B. Ionescu, Klaus Seyerlehner, I. Mironica, C. Vertan, P. Lambert,
"Automatic Web Video Categorization Using Audio-Visual Information and Hierarchical Clustering RF"
: Proceedings of the 20thEuropean Signal Processing Conference, Seite(n) 375-379, 2012
Original Titel:
Automatic Web Video Categorization Using Audio-Visual Information and Hierarchical Clustering RF
Sprache des Titels:
Englisch
Original Buchtitel:
Proceedings of the 20thEuropean Signal Processing Conference
Original Kurzfassung:
In this paper, we discuss and audio-visual approach to automatic
web video categorization. We propose content descriptors
which exploit audio, temporal, and color content. The
power of our descriptors was validated both in the context of
a classification system and as part of an information retrieval
approach. For this purpose, we used a real-world scenario,
comprising 26 video categories from the blip.tv media platform
(up to 421 hours of video footage). Additionally, to
bridge the descriptor semantic gap, we propose a new relevance
feedback technique which is based on hierarchical clustering.
Experiments demonstrated that retrieval performance
can be increased significantly and becomes comparable to that
of high level semantic textual descriptors.
Forschungs-