Skip to main content
Springer Nature Link
Log in

Deep learning network model based on fusion of spatiotemporal features for action recognition

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

In view of the problem that the current deep learning network does not fully extract and fuse spatio-temporal information in the action recognition task, resulting in low recognition accuracy, this paper proposes a deep learning network model based on fusion of spatio-temporal features (FSTFN). Through two networks composed of CNN (Convolutional Neural Networks) and LSTM (Long Short-Term Memory), the time and space information are extracted and fused; multi-segment input is used to process large-scale video frame information to solve the problem of long-term dependence and improve the prediction accuracy; The attention mechanism improves the weight of visual subjects in the network. The experimental verification on the UCF101 (University of Central Florida 101) data set shows that the prediction accuracy of the proposed FSFTN on the UCF101 data set is 92.7%, 4.7% higher than that of Two-stream, which verifies the effectiveness of the network model.

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
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Chen K, Forbus KD (2017) Action recognition from skeleton data via analogical generalization[C]. Proc. 30th International Workshop on Qualitative Reasoning, 55-67

  2. Cooijmans T, Ballas N, Laurent C et al (2016) Recurrent batch normalization[C]. International Conference on Learning Representations: 1-13

  3. Da Silva BCG, Carvalho-Tavares J, Ferrari RJ (2019) Detecting and tracking leukocytes in intravital video microscopy using a Hessian-based spatiotemporal approach[J]. Multidimens Syst Signal Process 30(2):815–839

    Article  Google Scholar 

  4. Deng J, Dong W, Socher R, Li L-J, Liand K, Fei-Fei L (2009) Imagenet: Alarge-scale hierarchical image database[C]. 2009 IEEE conference on computer vision and pattern recognition. IEEE, 248-255

  5. Donahue J, Hendricks AL, Guadarrama S, et al (2015)Long-term recurrent convolutional networks for visual recognition and description[C]. Proceedings of the IEEE conference on computer vision and pattern recognition, 2625-2634

  6. Fan M, Han Q, Zhang X, et al (2018) Human action recognition based on dense sampling of motion boundary and histogram of motion gradient[C]. 2018 IEEE 7th Data Driven Control and Learning Systems Conference (DDCLS). IEEE, 1033-1038

  7. Feichtenhofer C, Pinz A, Zisserman A (2016) Convolutional two-stream network fusion for video action recognition[C]. Proceedings of the IEEE conference on computer vision and pattern recognition, 1933-1941

  8. Han PY, Yee KE, Yin OS (2018) Localized temporal representation in human action recognition[C]. Proceedings of the 2018 VII International Conference on Network, Communication and Computing, 261-266

  9. Hao Y, Xie J, Lin Z (2018) Image Caption via Visual Attention Switch on DenseNet[C]. 2018 International Conference on Network Infrastructure and Digital Content (IC-NIDC). IEEE, 334-338

  10. He K, Zhang X, Ren S, et al (2016) Deep residual learning for image recognition[C]. Proceedings of the IEEE conference on computer vision and pattern recognition, 770-778

  11. Jain A, Singh D (2019) A review on histogram of oriented gradient[J]. IITM J Manag IT 10(1):34–36

    Google Scholar 

  12. Jiang B, Wang MM, Gan W, et al (2019) STM: Spatio-Temporal and motion encoding for action recognition[C]. Proceedings of the IEEE International Conference on Computer Vision, 2000-2009

  13. Karpathy A, Toderici G, Shetty S, et al (2014)Large-scale video classification with convolutional neural networks[C]. Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, 1725-1732

  14. Karthikeyan A, Pavithra S, Anu PM (2020) Detection and classification of 2D and 3D hyper spectral image using enhanced harris corner detector[J]. Scalable Comput: Pract Exp 21(1):93–100

    Google Scholar 

  15. Khan A, Sohail A, Zahoora U et al (2020) A survey of the recent architectures of deep convolutional neural networks[J]. Artif Intell Rev 53:5455–56516

  16. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks[C]. Advances in neural information processing systems, 1097-1105

  17. Kuehne H, Jhuang H, Stiefelhagen R, et al (2013) Hmdb51: A large video database for human motion recognition[M]//High Performance Computing in Science and Engineering ‘12. Springer, Berlin, Heidelberg, 571-582

  18. Li J, Liu X, Zhang M et al (2020)Spatio-temporal deformable 3D ConvNets with attention for action recognition[J]. Pattern Recognit 98:107–117

    Google Scholar 

  19. Meng Z, Kong X, Meng L, et al (2019)Lucas-Kanade optical flow based camera motion estimation approach[C]. 2019 International SoC Design Conference(ISOCC). IEEE, 77-78

