Deep Analysis of CNN-based Spatio-temporal Representations for Action Recognition



Published on



Computer Vision CVPR

In recent years, a number of approaches based on 2D or 3D convolutional neural networks (CNN) have emerged for video action recognition, achieving state-of-the-art results on several large-scale benchmark datasets. In this paper, we carry out in-depth comparative analysis to better understand the differences between these approaches and the progress made by them. To this end, we develop an unified framework for both 2D-CNN and 3D-CNN action models, which enables us to remove bells and whistles and provides a common ground for fair comparison. We then conduct an effort towards a large-scale analysis involving over 300 action recognition models. Our comprehensive analysis reveals that a) a significant leap is made in efficiency for action recognition, but not in accuracy; b) 2D-CNN and 3D-CNN models behave similarly in terms of spatio-temporal representation abilities and transferability.

This paper has been published at CVPR 2021.

Please cite our work using the BibTeX below.

    author    = {Chen, Chun-Fu Richard and Panda, Rameswar and Ramakrishnan, Kandan and Feris, Rogerio and Cohn, John and Oliva, Aude and Fan, Quanfu},
    title     = {Deep Analysis of CNN-Based Spatio-Temporal Representations for Action Recognition},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2021},
    pages     = {6165-6175}
Close Modal