File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Clothing co-parsing by joint image segmentation and labeling

TitleClothing co-parsing by joint image segmentation and labeling
Authors
KeywordsClothing Recognition
EM Algorithm
Image Understand
Human Parsing
Issue Date2014
Citation
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2014, p. 3182-3189 How to Cite?
Abstract© 2014 IEEE. This paper aims at developing an integrated system of clothing co-parsing, in order to jointly parse a set of clothing images (unsegmented but annotated with tags) into semantic configurations. We propose a data-driven framework consisting of two phases of inference. The first phase, referred as 'image co-segmentation', iterates to extract consistent regions on images and jointly refines the regions over all images by employing the exemplar-SVM (ESVM) technique [23]. In the second phase (i.e. 'region colabeling'), we construct a multi-image graphical model by taking the segmented regions as vertices, and incorporate several contexts of clothing configuration (e.g., item location and mutual interactions). The joint label assignment can be solved using the efficient Graph Cuts algorithm. In addition to evaluate our framework on the Fashionista dataset [30], we construct a dataset called CCP consisting of 2098 high-resolution street fashion photos to demonstrate the performance of our system. We achieve 90.29% / 88.23% segmentation accuracy and 65.52% / 63.89% recognition rate on the Fashionista and the CCP datasets, respectively, which are superior compared with state-of-the-art methods.
Persistent Identifierhttp://hdl.handle.net/10722/273701
ISSN
2023 SCImago Journal Rankings: 10.331
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorYang, Wei-
dc.contributor.authorLuo, Ping-
dc.contributor.authorLin, Liang-
dc.date.accessioned2019-08-12T09:56:24Z-
dc.date.available2019-08-12T09:56:24Z-
dc.date.issued2014-
dc.identifier.citationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2014, p. 3182-3189-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/10722/273701-
dc.description.abstract© 2014 IEEE. This paper aims at developing an integrated system of clothing co-parsing, in order to jointly parse a set of clothing images (unsegmented but annotated with tags) into semantic configurations. We propose a data-driven framework consisting of two phases of inference. The first phase, referred as 'image co-segmentation', iterates to extract consistent regions on images and jointly refines the regions over all images by employing the exemplar-SVM (ESVM) technique [23]. In the second phase (i.e. 'region colabeling'), we construct a multi-image graphical model by taking the segmented regions as vertices, and incorporate several contexts of clothing configuration (e.g., item location and mutual interactions). The joint label assignment can be solved using the efficient Graph Cuts algorithm. In addition to evaluate our framework on the Fashionista dataset [30], we construct a dataset called CCP consisting of 2098 high-resolution street fashion photos to demonstrate the performance of our system. We achieve 90.29% / 88.23% segmentation accuracy and 65.52% / 63.89% recognition rate on the Fashionista and the CCP datasets, respectively, which are superior compared with state-of-the-art methods.-
dc.languageeng-
dc.relation.ispartofProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition-
dc.subjectClothing Recognition-
dc.subjectEM Algorithm-
dc.subjectImage Understand-
dc.subjectHuman Parsing-
dc.titleClothing co-parsing by joint image segmentation and labeling-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/CVPR.2014.407-
dc.identifier.scopuseid_2-s2.0-84911408100-
dc.identifier.spage3182-
dc.identifier.epage3189-
dc.identifier.isiWOS:000361555603031-
dc.identifier.issnl1063-6919-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats