A Coupled Hidden Conditional Random Field Model for Simultaneous Face Clustering and Naming in Videos

Handle URI:
http://hdl.handle.net/10754/623776
Title:
A Coupled Hidden Conditional Random Field Model for Simultaneous Face Clustering and Naming in Videos
Authors:
Zhang, Yifan ( 0000-0002-9190-3509 ) ; Tang, Zhiqiang; Wu, Baoyuan ( 0000-0003-2183-5990 ) ; Ji, Qiang; Lu, Hanqing
Abstract:
For face naming in TV series or movies, a typical way is using subtitles/script alignment to get the time stamps of the names, and tagging them to the faces. We study the problem of face naming in videos when subtitles are not available. To this end, we divide the problem into two tasks: face clustering which groups the faces depicting a certain person into a cluster, and name assignment which associates a name to each face. Each task is formulated as a structured prediction problem and modeled by a hidden conditional random field (HCRF) model. We argue that the two tasks are correlated problems whose outputs can provide prior knowledge of the target prediction for each other. The two HCRFs are coupled in a unified graphical model called coupled HCRF where the joint dependence of the cluster labels and face name association is naturally embedded in the correlation between the two HCRFs. We provide an effective algorithm to optimize the two HCRFs iteratively and the performance of the two tasks on real-world data set can be both improved.
KAUST Department:
King Abdullah University of Science and Technology
Citation:
Zhang Y, Tang Z, Wu B, Ji Q, Lu H (2016) A Coupled Hidden Conditional Random Field Model for Simultaneous Face Clustering and Naming in Videos. IEEE Transactions on Image Processing 25: 5780–5792. Available: http://dx.doi.org/10.1109/tip.2016.2601491.
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
IEEE Transactions on Image Processing
Issue Date:
18-Aug-2016
DOI:
10.1109/tip.2016.2601491
Type:
Article
ISSN:
1057-7149; 1941-0042
Sponsors:
This work was supported in part by the 863 Program under Grant 2014AA015100, in part by the National Natural Science Foundation of China under Grant 61332016, Grant 61572500, Grant 61379100, and in part by the DARPA PerSEAS Program under Grant HR0011-10-C-0112. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Nikolaos V. Boulgouris.
Additional Links:
http://ieeexplore.ieee.org/document/7547293/
Appears in Collections:
Articles

Full metadata record

DC FieldValue Language
dc.contributor.authorZhang, Yifanen
dc.contributor.authorTang, Zhiqiangen
dc.contributor.authorWu, Baoyuanen
dc.contributor.authorJi, Qiangen
dc.contributor.authorLu, Hanqingen
dc.date.accessioned2017-05-31T11:23:04Z-
dc.date.available2017-05-31T11:23:04Z-
dc.date.issued2016-08-18en
dc.identifier.citationZhang Y, Tang Z, Wu B, Ji Q, Lu H (2016) A Coupled Hidden Conditional Random Field Model for Simultaneous Face Clustering and Naming in Videos. IEEE Transactions on Image Processing 25: 5780–5792. Available: http://dx.doi.org/10.1109/tip.2016.2601491.en
dc.identifier.issn1057-7149en
dc.identifier.issn1941-0042en
dc.identifier.doi10.1109/tip.2016.2601491en
dc.identifier.urihttp://hdl.handle.net/10754/623776-
dc.description.abstractFor face naming in TV series or movies, a typical way is using subtitles/script alignment to get the time stamps of the names, and tagging them to the faces. We study the problem of face naming in videos when subtitles are not available. To this end, we divide the problem into two tasks: face clustering which groups the faces depicting a certain person into a cluster, and name assignment which associates a name to each face. Each task is formulated as a structured prediction problem and modeled by a hidden conditional random field (HCRF) model. We argue that the two tasks are correlated problems whose outputs can provide prior knowledge of the target prediction for each other. The two HCRFs are coupled in a unified graphical model called coupled HCRF where the joint dependence of the cluster labels and face name association is naturally embedded in the correlation between the two HCRFs. We provide an effective algorithm to optimize the two HCRFs iteratively and the performance of the two tasks on real-world data set can be both improved.en
dc.description.sponsorshipThis work was supported in part by the 863 Program under Grant 2014AA015100, in part by the National Natural Science Foundation of China under Grant 61332016, Grant 61572500, Grant 61379100, and in part by the DARPA PerSEAS Program under Grant HR0011-10-C-0112. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Nikolaos V. Boulgouris.en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.relation.urlhttp://ieeexplore.ieee.org/document/7547293/en
dc.subjectconditional random fielden
dc.subjectFace clusteringen
dc.subjectface namingen
dc.titleA Coupled Hidden Conditional Random Field Model for Simultaneous Face Clustering and Naming in Videosen
dc.typeArticleen
dc.contributor.departmentKing Abdullah University of Science and Technologyen
dc.identifier.journalIEEE Transactions on Image Processingen
dc.contributor.institutionNational Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, , , Chinaen
dc.contributor.institutionDepartment of Electrical, Computer and Systems Engineering, Rensselaer Polytechnic Institute, Troy, NY, 12180, , United Statesen
kaust.authorWu, Baoyuanen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.