Abstract : We present a method for mining frequently occurring objects and scenes from videos. Object candidates are detected by finding recurring spatial arrangements of affine covariant regions. Our mining method is based on the class of frequent itemset mining algorithms, which have proven their efficiency in other domains, but have not been applied to video mining before. In this work we show how to express vector-quantized features and their spatial relations as itemsets. Furthermore, a fast motion segmentation method is introduced as an attention filter for the mining algorithm. Results are shown on real world data consisting of music video clips.
Hari Sundaram and Milind R. Naphade and John R. Smith and Yong Rui. International Conference on Image and Video Retrieval (CIVR '06), 2006, Tempe, United States. Springer-Verlag, 4071, pp.360--369, 2006, Lecture Notes in Computer Science (LNCS). 〈http://www.springerlink.com/content/5960q22u66204w51/〉. 〈10.1007/11788034_37〉
https://hal.inria.fr/inria-00548580
Contributeur : Thoth Team
<>
Soumis le : lundi 20 décembre 2010 - 09:49:20
Dernière modification le : mercredi 11 avril 2018 - 01:53:37
Document(s) archivé(s) le : lundi 21 mars 2011 - 03:19:47
Till Quack, Vittorio Ferrari, Luc Van Gool. Video mining with frequent itemset configurations. Hari Sundaram and Milind R. Naphade and John R. Smith and Yong Rui. International Conference on Image and Video Retrieval (CIVR '06), 2006, Tempe, United States. Springer-Verlag, 4071, pp.360--369, 2006, Lecture Notes in Computer Science (LNCS). 〈http://www.springerlink.com/content/5960q22u66204w51/〉. 〈10.1007/11788034_37〉. 〈inria-00548580〉
