A hybrid approach to improving semantic extraction of news video

被引：2

作者：

Hauptmann, A. G. ^{[1
]}

Chen, M. -Y. ^{[1
]}

Christel, M. ^{[1
]}

Lin, W. -H. ^{[1
]}

Yang, J. ^{[1
]}

机构：

[1] Carnegie Mellon Univ, Sch Comp Sci, Pittsburgh, PA 15213 USA

来源：

ICSC 2007: INTERNATIONAL CONFERENCE ON SEMANTIC COMPUTING, PROCEEDINGS | 2007年

基金：

美国国家科学基金会;

关键词：

D O I：

10.1109/ICSC.2007.68

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

In this paper we describe a hybrid approach to improving semantic extraction from news video. Experiments show the value of careful parameter tuning, exploiting multiple feature sets and multilingual linguistic resources, applying text retrieval approaches for image features, and establishing synergy between multiple concepts through undirected graphical models. No single approach provides a consistently better result for every concept detection, which suggests that extracting video semantics should exploit multiple resources and techniques rather than a single approach.

引用

页码：79 / +

页数：3