A probabilistic template-based approach to discovering repetitive patterns in broadcast videos

Peng Wang; Zhi-Qiang Liu; Shi-Qiang Yang

doi:10.1145/1101149.1101238

A probabilistic template-based approach to discovering repetitive patterns in broadcast videos

Peng Wang
, Zhi-Qiang Liu
, Shi-Qiang Yang

School of Creative Media

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

8 Citations (Scopus)

Abstract

There are usually repetitive sub-segments in broadcast videos, which may be associated with high-level concepts or events, e.g., news footage, repeated scores in basketball. Unsupervised mining techniques provide generic solutions to discovering such temporal patterns in various video genres, which are currently the subject of great interests to researchers working on multimedia content analysis. In this paper, we propose a novel approach to automatically detecting repetitive patterns in a video stream. In this approach, a video stream is first transformed to a symbol sequence via the spectral clustering algorithm. After computing the transition probabilities of any two symbols in temporal evolution, we produce a set of probabilistic templates to characterize the patterns of potential interest. Finally, we verify each probabilistic template by measuring the similarities between the video sub-segments and the template. Evaluations on various sports videos show promising results. Copyright © 2005 ACM.

Original language	English
Title of host publication	Proceedings of the 13th ACM International Conference on Multimedia, MM 2005
Pages	407-410
DOIs	https://doi.org/10.1145/1101149.1101238
Publication status	Published - 2005
Event	13th ACM International Conference on Multimedia, MM 2005 - Singapore, Singapore Duration: 6 Nov 2005 → 11 Nov 2005

Publication series

Name	Proceedings of the 13th ACM International Conference on Multimedia, MM 2005

Conference

Conference	13th ACM International Conference on Multimedia, MM 2005
Place	Singapore
City	Singapore
Period	6/11/05 → 11/11/05

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Funding

This research has been supported in part by research grants from National Natural Science Foundation of China No. 60273008, City University of Hong Kong No.7001679, and Hong Kong RGC CityU 1062/02E.

Research Keywords

Probabilistic template
Repetitive pattern discovery
Video mining

RGC Funding Information

RGC-funded

Access Output

10.1145/1101149.1101238

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{4010a39bd0604b79af47aaeccdd254a3,

title = "A probabilistic template-based approach to discovering repetitive patterns in broadcast videos",

abstract = "There are usually repetitive sub-segments in broadcast videos, which may be associated with high-level concepts or events, e.g., news footage, repeated scores in basketball. Unsupervised mining techniques provide generic solutions to discovering such temporal patterns in various video genres, which are currently the subject of great interests to researchers working on multimedia content analysis. In this paper, we propose a novel approach to automatically detecting repetitive patterns in a video stream. In this approach, a video stream is first transformed to a symbol sequence via the spectral clustering algorithm. After computing the transition probabilities of any two symbols in temporal evolution, we produce a set of probabilistic templates to characterize the patterns of potential interest. Finally, we verify each probabilistic template by measuring the similarities between the video sub-segments and the template. Evaluations on various sports videos show promising results. Copyright {\textcopyright} 2005 ACM.",

keywords = "Probabilistic template, Repetitive pattern discovery, Video mining",

author = "Peng Wang and Zhi-Qiang Liu and Shi-Qiang Yang",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].; 13th ACM International Conference on Multimedia, MM 2005 ; Conference date: 06-11-2005 Through 11-11-2005",

year = "2005",

doi = "10.1145/1101149.1101238",

language = "English",

isbn = "1595930442",

series = "Proceedings of the 13th ACM International Conference on Multimedia, MM 2005",

pages = "407--410",

booktitle = "Proceedings of the 13th ACM International Conference on Multimedia, MM 2005",

}

Wang, P, Liu, Z-Q & Yang, S-Q 2005, A probabilistic template-based approach to discovering repetitive patterns in broadcast videos. in Proceedings of the 13th ACM International Conference on Multimedia, MM 2005. Proceedings of the 13th ACM International Conference on Multimedia, MM 2005, pp. 407-410, 13th ACM International Conference on Multimedia, MM 2005, Singapore, Singapore, 6/11/05. https://doi.org/10.1145/1101149.1101238

A probabilistic template-based approach to discovering repetitive patterns in broadcast videos. / Wang, Peng; Liu, Zhi-Qiang; Yang, Shi-Qiang.
Proceedings of the 13th ACM International Conference on Multimedia, MM 2005. 2005. p. 407-410 (Proceedings of the 13th ACM International Conference on Multimedia, MM 2005).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - A probabilistic template-based approach to discovering repetitive patterns in broadcast videos

AU - Wang, Peng

AU - Liu, Zhi-Qiang

AU - Yang, Shi-Qiang

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

PY - 2005

Y1 - 2005

N2 - There are usually repetitive sub-segments in broadcast videos, which may be associated with high-level concepts or events, e.g., news footage, repeated scores in basketball. Unsupervised mining techniques provide generic solutions to discovering such temporal patterns in various video genres, which are currently the subject of great interests to researchers working on multimedia content analysis. In this paper, we propose a novel approach to automatically detecting repetitive patterns in a video stream. In this approach, a video stream is first transformed to a symbol sequence via the spectral clustering algorithm. After computing the transition probabilities of any two symbols in temporal evolution, we produce a set of probabilistic templates to characterize the patterns of potential interest. Finally, we verify each probabilistic template by measuring the similarities between the video sub-segments and the template. Evaluations on various sports videos show promising results. Copyright © 2005 ACM.

AB - There are usually repetitive sub-segments in broadcast videos, which may be associated with high-level concepts or events, e.g., news footage, repeated scores in basketball. Unsupervised mining techniques provide generic solutions to discovering such temporal patterns in various video genres, which are currently the subject of great interests to researchers working on multimedia content analysis. In this paper, we propose a novel approach to automatically detecting repetitive patterns in a video stream. In this approach, a video stream is first transformed to a symbol sequence via the spectral clustering algorithm. After computing the transition probabilities of any two symbols in temporal evolution, we produce a set of probabilistic templates to characterize the patterns of potential interest. Finally, we verify each probabilistic template by measuring the similarities between the video sub-segments and the template. Evaluations on various sports videos show promising results. Copyright © 2005 ACM.

KW - Probabilistic template

KW - Repetitive pattern discovery

KW - Video mining

UR - https://www.scopus.com/pages/publications/84883082139

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84883082139&origin=recordpage

U2 - 10.1145/1101149.1101238

DO - 10.1145/1101149.1101238

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 1595930442

SN - 9781595930446

T3 - Proceedings of the 13th ACM International Conference on Multimedia, MM 2005

SP - 407

EP - 410

BT - Proceedings of the 13th ACM International Conference on Multimedia, MM 2005

T2 - 13th ACM International Conference on Multimedia, MM 2005

Y2 - 6 November 2005 through 11 November 2005

ER -

A probabilistic template-based approach to discovering repetitive patterns in broadcast videos

Abstract

Publication series

Conference

Bibliographical note

Funding

Research Keywords

RGC Funding Information

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this