Skip to main content Skip to main navigation

Publikation

An Architecture for Mining Resources Complementary to Audio-Visual Streams.

Jan Nemrava; Paul Buitelaar; Thierry Declerck; V. Svátek; J. Petrák; A. Cobet; H. Zeiner; D. Sadlier; N. O'Connor; N. Simou; V. Tzouvaras
In: T. Bürger; S. Dasiopoulou; C. Eckes; et al. (Hrsg.). Proceedings of KAMC - Knowledge Acquisition from Multimedia Content - workshop at SAMT07 (International Conference on Semantics And digital Media Technologies). Knowledge Acquisition from Multimedia Content Workshop (KAMC), Vol. 253, CEUR Workshop Proceedings (Online), 2007.

Zusammenfassung

In this paper we attempt to characterize resources of information complementary to audio-visual (A/V) streams and propose their usage for enriching A/V data with semantic concepts in order to bridge the gap between low-level video detectors and high-level analysis. Our aim is to extract cross-media feature descriptors from semantically enriched and aligned resources so as to detect finer-grained events in video.We introduce an architecture for complementary resource analysis and discuss domain dependency aspects of this approach related to our domain of soccer broadcasts.

Weitere Links