Skip to main content
Springer Nature Link
Log in

C-HigherHRNet: cross-scale dynamic fusion for robust pose estimation in dense and crowded scenes

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

Abstract

Human pose estimation plays a fundamental role in understanding human behaviors and interactions in complex scenes. Among existing approaches, High-Resolution Networks (HRNet) and their variants have demonstrated strong performance in dense scenarios by maintaining high-resolution representations and enabling multi-scale feature fusion. However, the commonly used fusion strategies in HRNet are relatively simple, which limits their ability to effectively exploit cross-scale complementary information and thus affects robustness in challenging environments. To address these limitations, we propose C-HigherHRNet, an enhanced architecture built upon HigherHRNet. Specifically, a cross-scale dynamic fusion module is designed to adaptively aggregate informative features while suppressing redundant responses, improving the effectiveness of multi-scale representation learning. In addition, DySample-based upsampling is employed to enhance the quality of reconstructed feature maps, and skip connections are introduced to mitigate the loss of spatial details during multi-stage refinement. Extensive experiments on benchmark datasets, including COCO and CrowdPose, as well as a self-collected real-world dataset, demonstrate that the proposed method consistently improves keypoint localization accuracy. These results validate the effectiveness and generalization capability of C-HigherHRNet in handling complex scenarios with dense crowds and large-scale variations.

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+
from €37.37 /Month
  • Starting from 10 chapters or articles per month
  • Access and download chapters and articles from more than 300k books and 2,500 journals
  • Cancel anytime
View plans

Buy Now

Price includes VAT (Netherlands)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Explore related subjects

Discover the latest articles, books and news in related subjects, suggested using machine learning.

Data Availability

The publicly available datasets used in this study are COCO (https://cocodataset.org) and CrowdPose (https://github.com/Jeff-sjtu/CrowdPose). The privately collected dataset is not publicly available due to privacy/confidentiality reasons.

References

  1. Duan, H., Zhao, Y., Chen, K., Lin, D., Dai, B.: Revisiting skeleton-based action recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2969–2978. (2022)

  2. Liu, H., Liu, T., Zhang, Z., Sangaiah, A.K., Yang, B., Li, Y.: Arhpe: asymmetric relation-aware representation learning for head pose estimation in industrial human-computer interaction. IEEE Trans. Industr. Inf. 18(10), 7107–7117 (2022)

    Article  Google Scholar 

  3. Jahagirdar, A., Sathe, N., Thorat, S., Saxena, S.: Fire detection in nano-satellite imagery using mask r-cnn. Int. J. Signal Imaging Syst. Eng. 13(1), 19–26 (2024)

    Google Scholar 

  4. Toshev, A., Szegedy, C.: Deeppose: Human pose estimation via deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1653–1660. (2014)

  5. Newell, A., Huang, Z., Deng, J.: Associative embedding: end-to-end learning for joint detection and grouping. Advanc. Neural Inf. Process. Syst., 30. (2017)

  6. Cao, Z., Hidalgo, G., Simon, T., Wei, S.-E., Sheikh, Y.: Openpose: Realtime multi-person 2d pose estimation using part affinity fields. IEEE Trans. Pattern Anal. Mach. Intell. 43(1), 172–186 (2019)

    Article  Google Scholar 

  7. Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 466–481. (2018)

  8. Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., Zitnick, C.L.: Microsoft coco: common objects in context. In: European Conference on Computer Vision, pp. 740–755. Springer (2014)

  9. Li, J., Wang, C., Zhu, H., Mao, Y., Fang, H.-S., Lu, C.: Crowdpose: efficient crowded scenes pose estimation and a new benchmark. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10863–10872. (2019)

  10. Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5693–5703. (2019)

  11. Cheng, B., Xiao, B., Wang, J., Shi, H., Huang, T.S., Zhang, L.: Higherhrnet: scale-aware representation learning for bottom-up human pose estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5386–5395. (2020)

  12. Geng, Z., Sun, K., Xiao, B., Zhang, Z., Wang, J.: Bottom-up human pose estimation via disentangled keypoint regression. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14676–14686. (2021)

  13. Papandreou, G., Zhu, T., Chen, L.-C., Gidaris, S., Tompson, J., Murphy, K.: Personlab: person pose estimation and instance segmentation with a bottom-up, part-based, geometric embedding model. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 269–286. (2018)

  14. Kreiss, S., Bertoni, L., Alahi, A.: Pifpaf: Composite fields for human pose estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11977–11986. (2019)

  15. Yu, H., Du, C., Yu, L.: Scale-aware heatmap representation for human pose estimation. Pattern Recogn. Lett. 154, 1–6 (2022)

