Bilkent University Multimedia Database Group at TRECVID 2008
Date
2008-11Source Title
2008 TREC Video Retrieval Evaluation Notebook Papers
Publisher
National Institute of Standards and Technology
Language
English
Type
Conference PaperItem Usage Stats
85
views
views
16
downloads
downloads
Abstract
Bilkent University Multimedia Database Group (BILMDG) participated in two tasks at TRECVID 2008: content-based copy detection (CBCD) and high-level feature extraction (FE). Mostly MPEG-7 [1] visual features, which are also used as low-level features in our MPEG-7 compliant video database management system, are extracted for these tasks. This paper discusses our approaches in each task.
Keywords
Database systemsFeature extraction
Content-based copy detections
High-level feature extractions
Low-level features
Multimedia database
TRECVID
Video database management
Visual feature
Motion Picture Experts Group standards