skip to main content
10.1145/3697467.3697629acmotherconferencesArticle/Chapter ViewAbstractPublication PagesiotmlConference Proceedingsconference-collections
research-article

Research on Human Behavior Recognition Based on 3D-Ghostnet

Published: 08 November 2024 Publication History

Abstract

To address the problems of large number of parameters, low accuracy and information redundancy in traditional 3D convolutional neural networks, the paper proposes an improved lightweight action recognition network with fused attention mechanism. Firstly, the feature extraction capability is enhanced by adding an improved spatio-temporal separation self-attention mechanism; Then, an improved 3D-Ghostnet convolutional neural network is used in the 3D convolutional part to lighten the network and solve the information redundancy problem; Finally, experiments are conducted on several datasets to verify the effectiveness of the network. The results show that the proposed behaviour recognition network has a computational cost of14.85GFlops, a parametric amount of18.83 M, and a recognition accuracy of 75.9% and 96.2% on the HMDB51 dataset and the UCF101 dataset, demonstrating the effectiveness of the algorithmic framework.

References

[1]
Hatirnaz E, Sah M, Direkoglu C. A novel framework and concept-based semantic search Interface for abnormal crowd behaviour analysis in surveillance videos[J]. Multimedia Tools and Applications, 2020, 79(25-26): 17579-17617.
[2]
Liu ZH, Luo YZ. Intelligent video supervising technologies and their applications in security[J]. Ordnance Industry Automation. 2009; 4:7578.
[3]
Qianyin J, Guoming L, Jinwei Y, et al. A model based method of pedestrian abnormal behavior detection in traffic scene[C]//2015 IEEE First International Smart Cities Conference (ISC2). IEEE, 2015: 1-6.
[4]
Lentzas A, Vrakas D. Non-intrusive human activity recognition and abnormal behavior detection on elderly people: A review[J]. Artificial Intelligence Review, 2020, 53(3): 1975-2021.
[5]
Wang H, Schmid C. Action recognition with improved trajectories[C]//Proceedings of the IEEE international conference on computer vision. 2013: 3551-3558.
[6]
Lu J, Yan W Q, Nguyen M. Human behaviour recognition using deep learning[C]//2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). IEEE, 2018: 1-6.
[7]
Tran D, Bourdev L, Fergus R, et al. Learning spatiotemporal features with 3d convolutional networks[C]//Proceedings of the IEEE international conference on computer vision. 2015: 4489-4497.
[8]
Carreira J, Zisserman A. Quo vadis, action recognition? a new model and the kinetics dataset[C]//proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017: 6299-6308.
[9]
Qiu Z, Yao T, Mei T. Learning spatio-temporal representation with pseudo-3d residual networks[C]//proceedings of the IEEE International Conference on Computer Vision. 2017: 5533-5541.
[10]
Tran D, Wang H, Torresani L, et al. A closer look at spatiotemporal convolutions for action recognition[C]//Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 2018: 6450-6459.
[11]
Han K, Wang Y, Tian Q, et al. Ghostnet: More features from cheap operations[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 1580-1589.
[12]
Wang X, Girshick R, Gupta A, et al. Non-local neural networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7794-7803.
[13]
Bertasius G, Wang H, Torresani L. Is space-time attention all you need for video understanding? [C]//ICML. 2021, 2(3): 4.
[14]
Xie C, Wu Y, Maaten L, et al. Feature denoising for improving adversarial robustness[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019: 501-509.
[15]
Tai C, Xiao T, Zhang Y, et al. Convolutional neural networks with low-rank regularization[J]. arXiv preprint arXiv:1511.06067, 2015.
[16]
Huang Z, Wang X, Huang L, et al. Ccnet: Criss-cross attention for semantic segmentation[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2019: 603-612.
[17]
Kumawat S, Verma M, Nakashima Y, et al. Depthwise spatio-temporal STFT convolutional neural networks for human action recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 44(9): 4839-4851.
[18]
Wang M, Xing J, Liu Y. Actionclip: A new paradigm for video action recognition [J]. arXiv preprint arXiv: 2109.08472, 2021.
[19]
Diba A, Fayyaz M, Sharma V, et al. Temporal 3d convnets: New architecture and transfer learning for video classification [J]. arXiv preprint arXiv:1711.08200, 2017.
[20]
Wang L, Xiong Y, Wang Z, et al. Temporal segment networks: Towards good practices for deep action recognition[C]//European conference on computer vision. Springer, Cham, 2016: 20-36.

Index Terms

  1. Research on Human Behavior Recognition Based on 3D-Ghostnet

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    IoTML '24: Proceedings of the 2024 4th International Conference on Internet of Things and Machine Learning
    August 2024
    443 pages
    ISBN:9798400710353
    DOI:10.1145/3697467
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 08 November 2024

    Check for updates

    Author Tags

    1. 3D convolutional neural network
    2. Action recognition
    3. Divided space-time attention
    4. Ghost Module
    5. Light weight

    Qualifiers

    • Research-article

    Conference

    IoTML 2024

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 24
      Total Downloads
    • Downloads (Last 12 months)24
    • Downloads (Last 6 weeks)11
    Reflects downloads up to 18 Feb 2025

    Other Metrics

    Citations

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Full Text

    View this article in Full Text.

    Full Text

    HTML Format

    View this article in HTML Format.

    HTML Format

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media