    Article  Google Scholar 

  16. Lin, T.-Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125. (2017)

  17. Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759–8768 (2018)

  18. Ghiasi, G., Lin, T.-Y., Le, Q.V.: Nas-fpn: Learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7036–7045. (2019)

  19. Tan, M., Pang, R., Le, Q.V.: Efficientdet: scalable and efficient object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10781–10790. (2020)

  20. Dai, L., Yan, R., Tang, J., Zhao, M.: Clct: complementary local consensus transformer for two-view correspondence pruning. IEEE Trans. Multimedia, (2026)

  21. Dai, L., Liu, X., Liu, Y., Yang, C., Wei, L., Lin, Y., Chen, R.: Enhancing two-view correspondence learning by local-global self-attention. Neurocomputing 459, 176–187 (2021)

    Article  Google Scholar 

  22. Dai, L., Du, X., Tang, J.: Lecot: revisiting network architecture for two-view correspondence pruning. SCIENCE CHINA Inf. Sci. 69(1), 112104 (2026)

    Article  Google Scholar 

  23. Dai, L., Liu, Y., Ma, J., Wei, L., Lai, T., Yang, C., Chen, R.: Ms2dg-net: Progressive correspondence learning via multiple sparse semantics dynamic graph. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8963–8972. IEEE (2022)

  24. Dai, L., Du, X., Tang, J.: Trga: reconsidering the application of graph neural networks in two-view correspondence pruning. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 5633–5642. (2024)

  25. Luanyuan, D., Du, X., Zhang, H., Tang, J.: Mgnet: learning correspondences via multiple graphs. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 3945–3953. (2024)

  26. Shi, W., Caballero, J., Huszár, F., Totz, J., Aitken, A.P., Bishop, R., Rueckert, D., Wang, Z.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1874–1883. (2016)

  27. Wang, J., Chen, K., Xu, R., Liu, Z., Loy, C.C., Lin, D.: Carafe: content-aware reassembly of features. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3007–3016. (2019)

  28. Liu, W., Lu, H., Fu, H., Cao, Z.: Learning to upsample by learning to sample. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6027–6037. (2023)

  29. Quan, H., Hu, Y., Bonarini, A.: Polimi-itw-s: a large-scale dataset for human activity recognition in the wild. Data Brief 43, 108420 (2022)

    Article  Google Scholar 

  30. 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)

  31. Papandreou, G., Zhu, T., Kanazawa, N., Toshev, A., Tompson, J., Bregler, C., Murphy, K.: 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)

  32. 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, pp. 7103–7112. (2018)

  33. Fang, H.-S., Li, J., Tang, H., Xu, C., Zhu, H., Xiu, Y., Li, Y.-L., Lu, C.: Alphapose: whole-body regional multi-person pose estimation and tracking in real-time. IEEE Trans. Pattern Anal. Mach. Intell. 45(6), 7157–7173 (2022)

    Article  Google Scholar 

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

Download references

Funding

This work was supported in part by Liaoning Provincial Department of Education Basic Research Key Project (LJ212410153035)

Liaoning Provincial Science and Technology Plan Joint Project (2024-MSLH-385).

Author information

Authors and Affiliations

  1. School of Electrical and Control Engineering, Shenyang Jianzhu University, Hunnan, ShenYang, 110168, LiaoNing, China

    Xin Wang, Mingyang Guo & Guanhua Li

  2. School of Computer Science and Engineering, Shenyang Jianzhu University, Hunnan, ShenYang, 110168, LiaoNing, China

    Shoujin Wang

Authors
  1. Xin Wang
    View author publications

    Search author on:PubMed Google Scholar

  2. Mingyang Guo
    View author publications

    Search author on:PubMed Google Scholar

  3. Shoujin Wang
    View author publications

    Search author on:PubMed Google Scholar

  4. Guanhua Li
    View author publications

    Search author on:PubMed Google Scholar

Contributions

XW and MG wrote the main manuscript text and SW and GL performed the validation. All authors reviewed the manuscript.

Corresponding author

Correspondence to Xin Wang.

Ethics declarations

Conflict of interest

The authors declare no conflict of interest.

Additional information

Publisher's Note

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

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file 1 (pdf 9398 KB) (download PDF )

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, X., Guo, M., Wang, S. et al. C-HigherHRNet: cross-scale dynamic fusion for robust pose estimation in dense and crowded scenes. SIViP 20, 747 (2026). https://doi.org/10.1007/s11760-026-05832-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Version of record:

  • DOI: https://doi.org/10.1007/s11760-026-05832-2

Keywords