Automatic digest generation by extracting important scenes from the content of presentations

被引：2

作者：

Le, Hieu Hanh ^{[1
]}

Lertrusdachakul, Thitiporn ^{[2
]}

Watanabe, Tetsutaro ^{[3
]}

Yokota, Haruo ^{[3
,4
]}

机构：

[1] Tokyo Inst Technol, Fac Engn, Dept Comp Sci, Tokyo, Japan

[2] Ricoh Company Ltd, R&D Grp, Tokai, Ibaraki, Japan

[3] Tokyo Inst Technol, Grad Sch Informat & Engn, Dept Comp Sci, Tokyo, Japan

[4] Tokyo Inst Technol, Global Sci Informat & Comp Ctr, Tokyo, Japan

来源：

DEXA 2008: 19TH INTERNATIONAL CONFERENCE ON DATABASE AND EXPERT SYSTEMS APPLICATIONS, PROCEEDINGS | 2008年

基金：

日本科学技术振兴机构;

关键词：

D O I：

10.1109/DEXA.2008.21

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Recently, combining a video recording of a presentation along with the digital slides used in it has become popular in E-learning and presentation of archives. For users of the archives, it is useful to preview a digest of such content to grasp the atmosphere and/or an outline of the presentation. This paper proposes a method of automatic digest generation by extracting important scenes from the presentation content. The extracted scenes are chosen based on several factors such as frequency and specificity of words, scene duration and order. Finally, the effectiveness of the proposed methods are evaluated by comparing with testers' answer sets for actual lectures.

引用

页码：590 / +

页数：2

共 12 条

[1]

BARZILAY R, 1997, P INT SCAL TEST SUMM

[2]

CHIORI H, 2002, THESIS TOKYO I TECHN

[3]

Gong Y., 2001, P 24 ANN INT ACM SIG, P19, DOI DOI 10.1145/383952.383955

[4] Auto-summarization of audio-video presentations [J].

He, LW ;

Sanocki, E ;

Gupta, A ;

Grudin, J .

ACM MULTIMEDIA 99, PROCEEDINGS, 1999, :489-498

[5]

NAKANO W, 2006, P 8 IEEE INT S MULT

[6]

OKAMOTO H, 2007, IEICE T INF SYST, P209

[7]

PICKERING MJ, 2003, IMAGE VIDEO RETRIEVA

[8]

*RIC JAP, MPMEISTER 2

[9]

SANDERSON M, 1998, P 7 INT C INF KNOWL

[10]

WANG J, 2004, P IEEE INT C MULT EX, V1, P599

← 1 2 →