Experts-Shift: Learning active spatial classification experts for keyframe-based video segmentation

Experts-Shift is a novel statistical framework for keyframe-based video segmentation. Compared to existing video segmentation techniques with simple color models, our method proposes a probability mixture model coupling strong image classifiers (experts) with latent spatial configuration. In order t...

Full description

Saved in:
Bibliographic Details
Main Authors: Yibiao Zhao, Yanbiao Duan, Xiaohan Nie, Yaping Huang, Siwei Luo
Format: Conference Proceeding
Language:English
Subjects:
Computer vision
Image color analysis
Image segmentation
Joints
Pixel
Video sequences
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 627
container_issue
container_start_page 622
container_title
container_volume
creator Yibiao Zhao
Yanbiao Duan
Xiaohan Nie
Yaping Huang
Siwei Luo
description Experts-Shift is a novel statistical framework for keyframe-based video segmentation. Compared to existing video segmentation techniques with simple color models, our method proposes a probability mixture model coupling strong image classifiers (experts) with latent spatial configuration. In order to propagate image labels to the successive frames, our algorithm track all experts jointly by a efficient MCMC sampler with their relations modeled by MRFs. This algorithm is capable to handle overlapping color distribution, ambiguous image boundaries, large displacement in challenging scenario with a solid foundation of both generative modeling and discriminative learning. Experiment shows our algorithm achieves high quality results and need less supervision than previous work.
doi_str_mv 10.1109/WACV.2011.5711562
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_5711562</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5711562</ieee_id><sourcerecordid>5711562</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-66b428f1284bf2d6b3151072e840582b949652e5f0d59474088292258f6fd1b3</originalsourceid><addsrcrecordid>eNpFUMlqwzAUVDdokvYDSi_6AaV6z5Is9RZCukCgh5T2GGT7KVWb2MYyIfn7Lgn0NAyzwAxjNyDHANLdvU-mb2OUAGOdA2iDJ2wICpVyyml7ygZoFAqXWTj7F4w5ZwPQWgqdO3nJhil9Spk5cNmAlbNdS12fxOIjhv6ez8l3daxX3Jd93BJPre-jX_Ny7VOKIZY_tKk5HVI8NB3_on3o_IZE4RNVfBsranii1Ybq_s99xS6CXye6PuKILR5mr9MnMX95fJ5O5iI62QtjCoU2AFpVBKxMkYEGmSNZJbXF4neJRtJBVtqpXElr0SFqG0yooMhG7PbQGolo2XZx47v98vhT9g1uSli5</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Experts-Shift: Learning active spatial classification experts for keyframe-based video segmentation</title><source>IEEE Xplore All Conference Series</source><creator>Yibiao Zhao ; Yanbiao Duan ; Xiaohan Nie ; Yaping Huang ; Siwei Luo</creator><creatorcontrib>Yibiao Zhao ; Yanbiao Duan ; Xiaohan Nie ; Yaping Huang ; Siwei Luo</creatorcontrib><description>Experts-Shift is a novel statistical framework for keyframe-based video segmentation. Compared to existing video segmentation techniques with simple color models, our method proposes a probability mixture model coupling strong image classifiers (experts) with latent spatial configuration. In order to propagate image labels to the successive frames, our algorithm track all experts jointly by a efficient MCMC sampler with their relations modeled by MRFs. This algorithm is capable to handle overlapping color distribution, ambiguous image boundaries, large displacement in challenging scenario with a solid foundation of both generative modeling and discriminative learning. Experiment shows our algorithm achieves high quality results and need less supervision than previous work.</description><identifier>ISSN: 1550-5790</identifier><identifier>ISBN: 1424494966</identifier><identifier>ISBN: 9781424494965</identifier><identifier>EISSN: 2642-9381</identifier><identifier>EISBN: 1424494958</identifier><identifier>EISBN: 9781424494958</identifier><identifier>EISBN: 9781424494972</identifier><identifier>EISBN: 1424494974</identifier><identifier>DOI: 10.1109/WACV.2011.5711562</identifier><language>eng</language><publisher>IEEE</publisher><subject>Computer vision ; Image color analysis ; Image segmentation ; Joints ; Pixel ; Video sequences</subject><ispartof>2011 IEEE Workshop on Applications of Computer Vision (WACV), 2011, p.622-627</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/5711562$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54555,54920,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5711562$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Yibiao Zhao</creatorcontrib><creatorcontrib>Yanbiao Duan</creatorcontrib><creatorcontrib>Xiaohan Nie</creatorcontrib><creatorcontrib>Yaping Huang</creatorcontrib><creatorcontrib>Siwei Luo</creatorcontrib><title>Experts-Shift: Learning active spatial classification experts for keyframe-based video segmentation</title><title>2011 IEEE Workshop on Applications of Computer Vision (WACV)</title><addtitle>WACV</addtitle><description>Experts-Shift is a novel statistical framework for keyframe-based video segmentation. Compared to existing video segmentation techniques with simple color models, our method proposes a probability mixture model coupling strong image classifiers (experts) with latent spatial configuration. In order to propagate image labels to the successive frames, our algorithm track all experts jointly by a efficient MCMC sampler with their relations modeled by MRFs. This algorithm is capable to handle overlapping color distribution, ambiguous image boundaries, large displacement in challenging scenario with a solid foundation of both generative modeling and discriminative learning. Experiment shows our algorithm achieves high quality results and need less supervision than previous work.</description><subject>Computer vision</subject><subject>Image color analysis</subject><subject>Image segmentation</subject><subject>Joints</subject><subject>Pixel</subject><subject>Video sequences</subject><issn>1550-5790</issn><issn>2642-9381</issn><isbn>1424494966</isbn><isbn>9781424494965</isbn><isbn>1424494958</isbn><isbn>9781424494958</isbn><isbn>9781424494972</isbn><isbn>1424494974</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2011</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNpFUMlqwzAUVDdokvYDSi_6AaV6z5Is9RZCukCgh5T2GGT7KVWb2MYyIfn7Lgn0NAyzwAxjNyDHANLdvU-mb2OUAGOdA2iDJ2wICpVyyml7ygZoFAqXWTj7F4w5ZwPQWgqdO3nJhil9Spk5cNmAlbNdS12fxOIjhv6ez8l3daxX3Jd93BJPre-jX_Ny7VOKIZY_tKk5HVI8NB3_on3o_IZE4RNVfBsranii1Ybq_s99xS6CXye6PuKILR5mr9MnMX95fJ5O5iI62QtjCoU2AFpVBKxMkYEGmSNZJbXF4neJRtJBVtqpXElr0SFqG0yooMhG7PbQGolo2XZx47v98vhT9g1uSli5</recordid><startdate>201101</startdate><enddate>201101</enddate><creator>Yibiao Zhao</creator><creator>Yanbiao Duan</creator><creator>Xiaohan Nie</creator><creator>Yaping Huang</creator><creator>Siwei Luo</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201101</creationdate><title>Experts-Shift: Learning active spatial classification experts for keyframe-based video segmentation</title><author>Yibiao Zhao ; Yanbiao Duan ; Xiaohan Nie ; Yaping Huang ; Siwei Luo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-66b428f1284bf2d6b3151072e840582b949652e5f0d59474088292258f6fd1b3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Computer vision</topic><topic>Image color analysis</topic><topic>Image segmentation</topic><topic>Joints</topic><topic>Pixel</topic><topic>Video sequences</topic><toplevel>online_resources</toplevel><creatorcontrib>Yibiao Zhao</creatorcontrib><creatorcontrib>Yanbiao Duan</creatorcontrib><creatorcontrib>Xiaohan Nie</creatorcontrib><creatorcontrib>Yaping Huang</creatorcontrib><creatorcontrib>Siwei Luo</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Yibiao Zhao</au><au>Yanbiao Duan</au><au>Xiaohan Nie</au><au>Yaping Huang</au><au>Siwei Luo</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Experts-Shift: Learning active spatial classification experts for keyframe-based video segmentation</atitle><btitle>2011 IEEE Workshop on Applications of Computer Vision (WACV)</btitle><stitle>WACV</stitle><date>2011-01</date><risdate>2011</risdate><spage>622</spage><epage>627</epage><pages>622-627</pages><issn>1550-5790</issn><eissn>2642-9381</eissn><isbn>1424494966</isbn><isbn>9781424494965</isbn><eisbn>1424494958</eisbn><eisbn>9781424494958</eisbn><eisbn>9781424494972</eisbn><eisbn>1424494974</eisbn><abstract>Experts-Shift is a novel statistical framework for keyframe-based video segmentation. Compared to existing video segmentation techniques with simple color models, our method proposes a probability mixture model coupling strong image classifiers (experts) with latent spatial configuration. In order to propagate image labels to the successive frames, our algorithm track all experts jointly by a efficient MCMC sampler with their relations modeled by MRFs. This algorithm is capable to handle overlapping color distribution, ambiguous image boundaries, large displacement in challenging scenario with a solid foundation of both generative modeling and discriminative learning. Experiment shows our algorithm achieves high quality results and need less supervision than previous work.</abstract><pub>IEEE</pub><doi>10.1109/WACV.2011.5711562</doi><tpages>6</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1550-5790
ispartof 2011 IEEE Workshop on Applications of Computer Vision (WACV), 2011, p.622-627
issn 1550-5790
2642-9381
language eng
recordid cdi_ieee_primary_5711562
source IEEE Xplore All Conference Series
subjects Computer vision
Image color analysis
Image segmentation
Joints
Pixel
Video sequences
title Experts-Shift: Learning active spatial classification experts for keyframe-based video segmentation
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T16%3A43%3A50IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Experts-Shift:%20Learning%20active%20spatial%20classification%20experts%20for%20keyframe-based%20video%20segmentation&rft.btitle=2011%20IEEE%20Workshop%20on%20Applications%20of%20Computer%20Vision%20(WACV)&rft.au=Yibiao%20Zhao&rft.date=2011-01&rft.spage=622&rft.epage=627&rft.pages=622-627&rft.issn=1550-5790&rft.eissn=2642-9381&rft.isbn=1424494966&rft.isbn_list=9781424494965&rft_id=info:doi/10.1109/WACV.2011.5711562&rft.eisbn=1424494958&rft.eisbn_list=9781424494958&rft.eisbn_list=9781424494972&rft.eisbn_list=1424494974&rft_dat=%3Cieee_CHZPO%3E5711562%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i90t-66b428f1284bf2d6b3151072e840582b949652e5f0d59474088292258f6fd1b3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5711562&rfr_iscdi=true