In Still-to-Video (S2V) face recognition, only a few high resolution images are registered for each subject, while the probe is video clips of complex variations. As faces present distinct characteristics under different scenarios, recognition in the original space is obviously inefficient. Thus, in this paper, we propose a novel discriminant analysis method to learn separate mappings for different scenario patterns (still, video), and further pursue a common discriminant space based on these mappings. Concretely, by modeling each video as a manifold and each image as point data, we form the scenario-oriented mapping learning as a Point-Manifold Discriminant Analysis (PMDA) framework. The learning objective is formulated by incorporating the intra-class compactness and inter-class separability for good discrimination. Experiments on the COX-S2V dataset demonstrate the effectiveness of the proposed method.
Xue CHEN
Chinese Academy of Sciences
Chunheng WANG
Chinese Academy of Sciences
Baihua XIAO
Chinese Academy of Sciences
Yunxue SHAO
Chinese Academy of Sciences
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Xue CHEN, Chunheng WANG, Baihua XIAO, Yunxue SHAO, "Point-Manifold Discriminant Analysis for Still-to-Video Face Recognition" in IEICE TRANSACTIONS on Information,
vol. E97-D, no. 10, pp. 2780-2789, October 2014, doi: 10.1587/transinf.2014EDP7057.
Abstract: In Still-to-Video (S2V) face recognition, only a few high resolution images are registered for each subject, while the probe is video clips of complex variations. As faces present distinct characteristics under different scenarios, recognition in the original space is obviously inefficient. Thus, in this paper, we propose a novel discriminant analysis method to learn separate mappings for different scenario patterns (still, video), and further pursue a common discriminant space based on these mappings. Concretely, by modeling each video as a manifold and each image as point data, we form the scenario-oriented mapping learning as a Point-Manifold Discriminant Analysis (PMDA) framework. The learning objective is formulated by incorporating the intra-class compactness and inter-class separability for good discrimination. Experiments on the COX-S2V dataset demonstrate the effectiveness of the proposed method.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2014EDP7057/_p
Copy
@ARTICLE{e97-d_10_2780,
author={Xue CHEN, Chunheng WANG, Baihua XIAO, Yunxue SHAO, },
journal={IEICE TRANSACTIONS on Information},
title={Point-Manifold Discriminant Analysis for Still-to-Video Face Recognition},
year={2014},
volume={E97-D},
number={10},
pages={2780-2789},
abstract={In Still-to-Video (S2V) face recognition, only a few high resolution images are registered for each subject, while the probe is video clips of complex variations. As faces present distinct characteristics under different scenarios, recognition in the original space is obviously inefficient. Thus, in this paper, we propose a novel discriminant analysis method to learn separate mappings for different scenario patterns (still, video), and further pursue a common discriminant space based on these mappings. Concretely, by modeling each video as a manifold and each image as point data, we form the scenario-oriented mapping learning as a Point-Manifold Discriminant Analysis (PMDA) framework. The learning objective is formulated by incorporating the intra-class compactness and inter-class separability for good discrimination. Experiments on the COX-S2V dataset demonstrate the effectiveness of the proposed method.},
keywords={},
doi={10.1587/transinf.2014EDP7057},
ISSN={1745-1361},
month={October},}
Copy
TY - JOUR
TI - Point-Manifold Discriminant Analysis for Still-to-Video Face Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 2780
EP - 2789
AU - Xue CHEN
AU - Chunheng WANG
AU - Baihua XIAO
AU - Yunxue SHAO
PY - 2014
DO - 10.1587/transinf.2014EDP7057
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2014
AB - In Still-to-Video (S2V) face recognition, only a few high resolution images are registered for each subject, while the probe is video clips of complex variations. As faces present distinct characteristics under different scenarios, recognition in the original space is obviously inefficient. Thus, in this paper, we propose a novel discriminant analysis method to learn separate mappings for different scenario patterns (still, video), and further pursue a common discriminant space based on these mappings. Concretely, by modeling each video as a manifold and each image as point data, we form the scenario-oriented mapping learning as a Point-Manifold Discriminant Analysis (PMDA) framework. The learning objective is formulated by incorporating the intra-class compactness and inter-class separability for good discrimination. Experiments on the COX-S2V dataset demonstrate the effectiveness of the proposed method.
ER -