{"id":1184,"date":"2012-06-07T18:46:24","date_gmt":"2012-06-07T18:46:24","guid":{"rendered":"http:\/\/eccv2012.unifi.it\/?page_id=1184"},"modified":"2012-06-07T18:46:24","modified_gmt":"2012-06-07T18:46:24","slug":"internet-video-search","status":"publish","type":"page","link":"http:\/\/eccv2012.unifi.it\/program\/tutorials\/internet-video-search\/","title":{"rendered":"Internet Video Search"},"content":{"rendered":"

Organizers<\/strong>: Cees G.M. Snoek\u00a0(Univ. of Amsterdam, NL)<\/em>, Arnold W.M. Smeulders\u00a0(CWI, NL)<\/em>
\nDuration<\/strong>: half day
\nAbstract<\/strong>:\u00a0In this half\u2010day tutorial we focus on the computer vision challenges in internet video search, present methods how to achieve state\u2010of\u2010the\u2010art performance while maintaining efficient execution, and indicate how to obtain spatiotemporal improvements in the near future. Moreover, we give an overview of the latest developments and future trends in the field on the basis of the TRECVID competition \u2013 the leading competition for video search engines run by NIST \u2013 where we have achieved consistent top\u20102 performance over the years, including the 2008, 2009, 2010 and 2011 editions. This half\u2010day tutorial is especially meant for researchers and practitioners who are new to the field of video search (introductory), people who have started in this direction (intermediate), or people who are interested in a summary of the state\u2010of\u2010the\u2010art in this exciting area (general interest).<\/p>\n

Outline<\/strong>:<\/p>\n