An Enhanced Deep Feature Representation for Person Re-Identification

Shangxuan Wu, Ying-Cong Chen, Xiang Li, Ancong Wu, Jinjie You, Wei-Shi Zheng

WACV 2016 pp. 1-8

doi:10.1109/WACV.2016.7477681 /wacv/2016/wu2016wacv-enhanced/

Abstract

Feature representation and metric learning are two critical components in person re-identification models. In this paper, we focus on the feature representation and claim that hand-crafted histogram features can be complementary to Convolutional Neural Network (CNN) features. We propose a novel feature extraction model called Feature Fusion Net (FFN) for pedestrian image representation. In FFN, back propagation makes CNN features constrained by the handcrafted features. Utilizing color histogram features (RGB, HSV, YCbCr, Lab and YIQ) and texture features (multi-scale and multi-orientation Gabor features), we get a new deep feature representation that is more discriminative and compact. Experiments on three challenging datasets (VIPeR, CUHK01, PRID450s) validates the effectiveness of our proposal.

PDF WACV Semantic Scholar

Cite

Text

Wu et al. "An Enhanced Deep Feature Representation for Person Re-Identification." IEEE/CVF Winter Conference on Applications of Computer Vision, 2016. doi:10.1109/WACV.2016.7477681

Markdown

[Wu et al. "An Enhanced Deep Feature Representation for Person Re-Identification." IEEE/CVF Winter Conference on Applications of Computer Vision, 2016.](https://mlanthology.org/wacv/2016/wu2016wacv-enhanced/) doi:10.1109/WACV.2016.7477681

BibTeX

@inproceedings{wu2016wacv-enhanced,
  title     = {{An Enhanced Deep Feature Representation for Person Re-Identification}},
  author    = {Wu, Shangxuan and Chen, Ying-Cong and Li, Xiang and Wu, Ancong and You, Jinjie and Zheng, Wei-Shi},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
  year      = {2016},
  pages     = {1-8},
  doi       = {10.1109/WACV.2016.7477681},
  url       = {https://mlanthology.org/wacv/2016/wu2016wacv-enhanced/}
}