Video summarization based on user log enhanced link analysis

Bin Yu; Wei-Ying Ma; Klara Nahrstedt; Hong-Jiang Zhang

doi:10.1145/957013.957095

Video summarization based on user log enhanced link analysis

Bin Yu
, Wei-Ying Ma
, Klara Nahrstedt
, Hong-Jiang Zhang

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

69 Citations (Scopus)

Abstract

Efficient video data management calls for intelligent video summarization tools that automatically generate concise video summaries for fast skimming and browsing. Traditional video summarization techniques are based on low-level feature analysis, which generally fails to capture the semantics of video content. Our vision is that users unintentionally embed their understanding of the video content in their interaction with computers. This valuable knowledge, which is difficult for computers to learn autonomously, can be utilized for video summarization process. In this paper, we present an intelligent video browsing and summarization system that utilizes previous viewers' browsing log to facilitate future viewers. Specifically, a novel ShotRank notion is proposed as a measure of the subjective interestingness and importance of each video shot. A ShotRank computation framework is constructed to seamlessly unify low-level video analysis and user browsing log mining. The resulting ShotRank is used to organize the presentation of video shots and generate video skims. Experimental results from user studies have strongly confirmed that ShotRank indeed represents the subjective notion of interestingness and importance of each video shot, and it significantly improves future viewers' browsing experience.
Copyright 2003 ACM

Original language	English
Title of host publication	2003 Multimedia Conference - Proceedings of the 11th ACM International Conference on Multimedia, MM'03
Publisher	Association for Computing Machinery
Pages	382-391
DOIs	https://doi.org/10.1145/957013.957095
Publication status	Published - 2003
Externally published	Yes
Event	2003 Multimedia Conference - Proceedings of the 11th ACM International Conference on Multimedia, MM'03 - Berkeley, United States Duration: 2 Nov 2003 → 8 Nov 2003 https://dl.acm.org/doi/proceedings/10.1145/957013

Publication series

Name	Proceedings of the ACM International Multimedia Conference and Exhibition

Conference

Conference	2003 Multimedia Conference - Proceedings of the 11th ACM International Conference on Multimedia, MM'03
Place	United States
City	Berkeley
Period	2/11/03 → 8/11/03
Internet address	https://dl.acm.org/doi/proceedings/10.1145/957013

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

The authors would like to thank Zheng Chen for his suggestions to our work; all friends from MSR Asia who helped us to do the evaluation during the first author’s intern at MSR Asia; the reviewers and professor James Wang for their insightful comments; and NSF for the ITR grant that the first author is funded for completing this work.

Research Keywords

Link analysis
Log mining
Skimming
User behavior
Video content analysis
Video summarization

Access Output

10.1145/957013.957095

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Yu, B., Ma, W.-Y., Nahrstedt, K., & Zhang, H.-J. (2003). Video summarization based on user log enhanced link analysis. In 2003 Multimedia Conference - Proceedings of the 11th ACM International Conference on Multimedia, MM'03 (pp. 382-391). (Proceedings of the ACM International Multimedia Conference and Exhibition). Association for Computing Machinery. https://doi.org/10.1145/957013.957095

@inproceedings{122fa0e6ff684da7a306cb4ded9a2924,

title = "Video summarization based on user log enhanced link analysis",

abstract = "Efficient video data management calls for intelligent video summarization tools that automatically generate concise video summaries for fast skimming and browsing. Traditional video summarization techniques are based on low-level feature analysis, which generally fails to capture the semantics of video content. Our vision is that users unintentionally embed their understanding of the video content in their interaction with computers. This valuable knowledge, which is difficult for computers to learn autonomously, can be utilized for video summarization process. In this paper, we present an intelligent video browsing and summarization system that utilizes previous viewers' browsing log to facilitate future viewers. Specifically, a novel ShotRank notion is proposed as a measure of the subjective interestingness and importance of each video shot. A ShotRank computation framework is constructed to seamlessly unify low-level video analysis and user browsing log mining. The resulting ShotRank is used to organize the presentation of video shots and generate video skims. Experimental results from user studies have strongly confirmed that ShotRank indeed represents the subjective notion of interestingness and importance of each video shot, and it significantly improves future viewers' browsing experience. Copyright 2003 ACM",

keywords = "Link analysis, Log mining, Skimming, User behavior, Video content analysis, Video summarization",

author = "Bin Yu and Wei-Ying Ma and Klara Nahrstedt and Hong-Jiang Zhang",

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].; 2003 Multimedia Conference - Proceedings of the 11th ACM International Conference on Multimedia, MM'03 ; Conference date: 02-11-2003 Through 08-11-2003",

year = "2003",

doi = "10.1145/957013.957095",

language = "English",

series = "Proceedings of the ACM International Multimedia Conference and Exhibition",

publisher = "Association for Computing Machinery",

pages = "382--391",

booktitle = "2003 Multimedia Conference - Proceedings of the 11th ACM International Conference on Multimedia, MM'03",

address = "United States",

url = "https://dl.acm.org/doi/proceedings/10.1145/957013",

}

Yu, B, Ma, W-Y, Nahrstedt, K & Zhang, H-J 2003, Video summarization based on user log enhanced link analysis. in 2003 Multimedia Conference - Proceedings of the 11th ACM International Conference on Multimedia, MM'03. Proceedings of the ACM International Multimedia Conference and Exhibition, Association for Computing Machinery, pp. 382-391, 2003 Multimedia Conference - Proceedings of the 11th ACM International Conference on Multimedia, MM'03, Berkeley, California, United States, 2/11/03. https://doi.org/10.1145/957013.957095

Video summarization based on user log enhanced link analysis. / Yu, Bin; Ma, Wei-Ying; Nahrstedt, Klara et al.
2003 Multimedia Conference - Proceedings of the 11th ACM International Conference on Multimedia, MM'03. Association for Computing Machinery, 2003. p. 382-391 (Proceedings of the ACM International Multimedia Conference and Exhibition).

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

TY - GEN

T1 - Video summarization based on user log enhanced link analysis

AU - Yu, Bin

AU - Ma, Wei-Ying

AU - Nahrstedt, Klara

AU - Zhang, Hong-Jiang

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 - 2003

Y1 - 2003

N2 - Efficient video data management calls for intelligent video summarization tools that automatically generate concise video summaries for fast skimming and browsing. Traditional video summarization techniques are based on low-level feature analysis, which generally fails to capture the semantics of video content. Our vision is that users unintentionally embed their understanding of the video content in their interaction with computers. This valuable knowledge, which is difficult for computers to learn autonomously, can be utilized for video summarization process. In this paper, we present an intelligent video browsing and summarization system that utilizes previous viewers' browsing log to facilitate future viewers. Specifically, a novel ShotRank notion is proposed as a measure of the subjective interestingness and importance of each video shot. A ShotRank computation framework is constructed to seamlessly unify low-level video analysis and user browsing log mining. The resulting ShotRank is used to organize the presentation of video shots and generate video skims. Experimental results from user studies have strongly confirmed that ShotRank indeed represents the subjective notion of interestingness and importance of each video shot, and it significantly improves future viewers' browsing experience. Copyright 2003 ACM

AB - Efficient video data management calls for intelligent video summarization tools that automatically generate concise video summaries for fast skimming and browsing. Traditional video summarization techniques are based on low-level feature analysis, which generally fails to capture the semantics of video content. Our vision is that users unintentionally embed their understanding of the video content in their interaction with computers. This valuable knowledge, which is difficult for computers to learn autonomously, can be utilized for video summarization process. In this paper, we present an intelligent video browsing and summarization system that utilizes previous viewers' browsing log to facilitate future viewers. Specifically, a novel ShotRank notion is proposed as a measure of the subjective interestingness and importance of each video shot. A ShotRank computation framework is constructed to seamlessly unify low-level video analysis and user browsing log mining. The resulting ShotRank is used to organize the presentation of video shots and generate video skims. Experimental results from user studies have strongly confirmed that ShotRank indeed represents the subjective notion of interestingness and importance of each video shot, and it significantly improves future viewers' browsing experience. Copyright 2003 ACM

KW - Link analysis

KW - Log mining

KW - Skimming

KW - User behavior

KW - Video content analysis

KW - Video summarization

UR - https://www.scopus.com/pages/publications/2342476454

UR - https://www.scopus.com/pages/publications/2342476454#tab=impact

U2 - 10.1145/957013.957095

DO - 10.1145/957013.957095

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

T3 - Proceedings of the ACM International Multimedia Conference and Exhibition

SP - 382

EP - 391

BT - 2003 Multimedia Conference - Proceedings of the 11th ACM International Conference on Multimedia, MM'03

PB - Association for Computing Machinery

T2 - 2003 Multimedia Conference - Proceedings of the 11th ACM International Conference on Multimedia, MM'03

Y2 - 2 November 2003 through 8 November 2003

ER -

Video summarization based on user log enhanced link analysis

Abstract

Publication series

Conference

Bibliographical note

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this