File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Fusing robust face region descriptors via multiple metric learning for face recognition in the wild

TitleFusing robust face region descriptors via multiple metric learning for face recognition in the wild
Authors
Issue Date2013
Citation
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2013, p. 3554-3561 How to Cite?
AbstractIn many real-world face recognition scenarios, face images can hardly be aligned accurately due to complex appearance variations or low-quality images. To address this issue, we propose a new approach to extract robust face region descriptors. Specifically, we divide each image (resp. video) into several spatial blocks (resp. spatial-temporal volumes) and then represent each block (resp. volume) by sum-pooling the nonnegative sparse codes of position-free patches sampled within the block (resp. volume). Whitened Principal Component Analysis (WPCA) is further utilized to reduce the feature dimension, which leads to our Spatial Face Region Descriptor (SFRD) (resp. Spatial-Temporal Face Region Descriptor, STFRD) for images (resp. videos). Moreover, we develop a new distance metric learning method for face verification called Pairwise-constrained Multiple Metric Learning (PMML) to effectively integrate the face region descriptors of all blocks (resp. volumes) from an image (resp. a video). Our work achieves the state-of-the-art performances on two real-world datasets LFW and YouTube Faces (YTF) according to the restricted protocol. © 2013 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/321536
ISSN
2023 SCImago Journal Rankings: 10.331
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorCui, Zhen-
dc.contributor.authorLi, Wen-
dc.contributor.authorXu, Dong-
dc.contributor.authorShan, Shiguang-
dc.contributor.authorChen, Xilin-
dc.date.accessioned2022-11-03T02:19:36Z-
dc.date.available2022-11-03T02:19:36Z-
dc.date.issued2013-
dc.identifier.citationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2013, p. 3554-3561-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/10722/321536-
dc.description.abstractIn many real-world face recognition scenarios, face images can hardly be aligned accurately due to complex appearance variations or low-quality images. To address this issue, we propose a new approach to extract robust face region descriptors. Specifically, we divide each image (resp. video) into several spatial blocks (resp. spatial-temporal volumes) and then represent each block (resp. volume) by sum-pooling the nonnegative sparse codes of position-free patches sampled within the block (resp. volume). Whitened Principal Component Analysis (WPCA) is further utilized to reduce the feature dimension, which leads to our Spatial Face Region Descriptor (SFRD) (resp. Spatial-Temporal Face Region Descriptor, STFRD) for images (resp. videos). Moreover, we develop a new distance metric learning method for face verification called Pairwise-constrained Multiple Metric Learning (PMML) to effectively integrate the face region descriptors of all blocks (resp. volumes) from an image (resp. a video). Our work achieves the state-of-the-art performances on two real-world datasets LFW and YouTube Faces (YTF) according to the restricted protocol. © 2013 IEEE.-
dc.languageeng-
dc.relation.ispartofProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition-
dc.titleFusing robust face region descriptors via multiple metric learning for face recognition in the wild-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/CVPR.2013.456-
dc.identifier.scopuseid_2-s2.0-84887338978-
dc.identifier.spage3554-
dc.identifier.epage3561-
dc.identifier.isiWOS:000331094303080-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats