Deep Analysis of CNN-based Spatio-temporal Representations for Action Recognition
Abstract
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 3DCNN models behave similarly in terms of spatio-temporal representation abilities and transferability.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 19, 2021
- Accession Number
- AD1151701
Entities
People
- Aude Oliva
- Chun-fu Chen
- John Cohn
- Kandan Ramakrishnan
- Quanfu Fan
- Rameswar Panda
- Rogerio Feris
Organizations
- Massachusetts Institute of Technology