Unsupervised people organization and its application on individual retrieval from videos

Pengyi Hao, Seiichiro Kamata

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

3 Citations (Scopus)

Abstract

In this paper, a method named histogram intersection metric learning from scene tracks is proposed for automatic organizing people in videos. We make the following contributions: (i) learning histogram intersection distance instead of Mahalanobis distance for widely used face features; (ii) learning the metric from scene tracks without manually labeling any examples, which enables learning across large variations in pose, expression, occlusion and illumination with small number of face pairs and can distinguish different people powerfully. We firstly test face identification, track clustering, and people organization on a long film, then individual retrieval based on people organization from a large video dataset is evaluated, demonstrating significantly increased search quality with respect to previous approaches on this area.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
Pages2001-2004
Number of pages4
Publication statusPublished - 2012
Event21st International Conference on Pattern Recognition, ICPR 2012 - Tsukuba
Duration: 2012 Nov 112012 Nov 15

Other

Other21st International Conference on Pattern Recognition, ICPR 2012
CityTsukuba
Period12/11/1112/11/15

Fingerprint

Labeling
Lighting

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Hao, P., & Kamata, S. (2012). Unsupervised people organization and its application on individual retrieval from videos. In Proceedings - International Conference on Pattern Recognition (pp. 2001-2004). [6460551]

Unsupervised people organization and its application on individual retrieval from videos. / Hao, Pengyi; Kamata, Seiichiro.

Proceedings - International Conference on Pattern Recognition. 2012. p. 2001-2004 6460551.

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

Hao, P & Kamata, S 2012, Unsupervised people organization and its application on individual retrieval from videos. in Proceedings - International Conference on Pattern Recognition., 6460551, pp. 2001-2004, 21st International Conference on Pattern Recognition, ICPR 2012, Tsukuba, 12/11/11.
Hao P, Kamata S. Unsupervised people organization and its application on individual retrieval from videos. In Proceedings - International Conference on Pattern Recognition. 2012. p. 2001-2004. 6460551
Hao, Pengyi ; Kamata, Seiichiro. / Unsupervised people organization and its application on individual retrieval from videos. Proceedings - International Conference on Pattern Recognition. 2012. pp. 2001-2004
@inproceedings{bf334ab4f2024c72b6124f35a997814d,
title = "Unsupervised people organization and its application on individual retrieval from videos",
abstract = "In this paper, a method named histogram intersection metric learning from scene tracks is proposed for automatic organizing people in videos. We make the following contributions: (i) learning histogram intersection distance instead of Mahalanobis distance for widely used face features; (ii) learning the metric from scene tracks without manually labeling any examples, which enables learning across large variations in pose, expression, occlusion and illumination with small number of face pairs and can distinguish different people powerfully. We firstly test face identification, track clustering, and people organization on a long film, then individual retrieval based on people organization from a large video dataset is evaluated, demonstrating significantly increased search quality with respect to previous approaches on this area.",
author = "Pengyi Hao and Seiichiro Kamata",
year = "2012",
language = "English",
isbn = "9784990644109",
pages = "2001--2004",
booktitle = "Proceedings - International Conference on Pattern Recognition",

}

TY - GEN

T1 - Unsupervised people organization and its application on individual retrieval from videos

AU - Hao, Pengyi

AU - Kamata, Seiichiro

PY - 2012

Y1 - 2012

N2 - In this paper, a method named histogram intersection metric learning from scene tracks is proposed for automatic organizing people in videos. We make the following contributions: (i) learning histogram intersection distance instead of Mahalanobis distance for widely used face features; (ii) learning the metric from scene tracks without manually labeling any examples, which enables learning across large variations in pose, expression, occlusion and illumination with small number of face pairs and can distinguish different people powerfully. We firstly test face identification, track clustering, and people organization on a long film, then individual retrieval based on people organization from a large video dataset is evaluated, demonstrating significantly increased search quality with respect to previous approaches on this area.

AB - In this paper, a method named histogram intersection metric learning from scene tracks is proposed for automatic organizing people in videos. We make the following contributions: (i) learning histogram intersection distance instead of Mahalanobis distance for widely used face features; (ii) learning the metric from scene tracks without manually labeling any examples, which enables learning across large variations in pose, expression, occlusion and illumination with small number of face pairs and can distinguish different people powerfully. We firstly test face identification, track clustering, and people organization on a long film, then individual retrieval based on people organization from a large video dataset is evaluated, demonstrating significantly increased search quality with respect to previous approaches on this area.

UR - http://www.scopus.com/inward/record.url?scp=84874571358&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874571358&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9784990644109

SP - 2001

EP - 2004

BT - Proceedings - International Conference on Pattern Recognition

ER -