Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions
Abstract
Deep convolutional neural networks (ConvNets) have been recently shown to attain state-of-the-art performance for action recognition on standard-resolution videos. However, less attention has been paid to recognition performance at extremely low resolutions (eLR) (e.g., 16 12 pixels). Reliable action recognition using eLR cameras would address privacy concerns in various application environments such as private homes, hospitals, nursing/rehabilitation facilities, etc. In this paper, we propose a semi-coupled, filter-sharing network that leverages highresolution (HR) videos during training in order to assist an eLR ConvNet. We also study methods for fusing spatial and temporal ConvNets customized for eLR videos in order to take advantage of appearance and motion information. Our method outperforms state-of-the-art methods at extremely low resolutions on IXMAS (93:7%) and HMDB (29:2%) datasets.
Cite
Text
Chen et al. "Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions." IEEE/CVF Winter Conference on Applications of Computer Vision, 2017. doi:10.1109/WACV.2017.23Markdown
[Chen et al. "Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions." IEEE/CVF Winter Conference on Applications of Computer Vision, 2017.](https://mlanthology.org/wacv/2017/chen2017wacv-semi/) doi:10.1109/WACV.2017.23BibTeX
@inproceedings{chen2017wacv-semi,
title = {{Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions}},
author = {Chen, Jiawei and Wu, Jonathan and Konrad, Janusz and Ishwar, Prakash},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
year = {2017},
pages = {139-147},
doi = {10.1109/WACV.2017.23},
url = {https://mlanthology.org/wacv/2017/chen2017wacv-semi/}
}