An End-to-End System for Unconstrained Face Verification with Deep Convolutional Neural Networks
Abstract
In this paper, we present an end-to-end system for the unconstrained face verification problem based on deep convolutional neural networks (DCNN). The end-to-end system consists of three modules for face detection, alignment and verification and is evaluated using the newly released IARPA Janus Benchmark A (IJB-A) dataset and its extended version Janus Challenging set 2 (JANUS CS2) dataset. The IJB-A and CS2 datasets include real-world unconstrained faces of 500 subjects with significant pose and illumination variations which are much harder than the Labeled Faces in the Wild (LFW) and Youtube Face (YTF) datasets. Results of experimental evaluations for the proposed system on the IJB-A dataset are provided.
Cite
Text
Chen et al. "An End-to-End System for Unconstrained Face Verification with Deep Convolutional Neural Networks." IEEE/CVF International Conference on Computer Vision Workshops, 2015. doi:10.1109/ICCVW.2015.55Markdown
[Chen et al. "An End-to-End System for Unconstrained Face Verification with Deep Convolutional Neural Networks." IEEE/CVF International Conference on Computer Vision Workshops, 2015.](https://mlanthology.org/iccvw/2015/chen2015iccvw-endtoend/) doi:10.1109/ICCVW.2015.55BibTeX
@inproceedings{chen2015iccvw-endtoend,
title = {{An End-to-End System for Unconstrained Face Verification with Deep Convolutional Neural Networks}},
author = {Chen, Jun-Cheng and Ranjan, Rajeev and Kumar, Amit and Chen, Ching-Hui and Patel, Vishal M. and Chellappa, Rama},
booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
year = {2015},
pages = {360-368},
doi = {10.1109/ICCVW.2015.55},
url = {https://mlanthology.org/iccvw/2015/chen2015iccvw-endtoend/}
}