Skip to main content
Springer Nature Link
Log in

Pose Knowledge Transfer for multi-person pose estimation

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

Multi-person pose estimation is a fundamental yet challenging research topic for many computer vision applications. In this paper, to relieve the problem of variable pose structure and occlusion in complex scenes, we propose a novel Pose Knowledge Transfer approach for multi-person pose estimation, which doesn’t take into account deeper and wider network structure design. This approach contains a Keypoint Region Erasing (KRE) scheme and a Bi-directional Pose Knowledge Transfer (BPKT) model learning strategy for this task. The KRE encourages human pose estimator to explicitly focus learning on keypoints connectivity to robustly localize the occluded keypoint via its adjacent visible body patches. Specifically, without additional model parameters involvement, the BPKT effectively transfers the local connectivity knowledge and the global body configuration knowledge between two network with the same structure to encounter variable pose structure. Extensive experiments demonstrate that the BPKT and the KRE significantly improve the performance of a range of state-of-the-art human pose estimation models, consistently validating the effectiveness and generalization property of our model-agnostic approach on the MPII human pose dataset and the COCO keypoint benchmark.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. Miki, D., Abe, S., Chen, S., Demachi, K.: Robust human pose estimation from distorted wide-angle images through iterative search of transformation parameters. Signal Image Video Process. 14, 693–700 (2020)

    Article  Google Scholar 

  2. Zhang, F., Zhu, X., Ye, M.: Fast human pose estimation. In: CVPR, pp. 3517–3526. IEEE (2019)

  3. Fabbri, M., Lanzi, F., Calderara, S., Alletto, S., Cucchiara, R.: Compressed volumetric heatmaps for multi-person 3D pose estimation. In: CVPR, pp. 7204–7213. IEEE (2020)

  4. Ning, G., Pei, J., Huang, H.: LightTrack: A generic framework for online top-down human pose tracking. In: CVPR Workshops, pp. 1034–1035. IEEE (2020)

  5. Shi, L., Zhang, Y., Cheng, J., Lu, H.: Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: CVPR, pp. 12026-12035. IEEE (2019)

  6. Xu, J., Zhao, R., Zhu, F., Wang, H., Ouyang, W.: Attention-aware compositional network for person re-identification. In: CVPR, pp. 2119-2128. IEEE (2018)

  7. Cai, Y., Wang, Z., Luo, Z., Yin, B., Du, A., Wang, H., Zhang, X., Zhou, X., Zhou, E., Sun, J.: Learning delicate local representations for multi-person pose estimation (2020). arXiv:2003.04030

  8. Ronchi, M. R., Perona, P.: Benchmarking and Error Diagnosis in Multi-Instance Pose Estimation. In: ICCV, pp. 369-378. IEEE (2017)

  9. Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollar, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: ECCV, pp. 740-755. Springer (2014)

  10. Andriluka, M., Pishchulin, L., Gehler, P. V., Schiele, B.: 2D human pose estimation: new benchmark and state of the art analysis. In: CVPR, pp. 3686–3693 IEEE (2014)

  11. He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: ICCV, pp. 2961–2969. IEEE (2017)

  12. Papandreou, G., Zhu, T., Kanazawa, N., Toshev, A., Tompson, J., Bregler, C., Murphy, K.: Towards accurate multi-person pose estimation in the wild. In: CVPR, pp. 4903–4911. IEEE (2017)

  13. Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G., Sun, J.: Cascaded pyramid network for multi-person pose estimation. In: CVPR, pp. 7103–7112. IEEE (2018)

  14. Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR, pp. 2117–2125. IEEE (2017)

  15. Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: ECCV, pp. 466–481. Springer (2018)

  16. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778. IEEE (2016)

  17. Sun, K., Xiao, B., Liu, D., Wang, J.: Deep High-Resolution Representation Learning for Human Pose Estimation. In: CVPR, pp. 5693-5703. IEEE (2019)

