TUD-MIR at MediaEval 2011 Genre Tagging Task: Query Expansion from a Limited Number of Labeled Videos
Stevan Rudinac, Martha A. Larson, Alan Hanjalić · MediaEval · 2011
this paper we present results of our initial res earch on genre tagging. We approach the task from information retr ieval perspec- tive using a relatively small number of labeled vid eos in the de- velopment set to mine query expansion terms characteristic of each genre. We also investigate which sources of in formation associated with the videos or extracted from their audio channel, e.g. title, description, tags and automatic speech recognition tran- scripts yield the highest improvement within our qu ery expansion framework. The experiments performed on MediaEval 2011 Genre Tagging dataset demonstrate the effectiveness of our ap- proach.