Title :
Visualization approach based on multimedia clustering
Author :
Zhao, Wei ; Zhang, Junsheng ; Sun, Yunchuan
Author_Institution :
Network&Educ. Technol. Center, Renmin Univ. of China, Beijing
fDate :
July 31 2008-Aug. 1 2008
Abstract :
Multimedia is one kind of the most important resources on the current Web. To search and browse the multi-media content efficiently, it is necessary to improve the multimedia retrieval and classification approaches. For a multimedia snippet, the annotated tags and introduction texts around the multimedia can reflect the content and characteristics of the multimedia. This paper proposes an efficient approach to cluster and visualize the multimedia by constructing semantic field with a set of multimedia tags. A semantic field is a circle region with several gravitation sources (tags)to locate a multimedia by calculating the positions in the field. We have developed an experiment on audio clustering for about 1000 multimedia resources including images, audios, and videos using the semantic field approach, and the result shows the approach is efficient.
Keywords :
data visualisation; information retrieval; multimedia computing; pattern clustering; semantic networks; text analysis; audio clustering; classification approaches; gravitation sources; multimedia clustering; multimedia contents; multimedia retrieval; multimedia visualization; semantic fields; Clustering algorithms; Content based retrieval; Data visualization; Educational technology; Face recognition; Machine learning algorithms; Sun; Support vector machine classification; Support vector machines; Videos; clustering; multimedia; similarity; tags; visualization;
Conference_Titel :
Ubi-Media Computing, 2008 First IEEE International Conference on
Conference_Location :
Lanzhou
Print_ISBN :
978-1-4244-1865-7
Electronic_ISBN :
978-1-4244-1866-4
DOI :
10.1109/UMEDIA.2008.4570888
