Skip to main content
SpringerLink
Log in

Simple Pose Network with Skip-Connections for Single Human Pose Estimation

  • Conference paper
  • First Online:
Advances in Computational Collective Intelligence (ICCCI 2020)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1287))

Included in the following conference series:

  • 1182 Accesses

Abstract

Recently, following the success of deep convolutional neural networks, human pose estimation problem has been largely improved. This paper introduces an improved version of the Simple Pose network for single human pose estimation. It adds the skip-connections between the same-resolution layers of the backbone and up-sampling stream to fuse low-level and high-level features. To make the depth of features from low-level and high-level are same, this paper uses \(1\,\times \,1\) convolutional layer. The experiments show that this naive technique makes the new networks better over 1% mAP scores with just a small increment in model size.

Most of this work was done when Van-Thanh Hoang studied at University of Ulsan.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Bulat, A., Tzimiropoulos, G.: Human pose estimation via convolutional part heatmap regression. In: Proceedings of the European Conference on Computer Vision, pp. 717–732 (2016)

    Google Scholar 

  2. Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G., Sun, J.: Cascaded pyramid network for multi-person pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)

    Google Scholar 

  3. Chen, Y., Shen, C., Wei, X.S., Liu, L., Yang, J.: Adversarial posenet: a structure-aware convolutional network for human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1212–1221 (2017)

    Google Scholar 

  4. Chu, X., Yang, W., Ouyang, W., Ma, C., Yuille, A.L., Wang, X.: Multi-context attention for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1831–1840 (2017)

    Google Scholar 

  5. Gkioxari, G., Arbelaez, P., Bourdev, L., Malik, J.: Articulated pose estimation using discriminative armlet classifiers. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3342–3349 (2013)

    Google Scholar 

  6. He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)

    Google Scholar 

  7. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  8. Hoang, V.T., Hoang, V.D., Jo, K.H.: An improved method for 3D shape estimation using cascade of neural networks. In: Proceedings of the IEEE International Conference on Industrial Informatics, pp. 285–289 (2017)

    Google Scholar 

  9. Hoang, V.T., Jo, K.H.: 3D human pose estimation using cascade of multiple neural networks. IEEE Transactions on Industrial Informatics 15(4), 2064–2072 (2019). https://doi.org/10.1109/TII.2018.2864824

    Article  Google Scholar 

  10. Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., Schiele, B.: Deepercut: a deeper, stronger, and faster multi-person pose estimation model. In: Proceedings of the European Conference on Computer Vision, pp. 34–50 (2016)

    Google Scholar 

  11. Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the International Conference on Machine Learning, pp. 448–456 (2015)

    Google Scholar 

  12. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the International Conference on Learning Representations (2015)

    Google Scholar 

  13. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Proceedings of Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)

    Google Scholar 

  14. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998). https://doi.org/10.1109/5.726791

    Article  Google Scholar 

  15. Lin, T.Y., et al.: Microsoft coco: common objects in context. In: Proceedings of the European Conference on Computer Vision, pp. 740–755 (2014)

    Google Scholar 

  16. Liu, W., et al.: Ssd: single shot multibox detector. In: Proceedings of the European Conference on Computer Vision, pp. 21–37 (2016)

    Google Scholar 

  17. Luo, R.C., Chen, S.Y.: Human pose estimation in 3-D space using adaptive control law with point-cloud-based limb regression approach. IEEE Trans. Ind. Inform. 12(1), 51–58 (2016)

    Article  MathSciNet  Google Scholar 

  18. Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Proceedings of the European Conference on Computer Vision, pp. 483–499 (2016)

    Google Scholar 

  19. Papandreou, G., et al.: Towards accurate multi-person pose estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4903–4911 (2017)

    Google Scholar 

  20. Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Proceedings of the Neural Information Processing Systems (2019)

    Google Scholar 

  21. Pishchulin, L., Andriluka, M., Gehler, P., Schiele, B.: Poselet conditioned pictorial structures. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 588–595 (2013)

    Google Scholar 

  22. Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2017)

    Article  Google Scholar 

  23. Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015)

    Article  MathSciNet  Google Scholar 

  24. Sapp, B., Taskar, B.: Modec: multimodal decomposable models for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3674–3681 (2013)

    Google Scholar 

  25. Tompson, J.J., Jain, A., LeCun, Y., Bregler, C.: Joint training of a convolutional network and a graphical model for human pose estimation. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 1799–1807 (2014)

    Google Scholar 

  26. Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: Proceedings of the European Conference on Computer Vision (2018)

    Google Scholar 

  27. Yang, W., Li, S., Ouyang, W., Li, H., Wang, X.: Learning feature pyramids for human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1281–1290 (2017)

    Google Scholar 

  28. Yu, J., Hong, C., Rui, Y., Tao, D.: Multitask autoencoder model for recovering human poses. IEEE Trans. Ind. Electron. 65(6), 5060–5068 (2018)

    Article  Google Scholar 

Download references

Acknowledgments

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the government (MSIT) (No. 2020R1A2C2008972).

Author information

Authors and Affiliations

  1. Department of Engineering-Technology, Quang Binh University, Dong Hoi, Vietnam

    Van-Thanh Hoang

  2. School of Electrical Engineering, University of Ulsan, Ulsan, Korea

    Van-Thanh Hoang & Kang-Hyun Jo

Authors
  1. Van-Thanh Hoang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kang-Hyun Jo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Van-Thanh Hoang .

Editor information

Editors and Affiliations

  1. Wroclaw University of Economics and Business, Wrocław, Poland

    Marcin Hernes

  2. Wrocław University of Science and Technology, Wrocław, Poland

    Krystian Wojtkiewicz

  3. University of Newcastle, Newcastle, Australia

    Edward Szczerbicki

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Hoang, VT., Jo, KH. (2020). Simple Pose Network with Skip-Connections for Single Human Pose Estimation. In: Hernes, M., Wojtkiewicz, K., Szczerbicki, E. (eds) Advances in Computational Collective Intelligence. ICCCI 2020. Communications in Computer and Information Science, vol 1287. Springer, Cham. https://doi.org/10.1007/978-3-030-63119-2_14

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-63119-2_14

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-63118-5

  • Online ISBN: 978-3-030-63119-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation