?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Modeling+Object+Appearance+using+Context-Conditioned+Component+Analysis&rft.creator=Turmukhambetov%2C+D&rft.creator=Campbell%2C+NDF&rft.creator=Prince%2C+SJD&rft.creator=Kautz%2C+J&rft.description=Subspace+models+have+been+very+successful+at+modeling%0D%0Athe+appearance+of+structured+image+datasets+when+the+visual+objects+have+been+aligned+in+the+images+(e.g.%2C+faces).%0D%0AEven+with+extensions+that+allow+for+global+transformations+or+dense+warps+of+the+image%2C+the+set+of+visual+objects+whose+appearance+may+be+modeled+by+such+methods+is+limited.%0D%0AThey+are+unable+to+account+for+visual+objects+where+occlusion+leads+to+changing+visibility+of+different+object+parts+(without+a+strict+layered+structure)+and+where+a+one-toone+mapping+between+parts+is+not+preserved.+For+example+bunches+of+bananas+contain+different+numbers+of+bananas+but+each+individual+banana+shares+an+appearance+subspace.%0D%0AIn+this+work+we+remove+the+image+space+alignment+limitations+of+existing+subspace+models+by+conditioning+the+models+on+a+shape+dependent+context+that+allows+for+the+complex%2C+non-linear+structure+of+the+appearance+of+the+visual+object+to+be+captured+and+shared.+This+allows+us+to+exploit+the+advantages+of+subspace+appearance+models+with+non-rigid%2C+deformable+objects+whilst+also+dealing+with+complex+occlusions+and+varying+numbers+of+parts.+We+demonstrate+the+effectiveness+of+our+new+model+with+examples+of+structured+inpainting+and+appearance+transfer.&rft.subject=Visualization%2C+Mathematical+model%2C+Context%2C+Context+modeling%2C+Active+appearance+model%2C+Image+color+analysis%2C+Analytical+models&rft.publisher=IEEE&rft.date=2015-10-15&rft.type=Proceedings+paper&rft.language=eng&rft.source=+++++In%3A++Proceedings+of+Computer+Vision+and+Pattern+Recognition+(CVPR)%2C+2015+IEEE+Conference.++(pp.+pp.+4156-4164).++IEEE%3A+Boston%2C+MA%2C+USA.+(2015)+++++&rft.format=text&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F1468724%2F1%2F2198.pdf&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F1468724%2F&rft.rights=open