, and X. Bai, “Triplet-center loss for multi-view 3d object retrieval,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 1945–1954.
  21. W. Liu, Y. Wen, Z. Yu, and M. Yang, “Large-margin softmax loss for convolutional neural networks,” arXiv preprint arXiv:1612.02295, 2016.
  22. W. Liu, Y. Wen, Z. Yu, M. Li, B. Raj, and L. Song, “Sphereface: Deep hypersphere embedding for face recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 212–220.
  23. F. Wang, J. Cheng, W. Liu, and H. Liu, “Additive margin softmax for face verification,” IEEE Signal Processing Letters, vol. 25, no. 7, pp. 926–930, 2018.
  24. J. Deng, J. Guo, N. Xue, and S. Zafeiriou, “Arcface: Additive angular margin loss for deep face recognition,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 4690–4699.
  25. M. Kim, A. K. Jain, and X. Liu, “Adaface: Quality adaptive margin for face recognition,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 18 750–18 759.
  26. Y. Zhang, Y. Huang, S. Yu, and L. Wang, “Cross-view gait recognition by discriminative feature learning,” IEEE Transactions on Image Processing, vol. 29, pp. 1001–1015, 2019.
  27. J. Peeples, C. H. McCurley, S. Walker, D. Stewart, and A. Zare, “Learnable adaptive cosine estimator (lace) for image classification,” in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022, pp. 3479–3489.
  28. L. Li, W. Zheng, Z. Zhang, Y. Huang, and L. Wang, “Skeleton-based relational modeling for action recognition. corr abs/1805.02556 (2018),” 1805.
  29. X. Jiang, K. Xu, and T. Sun, “Action recognition scheme based on skeleton representation with ds-lstm network,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 30, no. 7, pp. 2129–2140, 2019.
  30. M. Henaff, J. Bruna, and Y. LeCun, “Deep convolutional networks on graph-structured data,” arXiv preprint arXiv:1506.05163, 2015.
  31. T. Soo Kim and A. Reiter, “Interpretable 3d human action analysis with temporal convolutional networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition workshops, 2017, pp. 20–28.
  32. C. Li, Q. Zhong, D. Xie, and S. Pu, “Skeleton-based action recognition with convolutional neural networks,” in 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW).   IEEE, 2017, pp. 597–600.
  33. C. Cao, C. Lan, Y. Zhang, W. Zeng, H. Lu, and Y. Zhang, “Skeleton-based action recognition with gated convolutional neural networks,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 29, no. 11, pp. 3247–3257, 2018.
  34. C. Li, C. Xie, B. Zhang, J. Han, X. Zhen, and J. Chen, “Memory attention networks for skeleton-based action recognition,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 9, pp. 4800–4814, 2021.
  35. D. I. Shuman, S. K. Narang, P. Frossard, A. Ortega, and P. Vandergheynst, “The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains,” IEEE signal processing magazine, vol. 30, no. 3, pp. 83–98, 2013.
  36. T. Kipf, E. Fetaya, K.-C. Wang, M. Welling, and R. Zemel, “Neural relational inference for interacting systems,” in International Conference on Machine Learning.   PMLR, 2018, pp. 2688–2697.
  37. F. Ye, S. Pu, Q. Zhong, C. Li, D. Xie, and H. Tang, “Dynamic gcn: Context-enriched topology learning for skeleton-based action recognition,” in Proceedings of the 28th ACM International Conference on Multimedia, 2020, pp. 55–63.
  38. K. Cheng, Y. Zhang, X. He, W. Chen, J. Cheng, and H. Lu, “Skeleton-based action recognition with shift graph convolutional network,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 183–192.
  39. Z. Qin, Y. Liu, P. Ji, D. Kim, L. Wang, R. McKay, S. Anwar, and T. Gedeon, “Fusing higher-order features in graph neural networks for skeleton-based action recognition,” IEEE Transactions on Neural Networks and Learning Systems, 2022.
