Discovering Video Structure Using the PseudoSemantic Trace
Author
CM Taskiran, CA Bouman, EJ Delp
Entry type
inproceedings
Abstract
In this paper, we describe a framework of analyzing programs belonging to different TV program genres Hidden Markov Models and pseudo-semantic feature s derived from video shots. Clustering using Gaussian mixture models is used to determine the order of the modes. Results for initial genre classification experiments using two simple features derived from video shots are given.
Date
2001
Booktitle
Storage and Retrieval for Media Databases 2001
Journal
Proceedings of SPIE
Key alpha
Delp
Pages
571-578
Volume
4315
Publication Date
2001-01-01

