Learning to track: conceptual manifold map for closed-form tracking

Our objective is to model the visual manifold of object appearance corresponding to geometric transformation. We learn a generative model for object appearance where the appearance of the object at each new frame is a function that maps from a conceptual representation of the geometric transformatio...

Full description

Saved in:
Bibliographic Details
Published in2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) Vol. 1; pp. 724 - 730 vol. 1
Main Author Elgammal, A.
Format Conference Proceeding
LanguageEnglish
Published IEEE 2005
Subjects
Application software
Computer science
Computer vision
Human robot interaction
Layout
Lighting
Medical robotics
Search problems
Solid modeling
Tracking
Online AccessGet full text
ISBN0769523722
9780769523729
ISSN1063-6919
1063-6919
DOI10.1109/CVPR.2005.209

Cover

Abstract Our objective is to model the visual manifold of object appearance corresponding to geometric transformation. We learn a generative model for object appearance where the appearance of the object at each new frame is a function that maps from a conceptual representation of the geometric transformation space into the visual manifold. By learning such generative model we can infer the geometric transformation (track) directly from the tracked object appearance. As a result tracking can be achieved in a closed form and therefore can be done very efficiently.
AbstractList Our objective is to model the visual manifold of object appearance corresponding to geometric transformation. We learn a generative model for object appearance where the appearance of the object at each new frame is a function that maps from a conceptual representation of the geometric transformation space into the visual manifold. By learning such generative model we can infer the geometric transformation (track) directly from the tracked object appearance. As a result tracking can be achieved in a closed form and therefore can be done very efficiently.
Author Elgammal, A.
Author_xml – sequence: 1
  givenname: A.
  surname: Elgammal
  fullname: Elgammal, A.
  organization: Dept. of Comput. Sci., Rutgers Univ., Piscataway, NJ, USA
BookMark eNpNTktLw0AYXLSCbe3Rk5f9A2n3kX15k2BVCFREvZYv-5BoshuSePDfu1APzmFmYOb7mBVaxBQ9QteUbCklZle9P79sGSEikzlDS0okL6Sh5hytiJJGMK4YW_wLLtFmmj5JBjdcl2yJqtrDGNv4geeE5xHs1y22KVo_zN_Q4R5iG1LnshlwSCO2XZq8K7LtT_V8eoUuAnST3_zpGr3t71-rx6I-PDxVd3XRUiXmwlIwTeMa7VzQEKRVRoER3FrpAjSB6EbToANTQMDl-YJoxYLXSlivfOBrdHP623rvj8PY9jD-HGkpFS8J_wVqVk7t
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR.2005.209
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Computer Science
EISSN 1063-6919
EndPage 730 vol. 1
ExternalDocumentID 1467340
Genre orig-research
GroupedDBID 23M
29F
29O
6IE
6IH
6IK
ABDPE
ACGFS
ALMA_UNASSIGNED_HOLDINGS
CBEJK
IPLJI
M43
RIE
RIO
RNS
ID FETCH-LOGICAL-i175t-c1a9bbdb8ddf8af6c797a953cc6dfabf08b81f8f27a0ad69550872fe875ce7ef3
IEDL.DBID RIE
ISBN 0769523722
9780769523729
ISSN 1063-6919
IngestDate Wed Aug 27 02:18:22 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i175t-c1a9bbdb8ddf8af6c797a953cc6dfabf08b81f8f27a0ad69550872fe875ce7ef3
ParticipantIDs ieee_primary_1467340
PublicationCentury 2000
PublicationDate 20050000
PublicationDateYYYYMMDD 2005-01-01
PublicationDate_xml – year: 2005
  text: 20050000
PublicationDecade 2000
PublicationTitle 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
PublicationTitleAbbrev CVPR
PublicationYear 2005
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0000393842
ssj0023720
ssj0003211698
Score 1.6456035
Snippet Our objective is to model the visual manifold of object appearance corresponding to geometric transformation. We learn a generative model for object appearance...
SourceID ieee
SourceType Publisher
StartPage 724
SubjectTerms Application software
Computer science
Computer vision
Human robot interaction
Layout
Lighting
Medical robotics
Search problems
Solid modeling
Tracking
Title Learning to track: conceptual manifold map for closed-form tracking
URI https://ieeexplore.ieee.org/document/1467340
Volume 1
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LTwIxEG6QkydUML7Tg0cL7Lv1SiTEBEOMGG6kT2MgLIHdi7_emX1hjAdv7exusm22O9837XxDyH2oVTw01sO_n2QhIAQmpKcZiruBx1HKN5g7PH2JJ_PweREtWuShyYWx1haHz2wfm8Vevkl1jqGyAa7qIASCfgTErczVauIpmGPKK5qH_QCYTSyaHQUfq7EUO59xwGLhiZLCiwgv-JUST90XBzHOweh99lqGXnw8tPijBEvhgcYdMq3fvTx4surnmerrr1-yjv8d3AnpHXL96KzxYqekZTdnpFOBU1ot_T2Y6voPta1LRpU46wfNUprtpF49Ul2mQeZyTVFZw6VrA40tBWxM9TrdW8MQJpe3w6M9Mh8_vY0mrCrKwD4BaWRMe1IoZRQ3xnHpYp2IRIoo0Do2Tio35Ip7jjs_kUNpYEIBASa-s8CLtE2sC85Je5Nu7AWhKEkqoyDiLrIhwGeRDGWYaOk8J6DBL0kXp2m5LXU3ltUMXf1tvibHhaxqER65Ie1sl9tbAAyZuiu-lG_MfreD
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LTwIxEG4IHvSECsa3PXi0wL5br0SCCoQYMNxIn8ZAWAK7F3-9031hjAdv09ndZNtsd76Z6XyD0L0vRdhV2rF_P058QAiEcUcSS-4GFkcIV9na4dE4HMz8l3kwr6GHqhZGa50dPtNtK2a5fBXL1IbKOnZXez446Adg9wMnr9aqIiq2ypQWjp4de-DbhKzKKbi2H0uW-ww9EjKH5U48C-wFt-DiKcdsT8fZ6b1P3vLgi2uPLf5owpLZoH4Djcq3z4-eLNtpItry6xex43-nd4xa-2o_PKns2Amq6fUpahTwFBebfweqsgNEqWuiXkHP-oGTGCdbLpePWOaFkClfYcutYeKVAmGDAR1juYp3WhELlPPb4dEWmvWfpr0BKdoykE_AGgmRDmdCKEGVMpSbUEYs4izwpAyV4cJ0qaCOocaNeJcrWFDAgJFrNHhGUkfaeGeovo7X-hxhS0rKAy-gJtA-AGgWdbkfSW4cw0CgF6hpl2mxyZk3FsUKXf6tvkOHg-louBg-j1-v0FFGspoFS65RPdmm-gbgQyJus6_mG5XWusw
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2005+IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition+%28CVPR%2705%29&rft.atitle=Learning+to+track%3A+conceptual+manifold+map+for+closed-form+tracking&rft.au=Elgammal%2C+A.&rft.date=2005-01-01&rft.pub=IEEE&rft.isbn=9780769523729&rft.issn=1063-6919&rft.eissn=1063-6919&rft.volume=1&rft.spage=724&rft.epage=730+vol.+1&rft_id=info:doi/10.1109%2FCVPR.2005.209&rft.externalDocID=1467340
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1063-6919&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1063-6919&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1063-6919&client=summon