skip to main content
10.1145/3555776.3578481acmconferencesArticle/Chapter ViewAbstractPublication PagessacConference Proceedingsconference-collections
poster

Convolutional Method for Modeling Video Temporal Context Effectively in Transformer

Published: 07 June 2023 Publication History

Abstract

Video understanding remains a challenging task because video understanding models have many parameters to be trained and should capture detailed spatiotemporal contexts in video effectively. Recent methods have typically employed 3D convolution modules or else self-attention modules. However, we identify that when the self-attention mechanism captures temporal semantics, it often struggles to find out proper temporal context for video understanding. In this paper, we propose a new method for enhancing temporal modeling by incorporating 3D convolution modules into attention-based model, transformer. In particular, we replace the temporal attention of the TimeSformer with a 3D convolution module to improve temporal context learning. In contrast to the TimeSformer, our proposed method can focus on modeling temporal details at the low-level encoders, while gradually getting to focus on temporal contexts more globally at the high-level encoders. Our method surpasses the TimeSformer by 2.2% margin on Something-Something v2, which is required complex temporal modeling for getting high performance.

References

[1]
Anurag Arnab, Mostafa Dehghani, Georg Heigold, Chen Sun, Mario Lučić, and Cordelia Schmid. 2021. Vivit: A video vision transformer. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 6836--6846.
[2]
Gedas Bertasius, Heng Wang, and Lorenzo Torresani. 2021. Is space-time attention all you need for video understanding?. In ICML, Vol. 2. 4.
[3]
Adrian Bulat, Juan Manuel Perez Rua, Swathikiran Sudhakaran, Brais Martinez, and Georgios Tzimiropoulos. 2021. Space-time mixing attention for video transformer. Advances in Neural Information Processing Systems 34 (2021), 19594--19607.
[4]
Joao Carreira, Eric Noland, Andras Banki-Horvath, Chloe Hillier, and Andrew Zisserman. 2018. A short note about kinetics-600. arXiv preprint arXiv:1808.01340 (2018).
[5]
Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition. Ieee, 248--255.
[6]
Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2020. An image is worth 16×16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020).
[7]
Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, and Kaiming He. 2019. Slow-fast networks for video recognition. In Proceedings of the IEEE/CVF international conference on computer vision. 6202--6211.
[8]
Raghav Goyal, Samira Ebrahimi Kahou, Vincent Michalski, Joanna Materzynska, Susanne Westphal, Heuna Kim, Valentin Haenel, Ingo Fruend, Peter Yianilos, Moritz Mueller-Freitag, et al. 2017. The" something something" video database for learning and evaluating visual common sense. In Proceedings of the IEEE international conference on computer vision. 5842--5850.
[9]
Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017).
[10]
Shuiwang Ji, Wei Xu, Ming Yang, and Kai Yu. 2012. 3D convolutional neural networks for human action recognition. IEEE transactions on pattern analysis and machine intelligence 35, 1 (2012), 221--231.
[11]
Yanghao Li, Chao-Yuan Wu, Haoqi Fan, Karttikeya Mangalam, Bo Xiong, Jitendra Malik, and Christoph Feichtenhofer. 2022. MViTv2: Improved Multiscale Vision Transformers for Classification and Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 4804--4814.
[12]
Ramprasaath R Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra. 2017. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision. 618--626.
[13]
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017).

Index Terms

  1. Convolutional Method for Modeling Video Temporal Context Effectively in Transformer

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    SAC '23: Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing
    March 2023
    1932 pages
    ISBN:9781450395175
    DOI:10.1145/3555776
    Permission to make digital or hard copies of part or all 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 third-party components of this work must be honored. For all other uses, contact the owner/author(s).

    Sponsors

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 07 June 2023

    Check for updates

    Author Tags

    1. video classification
    2. transformer
    3. 3D convolution
    4. self-attention
    5. temporal feature
    6. computer vision

    Qualifiers

    • Poster

    Conference

    SAC '23
    Sponsor:

    Acceptance Rates

    Overall Acceptance Rate 1,650 of 6,669 submissions, 25%

    Upcoming Conference

    SAC '25
    The 40th ACM/SIGAPP Symposium on Applied Computing
    March 31 - April 4, 2025
    Catania , Italy

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 69
      Total Downloads
    • Downloads (Last 12 months)37
    • Downloads (Last 6 weeks)0
    Reflects downloads up to 16 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

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media