  18. Li, B., Liu, K., Ji, Y., Yang, J., Liu, C.: Selective Complementary Features for Multi-Person Pose Estimation. In: ICIP, pp. 623-627. IEEE (2020)

  19. Bucilua, C., Caruana, R., Niculescu-Mizil, A.: Model compression. In: Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 535–541. ACM (2006)

  20. Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network (2015). arXiv:1503.02531

  21. Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: Fitnets: hints for thin deep nets (2014). arXiv:1412.6550

  22. Zhang, Y., Xiang, T., Hospedales, T.-M., Lu, H.: Deep mutual learning. In: CVPR, pp. 4320–4328. IEEE (2018)

  23. Meng, F., Cheng, H., Li, K., Xu, Z., Ji, R., Sun, X., Lu, G.: Filter grafting for deep neural networks (2020). arXiv:2001.05868

  24. Huang, J., Zhu, Z., Guo, F., Huang, G.: The devil is in the details: delving into unbiased data processing for human pose estimation. In: CVPR, pp. 5700–5709 IEEE (2020)

  25. Sun, X., Xiao, B., Wei, F., Liang, S., Wei, Y.: Integral human pose regression. In: ECCV, pp. 529–545. Springer (2018)

  26. Fang, H.-S., Xie, S., Tai, Y.-W., Lu, C.: RMPE: regional multi-person pose estimation. In: ICCV, pp. 2334–2343. IEEE (2017)

  27. Yang, W., Li, S., Ouyang, W., Li, H., Wang, X.: Learning feature pyramids for human pose estimation. In: ICCV, pp. 1281–1290. IEEE (2017)

  28. Huang, S., Gong, M., Tao, D.: A coarse-fine network for keypoint localization. In: ICCV, pp. 3028–3037. IEEE (2017)

  29. Moon, G., Chang, J. Y., Lee, K. M.: PoseFix: model-agnostic general human pose refinement network. In: CVPR, pp. 7773–7781. IEEE (2019)

  30. Su, K., Yu, D., Xu, Z., Geng, X., Wang, C.: Multi-person pose estimation with enhanced channel-wise and spatial information. In: CVPR, pp. 5674–5682. IEEE (2019)

  31. Yu, D., Su, K., Geng, X., Wang, C.: A Context-and-spatial aware network for multi-person pose estimation (2019). arXiv:1905.05355

  32. Zhang, F., Zhu, X., Dai, H., Ye, M., Zhu, C.: Distribution-Aware Coordinate Representation for Human Pose Estimation. In: CVPR, pp. 7093-7102 IEEE (2020)

  33. MS-COCO.: Coco Keypoint leaderboard. http://cocodataset.org

  34. Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., Devito, Z., Lin, Z., Desmaison, A., Antiga, L., Lerer, A.: Automatic differentiation in PyTorch. In: NIPS (2017)

  35. Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A. C., Fei-Fei, L.: ImageNet large scale visual recognition challenge. In: IJCV, pp. 115(3):211–252 (2015)

  36. Kingma, D. P., Ba, J.: Adam: A method for stochastic optimization (2014). arXiv:1412.6980

Download references

Acknowledgements

This research was supported by National Natural Science Foundation of China (61972059, 61773272), The Natural Science Foundation of the Jiangsu Higher Education Institutions of China (19KJA230001), and The Priority Academic Program Development of Jiangsu Higher Education Institutions.

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, Soochow University, Suzhou, China

    Buwei Li, Yi Ji, Ying Li & Chunping Liu

  2. School of Applied Technology, Soochow University, Suzhou, China

    Yunlong Xu

Authors
  1. Buwei Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Yi Ji
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Ying Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Yunlong Xu
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Chunping Liu
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Chunping Liu.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, B., Ji, Y., Li, Y. et al. Pose Knowledge Transfer for multi-person pose estimation. SIViP 16, 321–328 (2022). https://doi.org/10.1007/s11760-021-01922-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-021-01922-5

Keywords