  20. Nazir S, Yousaf MH, Velastin SA (2018) Evaluating a bag-of-visual features approach using spatio-temporal features for action recognition[J]. Comput Electr Eng 72:660–669

    Article  Google Scholar 

  21. Ragupathy P, Vivekanandan P (2021) A modified fuzzy histogram of optical flow for emotion classification[J]. Journal of Ambient Intelligence and Humanized Computing 12(2):1–8

  22. Sharma S, Kiros R, Salakhutdinov R (2015) Action recognition using visual attention[C]. Neural Information Processing Systems: Time Series Workshop, 1212-1225

  23. Simonyan K, Zisserman A (2014)Two-stream convolutional networks for action recognition in videos[C]. Advance Neural Information Processing Systems, 568-576

  24. Soomro K, Zamir A R,Shah M (2012) UCF101: A dataset of 101 human actions classes from videos in the wild[J]. arXiv:1212.0402:1055–1069

  25. Sun B, Kong D, Wang S et al (2019) Effective human action recognition using global and local offsets of skeleton joints[J]. Multimed Tools Appl 78(5):6329–6353

    Article  Google Scholar 

  26. Tanfous AB, Drira H, Amor BB (2020) Sparse coding of shape trajectories for facial expression and action recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence 42(10):2594–2607

    Article  Google Scholar 

  27. Tang Y, Tian Y, Lu J, et al (2018) Deep progressive reinforcement learning for skeleton-based action recognition[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 5323-5332

  28. Tran D, Bourdev L, Fergus R, et al (2015) Learning spatiotemporal features with 3d convolutional networks[C]. Proceedings of the IEEE international conference on computer vision, 4489-4497

  29. Wang L, Xiong Y, Wang Z et al (2016) Temporal segment networks: Towards good practices for deep action recognition[C]. European conference on computer vision. Springer, Cham, pp 20–36

  30. Wang X, Yu L, Ren K, et al (2017) Dynamic attention deep model for article recommendation by learning human editors’ demonstration[C]. Proceedings of the 23rd ACMSIGKDD International Conference on Knowledge Discovery and Data Mining, 2051-2059

  31. Yao K, Sang N, Gao C (2018) A cuboid bi-level log operator for action classification[J]. IEEE Access 6:54147–54157

    Article  Google Scholar 

  32. Yan S, Xiong Y, Lin D (2018) Spatial temporal graph convolutional networks for skeleton-based action recognition[C]. Thirty-second AAAI conference on artificial intelligence, 65-77

  33. Yu Y, Si X, Hu C et al (2019) A review of recurrent neural networks: LSTM cells and network architectures[J]. Neural Comput 31(7):1235–1270

    Article  MathSciNet  Google Scholar 

  34. Yue-Hei Ng J, Hausknecht M, Vijayanarasimhan S, et al (2015) Beyond short snippets: Deep networks for video classification[C]. Proceedings of the IEEE conference on computer vision and pattern recognition, 4694-4702

  35. Zhang Z (2018) Improved Adamoptimizer for deep neural networks[C]. 2018 IEEE/ACM 26th International Symposiumon Quality of Service(IWQoS). IEEE, 1-2

Download references

Acknowledgements

This research was financially supported by Major Scientific Research Project for Universities of Guangdong Province (2018KTSCX288, 2019KZDXM015, 2020ZDZX3058); Guangdong Provincial special funds Project for Discipline Construction (No.2013WYXM0122); Guangdong Provincial College Innovation and Entrepreneurship Project (S201913177027, S201913177040, 201813177028, 201813177046); Scientific Research Project of Shenzhen (JCYJ20170303140803747); Key Laboratory of Intelligent Multimedia Technology(201762005).

Author information

Authors and Affiliations

  1. Key Laboratory of Intelligent Multimedia Technology, Beijing Normal University, Zhuhai, 519087, China

    Ge Yang & Wu-xing Zou

  2. Advanced Institute of Natural Sciences, Beijing Normal University at Zhuhai, Zhuhai, 519087, China

    Ge Yang & Wu-xing Zou

  3. Engineering Lab on Intelligent Perception for Internet of Things (ELIP), Shenzhen Graduate School, Peking University, Shenzhen, 518055, China

    Ge Yang

Authors
  1. Ge Yang
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Wu-xing Zou
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Ge Yang.

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

Yang, G., Zou, Wx. Deep learning network model based on fusion of spatiotemporal features for action recognition. Multimed Tools Appl 81, 9875–9896 (2022). https://doi.org/10.1007/s11042-022-11937-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-11937-w

Keywords