Fisher vector encoded deep convolutional features for unconstrained face verification
Lists
Only you see this
Abstract
We present a method to combine the Fisher vector representation and the Deep Convolutional Neural Network (DCNN) features to generate a rerpesentation, called the Fisher vector encoded DCNN (FV-DCNN) features, for unconstrained face verification. One of the key features of our method is that spatial and appearance information are simultaneously processed when learning the Gaussian mixture model to encode the DCNN features. Evaluations on two challenging verification datasets show that the proposed FV-DCNN method is able to capture the salient local features and also performs well when compared to many state-of-the-art face verification methods.
BibTeX
@inproceedings{chen2016fisher,
author = {Jun-Cheng Chen and Jingxiao Zheng and Vishal M. Patel and Rama Chellappa},
title = {{Fisher vector encoded deep convolutional features for unconstrained face verification}},
booktitle = {ICIP},
year = {2016},
doi = {10.1109/icip.2016.7532906},
}Loading related content...