Unconstrained Face Verification Using Deep CNN Features
Abstract
In this paper, we present an algorithm for unconstrained face verification based on deep convolutional features and evaluate it on the newly released IARPA Janus Benchmark A (IJB-A) dataset as well as on the traditional Labeled Face in the Wild (LFW) dataset. The IJB-A dataset includes real-world unconstrained faces from 500 subjects with full pose and illumination variations which are much harder than the LFW and Youtube Face (YTF) datasets. The deep convolutional neural network (DCNN) is trained using the CASIA-WebFace dataset. Results of experimental evaluations on the IJB-A and the LFW datasets are provided.
Cite
Text
Chen et al. "Unconstrained Face Verification Using Deep CNN Features." IEEE/CVF Winter Conference on Applications of Computer Vision, 2016. doi:10.1109/WACV.2016.7477557Markdown
[Chen et al. "Unconstrained Face Verification Using Deep CNN Features." IEEE/CVF Winter Conference on Applications of Computer Vision, 2016.](https://mlanthology.org/wacv/2016/chen2016wacv-unconstrained/) doi:10.1109/WACV.2016.7477557BibTeX
@inproceedings{chen2016wacv-unconstrained,
title = {{Unconstrained Face Verification Using Deep CNN Features}},
author = {Chen, Jun-Cheng and Patel, Vishal M. and Chellappa, Rama},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
year = {2016},
pages = {1-9},
doi = {10.1109/WACV.2016.7477557},
url = {https://mlanthology.org/wacv/2016/chen2016wacv-unconstrained/}
}