Learnt quasi-transitive similarity for retrieval from large collections of faces

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

We are interested in identity-based retrieval of face sets from large unlabelled collections acquired in uncontrolled environments. Given a baseline algorithm for measuring the similarity of two face sets, the meta-algorithm introduced in this paper seeks to leverage the structure of the data corpus to make the best use of the available baseline. In particular, we show how partial transitivity of inter-personal similarity can be exploited to improve the retrieval of particularly challenging sets which poorly match the query under the baseline measure. We: (i) describe the use of proxy sets as a means of computing the similarity between two sets, (ii) introduce transitivity meta-features based on the similarity of salient modes of appearance variation between sets, (iii) show how quasi-transitivity can be learnt from such features without any labelling or manual intervention, and (iv) demonstrate the effectiveness of the proposed methodology through experiments on the notoriously challenging YouTube database.
Original languageEnglish
Title of host publicationProceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherIEEE Computer Society
Pages4883-4892
Number of pages10
ISBN (Electronic)9781467388511
DOIs
Publication statusPublished - 26 Jun 2016
EventIEEE Conference on Computer Vision and Pattern Recognition - Caesar's Palace, Las Vegas, United States
Duration: 26 Jun 20161 Jul 2016
Conference number: 29
http://cvpr2016.thecvf.com/

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition
PublisherIEEE
ISSN (Print)1063-6919
ISSN (Electronic)2575-7075

Conference

ConferenceIEEE Conference on Computer Vision and Pattern Recognition
Abbreviated titleCVPR
Country/TerritoryUnited States
CityLas Vegas
Period26/06/161/07/16
Internet address

Fingerprint

Dive into the research topics of 'Learnt quasi-transitive similarity for retrieval from large collections of faces'. Together they form a unique fingerprint.

Cite this