Browse DORAS
Browse Theses
Latest Additions
Creative Commons License
Except where otherwise noted, content on this site is licensed for use under a:

Movie indexing via event detection

Lehane, Bart and O'Connor, Noel E. (2006) Movie indexing via event detection. In: WIAMIS 2006 - 7th International Workshop on Image Analysis for Multimedia Interactive Services, 19-21 April 2006, Incheon, Korea.

Full text available as:

PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader


The past number of years has seen a large increase in the number of movies, and therefore movie databases, created. As movies are typically quite long, locating relevant clips in these databases is quite difficult unless a well defined index is in place. As movies are creatively made, creating automatic indexing algorithms is a challenging task. However, there are a number of underlying film grammar principles that are universally followed. By detecting and examining the use of these principles, it is possible to extract information about the occurrences of specific events in a movie. This work attempts to completely index a movie by detecting all of the relevant events. The event detection process involves examining the underlying structure of a movie and utilising audiovisual analysis techniques, supported by machine learning algorithms, to extract information based on this structure. This results in a summarised and indexed movie.

Item Type:Conference or Workshop Item (Paper)
Event Type:Workshop
Subjects:Computer Science > Digital video
Computer Science > Information retrieval
DCU Faculties and Centres:Research Initiatives and Centres > Centre for Digital Video Processing (CDVP)
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:Enterprise Ireland, European Commission IST-2000-32795
ID Code:398
Deposited On:01 Apr 2008 by DORAS Administrator. Last Modified 05 May 2010 14:13

Download statistics

Archive Staff Only: edit this record