Key issues in video summarization and its application

Author

Zhuang, Yueting ; Xiao, Ruogui ; Wu, Fei

Author_Institution

Inst. of Artificial Intelligence, Zhejiang Univ., China

Volume

1

fYear

2003

Firstpage

448

Abstract

The summarization of video content provides an effective way to speed up video browser and assist for video retrieval, this paper proposes a novel method for automatically summarizing multi-view video contents. Three kinds of content views such as semantic-face, video caption and visual features are presented in this paper. First, the human faces in video and images bear significant semantics, thus we can summarize video content by indexing and analyzing video faces, especially for video news. Second, video caption could be used to generate video summarization with high-level semantics since it implied lots of semantics inherently. Finally, the similar video shots could be integrated into concise representation through clustering and mining of visual features.

Keywords

content-based retrieval; information retrieval; pattern clustering; video databases; video signal processing; feature clustering; feature mining; indexing; multiview video contents; semantic-face; semantics; video browser; video caption; video content summarization; video retrieval; visual features; Content based retrieval; Face detection; Humans; Image analysis; Indexing; Information retrieval; Large-scale systems; Motion pictures; Multimedia databases; Multimedia systems;

fLanguage

English

Publisher

ieee

Conference_Titel

Information, Communications and Signal Processing, 2003 and Fourth Pacific Rim Conference on Multimedia. Proceedings of the 2003 Joint Conference of the Fourth International Conference on

Print_ISBN

0-7803-8185-8

Type

conf

DOI

10.1109/ICICS.2003.1292492

Filename

1292492