  40. K. Cheng, Y. Zhang, C. Cao, L. Shi, J. Cheng, and H. Lu, “Decoupling gcn with dropgraph module for skeleton-based action recognition,” in European Conference on Computer Vision.   Springer, 2020, pp. 536–553.
  41. H. Duan, Y. Zhao, K. Chen, D. Lin, and B. Dai, “Revisiting skeleton-based action recognition,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 2969–2978.
  42. I. Masi, Y. Wu, T. Hassner, and P. Natarajan, “Deep face recognition: A survey,” in 2018 31st SIBGRAPI conference on graphics, patterns and images (SIBGRAPI).   IEEE, 2018, pp. 471–478.
  43. M. Wang and W. Deng, “Deep face recognition: A survey,” Neurocomputing, vol. 429, pp. 215–244, 2021.
  44. R. Hadsell, S. Chopra, and Y. LeCun, “Dimensionality reduction by learning an invariant mapping,” in 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’06), vol. 2.   IEEE, 2006, pp. 1735–1742.
  45. K. Sohn, “Improved deep metric learning with multi-class n-pair loss objective,” Advances in neural information processing systems, vol. 29, 2016.
  46. A. Hermans, L. Beyer, and B. Leibe, “In defense of the triplet loss for person re-identification,” arXiv preprint arXiv:1703.07737, 2017.
  47. J. Wang, F. Zhou, S. Wen, X. Liu, and Y. Lin, “Deep metric learning with angular loss,” in Proceedings of the IEEE international conference on computer vision, 2017, pp. 2593–2601.
  48. F. Wang, X. Xiang, J. Cheng, and A. L. Yuille, “Normface: L2 hypersphere embedding for face verification,” in Proceedings of the 25th ACM international conference on Multimedia, 2017, pp. 1041–1049.
  49. H. Wang, Y. Wang, Z. Zhou, X. Ji, D. Gong, J. Zhou, Z. Li, and W. Liu, “Cosface: Large margin cosine loss for deep face recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 5265–5274.
  50. X. Zhang, R. Zhao, Y. Qiao, X. Wang, and H. Li, “Adacos: Adaptively scaling cosine logits for effectively learning deep face representations,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 10 823–10 832.
  51. B. Liu, W. Deng, Y. Zhong, M. Wang, J. Hu, X. Tao, and Y. Huang, “Fair loss: Margin-aware reinforcement learning for deep face recognition,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 10 052–10 061.
  52. D. Shao, Y. Zhao, B. Dai, and D. Lin, “Finegym: A hierarchical video dataset for fine-grained action understanding,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 2616–2625.
  53. H. Duan, J. Wang, K. Chen, and D. Lin, “Pyskl: Towards good practices for skeleton action recognition,” arXiv preprint arXiv:2205.09443, 2022.
  54. S. Liu, X. Liu, G. Huang, H. Qiao, L. Hu, D. Jiang, A. Zhang, Y. Liu, and G. Guo, “Fsd-10: A fine-grained classification dataset for figure skating,” Neurocomputing, vol. 413, pp. 360–367, 2020.
  55. A. Shahroudy, J. Liu, T.-T. Ng, and G. Wang, “Ntu rgb+ d: A large scale dataset for 3d human activity analysis,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 1010–1019.
  56. Z. Liu, H. Zhang, Z. Chen, Z. Wang, and W. Ouyang, “Disentangling and unifying graph convolutions for skeleton-based action recognition,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 143–152.
  57. M. Li, S. Chen, X. Chen, Y. Zhang, Y. Wang, and Q. Tian, “Actional-structural graph convolutional networks for skeleton-based action recognition,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 3595–3603.
  58. Z. Chen, S. Li, B. Yang, Q. Li, and H. Liu, “Multi-scale spatial temporal graph convolutional network for skeleton-based action recognition,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 2, 2021, pp. 1113–1122.
  59. L. Van der Maaten and G. Hinton, “Visualizing data using t-sne.” Journal of machine learning research, vol. 9, no. 11, 2008.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now