Large-scale concept ontology for multimedia

被引：312

作者：

Naphade, Milind ^{[1
]}

Smith, John R.

Tesic, Jelena

Chang, Shih-Fu

Hsu, Winston

Kennedy, Lyndon

Hauptmann, Alexander

Curtis, Jon

机构：

[1] IBM Corp, Thomas J Watson Res Ctr, Yorktown Hts, NY 10598 USA

[2] Columbia Univ, New York, NY 10027 USA

[3] Carnegie Mellon Univ, Pittsburgh, PA 15213 USA

来源：

IEEE MULTIMEDIA | 2006年 / 13卷 / 03期

关键词：

D O I：

10.1109/MMUL.2006.63

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 [计算机科学与技术];

摘要：

As increasingly powerful techniques emerge for machine tagging multimedia content, it becomes ever more important to standardize the underlying vocabularies. Doing so provides interoperability and lets the multimedia community focus ongoing research on a well-defined set of semantics. This column describes a recent collaborative effort of multimedia researchers, library scientists, and end users to develop a large standardized taxonomy for describing broadcast news video. The Large-Scale Concept Ontology for Multimedia (LSCOM) is the first of its kind designed to simultaneously optimize utility to facilitate end-user access, cover a large semantic space, make automated extraction feasible, and increase observability in diverse broadcast news video data sets. © 2006 IEEE.

引用

页码：86 / 91

页数：6