Person spotting: video shot retrieval for face sets

<p>Matching people based on their imaged face is hard because of the well known problems of illumination, pose, size and expression variation. Indeed these variations can exceed those due to identity. Fortunately, videos of people have the happy benefit of containing multiple exemplars of each...

Full description

Bibliographic Details
Main Authors: Sivic, J, Everingham, M, Zisserman, A
Format: Conference item
Language:English
Published: Springer 2007
_version_ 1826317231854714880
author Sivic, J
Everingham, M
Zisserman, A
author_facet Sivic, J
Everingham, M
Zisserman, A
author_sort Sivic, J
collection OXFORD
description <p>Matching people based on their imaged face is hard because of the well known problems of illumination, pose, size and expression variation. Indeed these variations can exceed those due to identity. Fortunately, videos of people have the happy benefit of containing multiple exemplars of each person in a form that can easily be associated automatically using straightforward visual tracking. We describe progress in harnessing these multiple exemplars in order to retrieve humans automatically in videos, given a query face in a shot. There are three areas of interest: (i) the matching of sets of exemplars provided by “tubes” of the spatial-temporal volume; (ii) the description of the face using a spatial orientation field; and, (iii) the structuring of the problem so that retrieval is immediate at run time.</p> <br> <p>The result is a person retrieval system, able to retrieve a ranked list of shots containing a particular person in the manner of Google. The method has been implemented and tested on two feature length movies.</p>
first_indexed 2025-02-19T04:36:44Z
format Conference item
id oxford-uuid:b1aa113d-c141-4c2f-a652-ad6dcb8c84e8
institution University of Oxford
language English
last_indexed 2025-02-19T04:36:44Z
publishDate 2007
publisher Springer
record_format dspace
spelling oxford-uuid:b1aa113d-c141-4c2f-a652-ad6dcb8c84e82025-01-31T15:19:44ZPerson spotting: video shot retrieval for face setsConference itemhttp://purl.org/coar/resource_type/c_5794uuid:b1aa113d-c141-4c2f-a652-ad6dcb8c84e8EnglishSymplectic ElementsSpringer2007Sivic, JEveringham, MZisserman, A<p>Matching people based on their imaged face is hard because of the well known problems of illumination, pose, size and expression variation. Indeed these variations can exceed those due to identity. Fortunately, videos of people have the happy benefit of containing multiple exemplars of each person in a form that can easily be associated automatically using straightforward visual tracking. We describe progress in harnessing these multiple exemplars in order to retrieve humans automatically in videos, given a query face in a shot. There are three areas of interest: (i) the matching of sets of exemplars provided by “tubes” of the spatial-temporal volume; (ii) the description of the face using a spatial orientation field; and, (iii) the structuring of the problem so that retrieval is immediate at run time.</p> <br> <p>The result is a person retrieval system, able to retrieve a ranked list of shots containing a particular person in the manner of Google. The method has been implemented and tested on two feature length movies.</p>
spellingShingle Sivic, J
Everingham, M
Zisserman, A
Person spotting: video shot retrieval for face sets
title Person spotting: video shot retrieval for face sets
title_full Person spotting: video shot retrieval for face sets
title_fullStr Person spotting: video shot retrieval for face sets
title_full_unstemmed Person spotting: video shot retrieval for face sets
title_short Person spotting: video shot retrieval for face sets
title_sort person spotting video shot retrieval for face sets
work_keys_str_mv AT sivicj personspottingvideoshotretrievalforfacesets
AT everinghamm personspottingvideoshotretrievalforfacesets
AT zissermana personspottingvideoshotretrievalforfacesets