Robust object tracking via online multiple instance metric learning

Min Yang; Caixia Zhang; Yuwei Wu; Mingtao Pei; Yunde Jia

doi:10.1109/ICMEW.2013.6618252

Robust object tracking via online multiple instance metric learning

Min Yang, Caixia Zhang, Yuwei Wu, Mingtao Pei, Yunde Jia

Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

8 Citations (Scopus)

Abstract

This paper presents a novel object tracking method using online multiple instance metric learning to adaptively capture appearance variations. More specifically, we seek for an appropriate metric via online metric learning to match the different appearances of an object and simultaneously separate the object from the background. The drift problem caused by potentially misaligned training examples is alleviated by performing online metric learning under the multiple instance setting. Both qualitative and quantitative evaluations on various challenging sequences are discussed.

Original language	English
Title of host publication	Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013
DOIs	https://doi.org/10.1109/ICMEW.2013.6618252
Publication status	Published - 2013
Event	2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013 - San Jose, CA, United States Duration: 15 Jul 2013 → 19 Jul 2013

Publication series

Name	Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013

Conference

Conference	2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013
Country/Territory	United States
City	San Jose, CA
Period	15/07/13 → 19/07/13

Keywords

appearance variation
multiple instance
object tracking
online metric learning

Access to Document

10.1109/ICMEW.2013.6618252

Cite this

Yang, M., Zhang, C., Wu, Y., Pei, M., & Jia, Y. (2013). Robust object tracking via online multiple instance metric learning. In Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013 Article 6618252 (Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013). https://doi.org/10.1109/ICMEW.2013.6618252

@inproceedings{cdcce4c9ded5472d95f6b63db3ea8832,

title = "Robust object tracking via online multiple instance metric learning",

abstract = "This paper presents a novel object tracking method using online multiple instance metric learning to adaptively capture appearance variations. More specifically, we seek for an appropriate metric via online metric learning to match the different appearances of an object and simultaneously separate the object from the background. The drift problem caused by potentially misaligned training examples is alleviated by performing online metric learning under the multiple instance setting. Both qualitative and quantitative evaluations on various challenging sequences are discussed.",

keywords = "appearance variation, multiple instance, object tracking, online metric learning",

author = "Min Yang and Caixia Zhang and Yuwei Wu and Mingtao Pei and Yunde Jia",

year = "2013",

doi = "10.1109/ICMEW.2013.6618252",

language = "English",

isbn = "9781479916047",

series = "Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013",

booktitle = "Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013",

note = "2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013 ; Conference date: 15-07-2013 Through 19-07-2013",

}

Yang, M, Zhang, C, Wu, Y , Pei, M & Jia, Y 2013, Robust object tracking via online multiple instance metric learning. in Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013., 6618252, Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013, 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013, San Jose, CA, United States, 15/07/13. https://doi.org/10.1109/ICMEW.2013.6618252

Robust object tracking via online multiple instance metric learning. / Yang, Min; Zhang, Caixia; Wu, Yuwei et al.
Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013. 2013. 6618252 (Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Robust object tracking via online multiple instance metric learning

AU - Yang, Min

AU - Zhang, Caixia

AU - Wu, Yuwei

AU - Pei, Mingtao

AU - Jia, Yunde

PY - 2013

Y1 - 2013

N2 - This paper presents a novel object tracking method using online multiple instance metric learning to adaptively capture appearance variations. More specifically, we seek for an appropriate metric via online metric learning to match the different appearances of an object and simultaneously separate the object from the background. The drift problem caused by potentially misaligned training examples is alleviated by performing online metric learning under the multiple instance setting. Both qualitative and quantitative evaluations on various challenging sequences are discussed.

AB - This paper presents a novel object tracking method using online multiple instance metric learning to adaptively capture appearance variations. More specifically, we seek for an appropriate metric via online metric learning to match the different appearances of an object and simultaneously separate the object from the background. The drift problem caused by potentially misaligned training examples is alleviated by performing online metric learning under the multiple instance setting. Both qualitative and quantitative evaluations on various challenging sequences are discussed.

KW - appearance variation

KW - multiple instance

KW - object tracking

KW - online metric learning

UR - http://www.scopus.com/inward/record.url?scp=84888212593&partnerID=8YFLogxK

U2 - 10.1109/ICMEW.2013.6618252

DO - 10.1109/ICMEW.2013.6618252

M3 - Conference contribution

AN - SCOPUS:84888212593

SN - 9781479916047

T3 - Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013

BT - Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013

T2 - 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013

Y2 - 15 July 2013 through 19 July 2013

ER -

Yang M, Zhang C, Wu Y , Pei M, Jia Y. Robust object tracking via online multiple instance metric learning. In Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013. 2013. 6618252. (Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013). doi: 10.1109/ICMEW.2013.6618252

Robust object tracking via online multiple instance metric learning

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this