by Brachmann, Christoph, Chunpir, Hashim I., Gennies, S., Haller, B., Hermes, Thorsten, Herzog, Otthein, Jacobs, Arne and Kehl, Philipp, Mochtarram, Astrid P., Möhlmann, Daniel and Schrumpf, Christian, Schultz, C., Stolper, B. and Walther-Franks, Benjamin
Abstract:
With the advances in digital audio and video analysis, automatic movie summarization has become an important field of research. Much of the work has been put into movie abstracting for large media databases. Looking at the topic from a different side, the movie industry has long since perfected the art of summarization in their advertising trailers to attract an audience. In this paper we introduce the approach of automatically generating entertaining Hollywood-like trailers based on a trailer grammar, enhanced by an ontology. The extraction of features from movies using state-of-the-art image and audio processing techniques builds the foundation for the selection of meaningful and usable material, which is re-assembled according to the defined rules. User testing of our automatically produced trailers shows that they are well accepted and in many ways comparable to professionally composed trailers.
Reference:
Brachmann, Christoph, Chunpir, Hashim I., Gennies, S., Haller, B., Hermes, Thorsten, Herzog, Otthein, Jacobs, Arne and Kehl, Philipp, Mochtarram, Astrid P., Möhlmann, Daniel and Schrumpf, Christian, Schultz, C., Stolper, B. and Walther-Franks, Benjamin, "Automatic Generation of Movie Trailers using Ontologies", In IMAGE - Journal of Interdisciplinary Image Science, vol. 5, pp. 117–139, 2007.
Bibtex Entry:
@ARTICLE{Brachmann2007,
author = {Brachmann, Christoph and Chunpir, Hashim I. and Gennies, S. and Haller,
B. and Hermes, Thorsten and Herzog, Otthein and Jacobs, Arne and
Kehl, Philipp and Mochtarram, Astrid P. and M{\"o}hlmann, Daniel
and Schrumpf, Christian and Schultz, C. and Stolper, B. and Walther-Franks,
Benjamin},
title = {Automatic Generation of Movie Trailers using Ontologies},
journal = {IMAGE - Journal of Interdisciplinary Image Science},
year = {2007},
volume = {5},
pages = {117--139},
abstract = {With the advances in digital audio and video analysis, automatic movie
summarization has become an important field of research. Much of
the work has been put into movie abstracting for large media databases.
Looking at the topic from a different side, the movie industry has
long since perfected the art of summarization in their advertising
trailers to attract an audience. In this paper we introduce the approach
of automatically generating entertaining Hollywood-like trailers
based on a trailer grammar, enhanced by an ontology. The extraction
of features from movies using state-of-the-art image and audio processing
techniques builds the foundation for the selection of meaningful
and usable material, which is re-assembled according to the defined
rules. User testing of our automatically produced trailers shows
that they are well accepted and in many ways comparable to professionally
composed trailers.},
owner = {pmania},
timestamp = {2012.11.06}
}