VERL:: An ontology framework for representing and annotating video events

被引：123

作者：

François, ARJ ^{[1
]}

Nevatia, R

Hobbs, J

Bolles, RC

机构：

[1] Univ So Calif, Inst Informat Sci, Los Angeles, CA 90089 USA

[2] SRI Int, Menlo Pk, CA 94025 USA

来源：

IEEE MULTIMEDIA | 2005年 / 12卷 / 04期

关键词：

D O I：

10.1109/MMUL.2005.87

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

A framework for video event representation and annotation that is based on the definition of an ontology suitable for video content is presented. An ontology consists of a specific vocabulary for describing a certain reality and a set of explicit assumptions regarding the vocabulary's intended meaning. The Video Event Representation Language (VERL) describes an event ontology, and the Video Event Markup Language (VEML) allows the annotation of the instances of the events described in VERL. The framework can be integrated with MPEG-7 standards.

引用

页码：76 / 86

页数：11

共 11 条

[1]

Allen J. F., 1997, Spatial and temporal reasoning, P205, DOI [10.1007/978-0-585-28322-7_7, DOI 10.1007/978-0-585-28322-7_7]

[2]

[Anonymous], 1997, KARMA: Knowledge-based action representations for metaphor and aspect

[3]

[Anonymous], 2004, W3C RECOMMENDATION

[4]

Bolles B., 2004, HIERARCHICAL VIDEO E

[5]

BOLLES B, 2004, ARDA EVENT TAXONOMY

[6] Recognition of visual activities and interactions by stochastic parsing [J].

Ivanov, YA ;

Bobick, AF .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2000, 22 (08) :852-872

[7]

Martinez J. M., 2003, JTC1SC29WG11N5525 IS

[8]

NEVATIA R, 2003, P IEEE CVPR WORKSH E, P39

[9]

NEVATIA R, 2004, P IEEE WORKSH EV DET

[10] Creating Semantic Web contents with Protege-2000 [J].

Noy, NF ;

Sintek, M ;

Decker, S ;

Crubézy, M ;

Fergerson, RW ;

Musen, MA .

IEEE INTELLIGENT SYSTEMS & THEIR APPLICATIONS, 2001, 16 (02) :60-71

← 1 2 →