Automatic chapter generation for consumer videos

Chia Wei Wang; Wen-Huang Cheng; Ja Ling Wu

doi:10.1109/ICCE.2007.341529

Automatic chapter generation for consumer videos

Chia Wei Wang^*, Wen-Huang Cheng, Ja Ling Wu

^*Corresponding author for this work

Institute of Electronics

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

Abstract

This paper proposes a novel framework for automatic chapter generation of consumer videos, in which the knowledge of media aesthetics and video production is utilized. For an input video, a set of specific visual and aural aesthetic features, called expressive elements, is first extracted. Then a high-level structure with aesthetic semantics, namely aesthetic intensity, is obtained and used to generate the corresponding video chapters. Experimental results demonstrate the effectiveness and efficiency of the proposed approach.

Original language	English
Title of host publication	Digest of Technical Papers - 2007 International Conference on Consumer Electronics, ICCE 2007
DOIs	https://doi.org/10.1109/ICCE.2007.341529
State	Published - 24 Aug 2007
Event	2007 Digest of Technical Papers International Conference on Consumer Electronics - Las Vegas, NV, United States Duration: 10 Jan 2007 → 14 Jan 2007

Publication series

Name	Digest of Technical Papers - IEEE International Conference on Consumer Electronics
ISSN (Print)	0747-668X

Conference

Conference	2007 Digest of Technical Papers International Conference on Consumer Electronics
Country	United States
City	Las Vegas, NV
Period	10/01/07 → 14/01/07

Access to Document

10.1109/ICCE.2007.341529

Link to publication in Scopus

Fingerprint Dive into the research topics of 'Automatic chapter generation for consumer videos'. Together they form a unique fingerprint.

Cite this

@inproceedings{c7849decf34f49e1a16906a74c92e64a,

title = "Automatic chapter generation for consumer videos",

abstract = "This paper proposes a novel framework for automatic chapter generation of consumer videos, in which the knowledge of media aesthetics and video production is utilized. For an input video, a set of specific visual and aural aesthetic features, called expressive elements, is first extracted. Then a high-level structure with aesthetic semantics, namely aesthetic intensity, is obtained and used to generate the corresponding video chapters. Experimental results demonstrate the effectiveness and efficiency of the proposed approach.",

author = "Wang, {Chia Wei} and Wen-Huang Cheng and Wu, {Ja Ling}",

year = "2007",

month = aug,

day = "24",

doi = "10.1109/ICCE.2007.341529",

language = "English",

isbn = "142440763X",

series = "Digest of Technical Papers - IEEE International Conference on Consumer Electronics",

booktitle = "Digest of Technical Papers - 2007 International Conference on Consumer Electronics, ICCE 2007",

note = "null ; Conference date: 10-01-2007 Through 14-01-2007",

}

Wang, CW, Cheng, W-H & Wu, JL 2007, Automatic chapter generation for consumer videos. in Digest of Technical Papers - 2007 International Conference on Consumer Electronics, ICCE 2007., 4146187, Digest of Technical Papers - IEEE International Conference on Consumer Electronics, 2007 Digest of Technical Papers International Conference on Consumer Electronics, Las Vegas, NV, United States, 10/01/07. https://doi.org/10.1109/ICCE.2007.341529

Automatic chapter generation for consumer videos. / Wang, Chia Wei; Cheng, Wen-Huang; Wu, Ja Ling.

Digest of Technical Papers - 2007 International Conference on Consumer Electronics, ICCE 2007. 2007. 4146187 (Digest of Technical Papers - IEEE International Conference on Consumer Electronics).

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

TY - GEN

T1 - Automatic chapter generation for consumer videos

AU - Wang, Chia Wei

AU - Cheng, Wen-Huang

AU - Wu, Ja Ling

PY - 2007/8/24

Y1 - 2007/8/24

N2 - This paper proposes a novel framework for automatic chapter generation of consumer videos, in which the knowledge of media aesthetics and video production is utilized. For an input video, a set of specific visual and aural aesthetic features, called expressive elements, is first extracted. Then a high-level structure with aesthetic semantics, namely aesthetic intensity, is obtained and used to generate the corresponding video chapters. Experimental results demonstrate the effectiveness and efficiency of the proposed approach.

AB - This paper proposes a novel framework for automatic chapter generation of consumer videos, in which the knowledge of media aesthetics and video production is utilized. For an input video, a set of specific visual and aural aesthetic features, called expressive elements, is first extracted. Then a high-level structure with aesthetic semantics, namely aesthetic intensity, is obtained and used to generate the corresponding video chapters. Experimental results demonstrate the effectiveness and efficiency of the proposed approach.

UR - http://www.scopus.com/inward/record.url?scp=34548018053&partnerID=8YFLogxK

U2 - 10.1109/ICCE.2007.341529

DO - 10.1109/ICCE.2007.341529

M3 - Conference contribution

AN - SCOPUS:34548018053

SN - 142440763X

SN - 9781424407637

T3 - Digest of Technical Papers - IEEE International Conference on Consumer Electronics

BT - Digest of Technical Papers - 2007 International Conference on Consumer Electronics, ICCE 2007

Y2 - 10 January 2007 through 14 January 2007

ER -