GSR-MAR: Global Super-Resolution for Person Multi-Attribute Recognition
Abstract
Person attribute recognition aims to predict attribute labels based on person's appearance usually captured from surveillance cameras. It is a challenging problem in computer vision due to poor imaging quality with complex background clutter and unconstrained viewing conditions from various angles and distances between person and surveillance cameras. In this paper, we address such a problem using an end-to-end network called Global Super-Resolution for Multi Attribute Recognition (GSR-MAR). GSR-MAR integrates a conversion process of low-resolution input images into high-resolution images and predicts person attributes from input images. Before performing the classification process, GSR-MAR not only converts low-resolution images to high-resolution images to recover details of image textures but also captures larger context information by using large separable convolutional layers. The experiment results on two popular benchmark datasets demonstrate the performance improvement and effectiveness of our GSR-MAR model over competing baselines.
Cite
Text
Siadari et al. "GSR-MAR: Global Super-Resolution for Person Multi-Attribute Recognition." IEEE/CVF International Conference on Computer Vision Workshops, 2019. doi:10.1109/ICCVW.2019.00140Markdown
[Siadari et al. "GSR-MAR: Global Super-Resolution for Person Multi-Attribute Recognition." IEEE/CVF International Conference on Computer Vision Workshops, 2019.](https://mlanthology.org/iccvw/2019/siadari2019iccvw-gsrmar/) doi:10.1109/ICCVW.2019.00140BibTeX
@inproceedings{siadari2019iccvw-gsrmar,
title = {{GSR-MAR: Global Super-Resolution for Person Multi-Attribute Recognition}},
author = {Siadari, Thomhert Suprapto and Han, Mikyong and Yoon, Hyunjin},
booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
year = {2019},
pages = {1098-1103},
doi = {10.1109/ICCVW.2019.00140},
url = {https://mlanthology.org/iccvw/2019/siadari2019iccvw-gsrmar/}
}