File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Hierarchical face parsing via deep learning

TitleHierarchical face parsing via deep learning
Authors
Issue Date2012
Citation
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2012, p. 2480-2487 How to Cite?
AbstractThis paper investigates how to parse (segment) facial components from face images which may be partially occluded. We propose a novel face parser, which recasts segmentation of face components as a cross-modality data transformation problem, i.e., transforming an image patch to a label map. Specifically, a face is represented hierarchically by parts, components, and pixel-wise labels. With this representation, our approach first detects faces at both the part- and component-levels, and then computes the pixel-wise label maps (Fig.1). Our part-based and component-based detectors are generatively trained with the deep belief network (DBN), and are discriminatively tuned by logistic regression. The segmentators transform the detected face components to label maps, which are obtained by learning a highly nonlinear mapping with the deep autoencoder. The proposed hierarchical face parsing is not only robust to partial occlusions but also provide richer information for face analysis and face synthesis compared with face keypoint detection and face alignment. The effectiveness of our algorithm is shown through several tasks on 2, 239 images selected from three datasets (e.g., LFW [12], BioID [13] and CUFSF [29]). © 2012 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/273518
ISSN

 

DC FieldValueLanguage
dc.contributor.authorLuo, Ping-
dc.contributor.authorWang, Xiaogang-
dc.contributor.authorTang, Xiaoou-
dc.date.accessioned2019-08-12T09:55:49Z-
dc.date.available2019-08-12T09:55:49Z-
dc.date.issued2012-
dc.identifier.citationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2012, p. 2480-2487-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/10722/273518-
dc.description.abstractThis paper investigates how to parse (segment) facial components from face images which may be partially occluded. We propose a novel face parser, which recasts segmentation of face components as a cross-modality data transformation problem, i.e., transforming an image patch to a label map. Specifically, a face is represented hierarchically by parts, components, and pixel-wise labels. With this representation, our approach first detects faces at both the part- and component-levels, and then computes the pixel-wise label maps (Fig.1). Our part-based and component-based detectors are generatively trained with the deep belief network (DBN), and are discriminatively tuned by logistic regression. The segmentators transform the detected face components to label maps, which are obtained by learning a highly nonlinear mapping with the deep autoencoder. The proposed hierarchical face parsing is not only robust to partial occlusions but also provide richer information for face analysis and face synthesis compared with face keypoint detection and face alignment. The effectiveness of our algorithm is shown through several tasks on 2, 239 images selected from three datasets (e.g., LFW [12], BioID [13] and CUFSF [29]). © 2012 IEEE.-
dc.languageeng-
dc.relation.ispartofProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition-
dc.titleHierarchical face parsing via deep learning-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/CVPR.2012.6247963-
dc.identifier.scopuseid_2-s2.0-84866665255-
dc.identifier.spage2480-
dc.identifier.epage2487-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats