Event detection and highlight detection of broadcasted game videos

Wei Ta Chu; Yung Chieh Chou

doi:10.1145/2810397.2810398

Event detection and highlight detection of broadcasted game videos

Wei Ta Chu, Yung Chieh Chou

Department of Computer Science and Information Engineering

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

12 Citations (Scopus)

Abstract

Efficient access of game videos is urgently demanded due to the emergence of live streaming platforms and the explosive numbers of gamers and viewers. In this work we facilitate efficient access from two aspects: game event detection and highlight detection. By recognizing predefined text displayed on screen when some events occur, we associate game events with time stamps to facilitate direct access. We jointly consider visual features, events, and viewer's reaction to construct two highlight models, and enable compact game presentation. Experimental results show the effectiveness of the proposed methods. As one of the early attempts on analyzing broadcasted game videos from the perspective of multimedia content analysis, our contributions are twofold. First, we design and extract game-specific features considering visual content, event semantics, and viewer's reaction. Second, we integrate clues from these three domains based on a psychological approach and a data-driven approach to characterize game highlights.

Original language	English
Title of host publication	HCMC 2015 - Proceedings of the 2nd Workshop on Computational Models of Social Interactions
Subtitle of host publication	Human-Computer-Media Communication, co-located with ACM MM 2015
Publisher	Association for Computing Machinery, Inc
Pages	1-8
Number of pages	8
ISBN (Electronic)	9781450337472
DOIs	https://doi.org/10.1145/2810397.2810398
Publication status	Published - 2015 Oct 30
Event	2nd Workshop on Computational Models of Social Interactions: Human-Computer-Media Communication, HCMC 2015 - Brisbane, Australia Duration: 2015 Oct 30 → …

Publication series

Name	HCMC 2015 - Proceedings of the 2nd Workshop on Computational Models of Social Interactions: Human-Computer-Media Communication, co-located with ACM MM 2015

Conference

Conference	2nd Workshop on Computational Models of Social Interactions: Human-Computer-Media Communication, HCMC 2015
Country/Territory	Australia
City	Brisbane
Period	15-10-30 → …

All Science Journal Classification (ASJC) codes

Media Technology
Computational Mathematics
General Computer Science

Access to Document

10.1145/2810397.2810398

Cite this

Chu, W. T., & Chou, Y. C. (2015). Event detection and highlight detection of broadcasted game videos. In HCMC 2015 - Proceedings of the 2nd Workshop on Computational Models of Social Interactions: Human-Computer-Media Communication, co-located with ACM MM 2015 (pp. 1-8). (HCMC 2015 - Proceedings of the 2nd Workshop on Computational Models of Social Interactions: Human-Computer-Media Communication, co-located with ACM MM 2015). Association for Computing Machinery, Inc. https://doi.org/10.1145/2810397.2810398

Chu, Wei Ta ; Chou, Yung Chieh. / Event detection and highlight detection of broadcasted game videos. HCMC 2015 - Proceedings of the 2nd Workshop on Computational Models of Social Interactions: Human-Computer-Media Communication, co-located with ACM MM 2015. Association for Computing Machinery, Inc, 2015. pp. 1-8 (HCMC 2015 - Proceedings of the 2nd Workshop on Computational Models of Social Interactions: Human-Computer-Media Communication, co-located with ACM MM 2015).

@inproceedings{f2ca8aa7f5c9432fa972a4f32395fbff,

title = "Event detection and highlight detection of broadcasted game videos",

abstract = "Efficient access of game videos is urgently demanded due to the emergence of live streaming platforms and the explosive numbers of gamers and viewers. In this work we facilitate efficient access from two aspects: game event detection and highlight detection. By recognizing predefined text displayed on screen when some events occur, we associate game events with time stamps to facilitate direct access. We jointly consider visual features, events, and viewer's reaction to construct two highlight models, and enable compact game presentation. Experimental results show the effectiveness of the proposed methods. As one of the early attempts on analyzing broadcasted game videos from the perspective of multimedia content analysis, our contributions are twofold. First, we design and extract game-specific features considering visual content, event semantics, and viewer's reaction. Second, we integrate clues from these three domains based on a psychological approach and a data-driven approach to characterize game highlights.",

author = "Chu, {Wei Ta} and Chou, {Yung Chieh}",

note = "Publisher Copyright: {\textcopyright} 2015 ACM.; 2nd Workshop on Computational Models of Social Interactions: Human-Computer-Media Communication, HCMC 2015 ; Conference date: 30-10-2015",

year = "2015",

month = oct,

day = "30",

doi = "10.1145/2810397.2810398",

language = "English",

series = "HCMC 2015 - Proceedings of the 2nd Workshop on Computational Models of Social Interactions: Human-Computer-Media Communication, co-located with ACM MM 2015",

publisher = "Association for Computing Machinery, Inc",

pages = "1--8",

booktitle = "HCMC 2015 - Proceedings of the 2nd Workshop on Computational Models of Social Interactions",

}

Chu, WT & Chou, YC 2015, Event detection and highlight detection of broadcasted game videos. in HCMC 2015 - Proceedings of the 2nd Workshop on Computational Models of Social Interactions: Human-Computer-Media Communication, co-located with ACM MM 2015. HCMC 2015 - Proceedings of the 2nd Workshop on Computational Models of Social Interactions: Human-Computer-Media Communication, co-located with ACM MM 2015, Association for Computing Machinery, Inc, pp. 1-8, 2nd Workshop on Computational Models of Social Interactions: Human-Computer-Media Communication, HCMC 2015, Brisbane, Australia, 15-10-30. https://doi.org/10.1145/2810397.2810398

Event detection and highlight detection of broadcasted game videos. / Chu, Wei Ta; Chou, Yung Chieh.
HCMC 2015 - Proceedings of the 2nd Workshop on Computational Models of Social Interactions: Human-Computer-Media Communication, co-located with ACM MM 2015. Association for Computing Machinery, Inc, 2015. p. 1-8 (HCMC 2015 - Proceedings of the 2nd Workshop on Computational Models of Social Interactions: Human-Computer-Media Communication, co-located with ACM MM 2015).

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

TY - GEN

T1 - Event detection and highlight detection of broadcasted game videos

AU - Chu, Wei Ta

AU - Chou, Yung Chieh

PY - 2015/10/30

Y1 - 2015/10/30

N2 - Efficient access of game videos is urgently demanded due to the emergence of live streaming platforms and the explosive numbers of gamers and viewers. In this work we facilitate efficient access from two aspects: game event detection and highlight detection. By recognizing predefined text displayed on screen when some events occur, we associate game events with time stamps to facilitate direct access. We jointly consider visual features, events, and viewer's reaction to construct two highlight models, and enable compact game presentation. Experimental results show the effectiveness of the proposed methods. As one of the early attempts on analyzing broadcasted game videos from the perspective of multimedia content analysis, our contributions are twofold. First, we design and extract game-specific features considering visual content, event semantics, and viewer's reaction. Second, we integrate clues from these three domains based on a psychological approach and a data-driven approach to characterize game highlights.

AB - Efficient access of game videos is urgently demanded due to the emergence of live streaming platforms and the explosive numbers of gamers and viewers. In this work we facilitate efficient access from two aspects: game event detection and highlight detection. By recognizing predefined text displayed on screen when some events occur, we associate game events with time stamps to facilitate direct access. We jointly consider visual features, events, and viewer's reaction to construct two highlight models, and enable compact game presentation. Experimental results show the effectiveness of the proposed methods. As one of the early attempts on analyzing broadcasted game videos from the perspective of multimedia content analysis, our contributions are twofold. First, we design and extract game-specific features considering visual content, event semantics, and viewer's reaction. Second, we integrate clues from these three domains based on a psychological approach and a data-driven approach to characterize game highlights.

UR - http://www.scopus.com/inward/record.url?scp=84964394111&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964394111&partnerID=8YFLogxK

U2 - 10.1145/2810397.2810398

DO - 10.1145/2810397.2810398

M3 - Conference contribution

AN - SCOPUS:84964394111

T3 - HCMC 2015 - Proceedings of the 2nd Workshop on Computational Models of Social Interactions: Human-Computer-Media Communication, co-located with ACM MM 2015

SP - 1

EP - 8

BT - HCMC 2015 - Proceedings of the 2nd Workshop on Computational Models of Social Interactions

PB - Association for Computing Machinery, Inc

T2 - 2nd Workshop on Computational Models of Social Interactions: Human-Computer-Media Communication, HCMC 2015

Y2 - 30 October 2015

ER -

Chu WT, Chou YC. Event detection and highlight detection of broadcasted game videos. In HCMC 2015 - Proceedings of the 2nd Workshop on Computational Models of Social Interactions: Human-Computer-Media Communication, co-located with ACM MM 2015. Association for Computing Machinery, Inc. 2015. p. 1-8. (HCMC 2015 - Proceedings of the 2nd Workshop on Computational Models of Social Interactions: Human-Computer-Media Communication, co-located with ACM MM 2015). doi: 10.1145/2810397.2810398

Event detection and highlight detection of broadcasted game videos

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this