|Proceedings of the 2nd International Conference on Semantics And digital Media Technologies (SAMT'07)
|J. Nemrava, P. Buitelaar, T. Declerck, V. Svátek, J. Petrák, A. Cobet, H. Zeiner, D. Sadlier, N. O’Connor
|Enhancing Video Analysis Results using Complementary Textual Resources
|In this document we deal with different sources of information complementary to audio-visual streams and propose their usage for enriching this data with semantic concepts in order to bridge the gap between low-level video analysis 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 resources analysis and discuss domain dependency aspects of this approach connected to our initial domain of football broadcasts.
|ow-level, high-level, cross-media feature descriptors, text detection, video OCR