Incorporating temporal context in Bag-of-Words models

Tamar Glaser; Lihi Zelnik-Manor

doi:10.1109/ICCVW.2011.6130436

Incorporating temporal context in Bag-of-Words models

Tamar Glaser, Lihi Zelnik-Manor

Technion - Israel Institute of Technology

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

Abstract

Bag-of-Words (BoW) is a highly popular model for recognition, due to its robustness and simplicity. Its modeling capabilities, however, are somewhat limited since it discards the spatial and temporal order of the codewords. In this paper we propose a new model: Contextual Sequence of Words (CSoW) which incorporates temporal order into the BoW model for video representation. The temporal context is incorporated in three scales that capture different aspects of the variability between different performances of the same action. We show that using CSoW instead of BoW leads to a significant improvement in action recognition rates, on several different setups.

Original language	English
Title of host publication	2011 IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011
Pages	1562-1569
Number of pages	8
DOIs	https://doi.org/10.1109/ICCVW.2011.6130436
State	Published - 2011
Event	2011 IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011 - Barcelona, Spain Duration: 6 Nov 2011 → 13 Nov 2011

Publication series

Name	Proceedings of the IEEE International Conference on Computer Vision

Conference

Conference	2011 IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011
Country/Territory	Spain
City	Barcelona
Period	6/11/11 → 13/11/11

All Science Journal Classification (ASJC) codes

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/ICCVW.2011.6130436

Cite this

@inproceedings{655f844b244d4651a5acc73342efb104,

title = "Incorporating temporal context in Bag-of-Words models",

abstract = "Bag-of-Words (BoW) is a highly popular model for recognition, due to its robustness and simplicity. Its modeling capabilities, however, are somewhat limited since it discards the spatial and temporal order of the codewords. In this paper we propose a new model: Contextual Sequence of Words (CSoW) which incorporates temporal order into the BoW model for video representation. The temporal context is incorporated in three scales that capture different aspects of the variability between different performances of the same action. We show that using CSoW instead of BoW leads to a significant improvement in action recognition rates, on several different setups.",

author = "Tamar Glaser and Lihi Zelnik-Manor",

year = "2011",

doi = "10.1109/ICCVW.2011.6130436",

language = "الإنجليزيّة",

isbn = "9781467300629",

series = "Proceedings of the IEEE International Conference on Computer Vision",

pages = "1562--1569",

booktitle = "2011 IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011",

note = "2011 IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011 ; Conference date: 06-11-2011 Through 13-11-2011",

}

Glaser, T & Zelnik-Manor, L 2011, Incorporating temporal context in Bag-of-Words models. in 2011 IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011., 6130436, Proceedings of the IEEE International Conference on Computer Vision, pp. 1562-1569, 2011 IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011, Barcelona, Spain, 6/11/11. https://doi.org/10.1109/ICCVW.2011.6130436

Incorporating temporal context in Bag-of-Words models. / Glaser, Tamar; Zelnik-Manor, Lihi.
2011 IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011. 2011. p. 1562-1569 6130436 (Proceedings of the IEEE International Conference on Computer Vision).

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

TY - GEN

T1 - Incorporating temporal context in Bag-of-Words models

AU - Glaser, Tamar

AU - Zelnik-Manor, Lihi

PY - 2011

Y1 - 2011

N2 - Bag-of-Words (BoW) is a highly popular model for recognition, due to its robustness and simplicity. Its modeling capabilities, however, are somewhat limited since it discards the spatial and temporal order of the codewords. In this paper we propose a new model: Contextual Sequence of Words (CSoW) which incorporates temporal order into the BoW model for video representation. The temporal context is incorporated in three scales that capture different aspects of the variability between different performances of the same action. We show that using CSoW instead of BoW leads to a significant improvement in action recognition rates, on several different setups.

AB - Bag-of-Words (BoW) is a highly popular model for recognition, due to its robustness and simplicity. Its modeling capabilities, however, are somewhat limited since it discards the spatial and temporal order of the codewords. In this paper we propose a new model: Contextual Sequence of Words (CSoW) which incorporates temporal order into the BoW model for video representation. The temporal context is incorporated in three scales that capture different aspects of the variability between different performances of the same action. We show that using CSoW instead of BoW leads to a significant improvement in action recognition rates, on several different setups.

UR - http://www.scopus.com/inward/record.url?scp=84856682724&partnerID=8YFLogxK

U2 - 10.1109/ICCVW.2011.6130436

DO - 10.1109/ICCVW.2011.6130436

M3 - منشور من مؤتمر

SN - 9781467300629

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 1562

EP - 1569

BT - 2011 IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011

T2 - 2011 IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011

Y2 - 6 November 2011 through 13 November 2011

ER -

Incorporating temporal context in Bag-of-Words models

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this