Deep Analysis of CNN-based Spatio-temporal Representations for Action Recognition
arXiv:2010.11757
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 3D-CNN models behave similarly in terms of spatio-temporal representation abilities and transferability. Our codes are available at https://github.com/IBM/action-recognition-pytorch.
arXiv commentCVPR 2021 camera-ready version. Codes and models are available on https://github.com/IBM/action-recognition-pytorch
References in corpus (8)
- Two-Stream Convolutional Networks for Action Recognition in Videos
- The Kinetics Human Action Video Dataset
- Unsupervised Learning of Video Representations using LSTMs
- Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors
- YouTube-8M: A Large-Scale Video Classification Benchmark
- Spatiotemporal Residual Networks for Video Action Recognition
- SlowFast Networks for Video Recognition
- Collaborative Spatio-temporal Feature Learning for Video Action Recognition