<XML><RECORDS><RECORD><REFERENCE_TYPE>3</REFERENCE_TYPE><REFNUM>8948</REFNUM><AUTHORS><AUTHOR>Reede,R.e.n.</AUTHOR><AUTHOR>Punitha,P.</AUTHOR><AUTHOR>Jose,J.M.</AUTHOR></AUTHORS><YEAR>2008</YEAR><TITLE>Video Redundancy Detection in Rushes Collection</TITLE><PLACE_PUBLISHED>ACM MM workshop on Video Summarization</PLACE_PUBLISHED><PUBLISHER>N/A</PUBLISHER><LABEL>Reede:2008:8948</LABEL><KEYWORDS><KEYWORD>video summarisation</KEYWORD></KEYWORDS<ABSTRACT>The rushes is a collection of raw material videos. There are various redundancies, such as rainbow screen, clipboard shot, white/black view, and unnecessary re-take. This pa- per develops a set of solutions to remove these video redun- dancies as well as an e®ective system for video summarisa- tion. We regard manual editing e®ects, e.g. clipboard shots, as di®erentiators in the visual language. A rushes video is therefore divided into a group of subsequences, each of which stands for a re-take instance. A graph matching algorithm is proposed to estimate the similarity between re-takes and suggests the best instance for content presentation. The ex- periments on the Rushes 2008 collection show that a video can be shortened to 4%-16% of the original size by redun- dancy detection. This signi¯cantly reduces the complexity in content selection and leads to an e®ective and e±cient video summarisation system.</ABSTRACT></RECORD></RECORDS></XML>