Generating Comprehensible Summaries of Rushes Sequences based on Robust Feature Matching
Access Status
Fulltext not available
Authors
Truong, Ba
Venkatesh, Svetha
Date
2007Type
Conference Paper
Metadata
Show full item recordCitation
Truong, B. and Venkatesh, S. 2007. Generating Comprehensible Summaries of Rushes Sequences based on Robust Feature Matching, in Wang, J.Z. et al (ed), Proceedings of the 9th ACM SIGMM International Workshop on Multimedia Information Retrieval (MIR 2007), Sep 24-29 2007, pp. 30-34. Augsburg, Germany: Association for Computing Machinery (ACM).
Source Title
Compilation Proceedings of MM'07 & Co-Located Workshops
Source Conference
TVS'07 Workshop held at the ACM Mulitmedia 2007
ISBN
School
Department of Computing
Collection
Abstract
This paper describes our first attempt at tackling a pilot task in Trecvid: video summarization of rushes data [3]. Our method is based on the tight clustering produced via SIFT matching. In this first attempt, we try to examine how our approach performs without complex implementation in terms of concept detection and excerpt assembly (i.e, no picture-in-picture, split screen and special transitions). Although we do not perform very well in terms of concept inclusion, we rank very well in terms of the summary being easy to understand and relevancy of included segments.