Pose-Aware Person Recognition

Vijay Kumar, Anoop Namboodiri, Manohar Paluri, C. V. Jawahar; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 6223-6232

Abstract


Person recognition methods that use multiple body regions have shown significant improvements over traditional face-based recognition. One of the primary challenges in full-body person recognition is the extreme variation in pose and view point. In this work, (i) we present an approach that tackles pose variations utilizing multiple models that are trained on specific poses, and combined using pose-aware weights during testing. (ii) For learning a person representation, we propose a network that jointly optimizes a single loss over multiple body regions. (iii) Finally, we introduce new benchmarks to evaluate person recognition in diverse scenarios and show significant improvements over previously proposed approaches on all the benchmarks including the photo album setting of PIPA.

Related Material


[pdf] [Supp] [arXiv]
[bibtex]
@InProceedings{Kumar_2017_CVPR,
author = {Kumar, Vijay and Namboodiri, Anoop and Paluri, Manohar and Jawahar, C. V.},
title = {Pose-Aware Person Recognition},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {July},
year = {2017}
}