Title :
Relational Social Image Search
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of Toronto, Toronto, ON, Canada
Abstract :
This paper proposes a method of finding the relationship between objects based on their spatial arrangement in a set of tagged images. Based on the relative coordinates of each object tag, we compute a joint Relativity between each tag pair. We then propose an efficient image search method using the joint Relativity graphs and provide simple examples where the proposed Relational Social Image (RSI) search produces more relevant and intuitive results than simple search.
Keywords :
graph theory; image retrieval; social sciences computing; RSI search method; joint relativity graphs; relational social image search method; relative object tag coordinates; spatial arrangement objects; tagged images; Computers; Joints; Method of moments; Multimedia communication; Search problems; Silicon; Visualization; image; search; social; tags; visual;
Conference_Titel :
Multimedia (ISM), 2013 IEEE International Symposium on
Conference_Location :
Anaheim, CA
Print_ISBN :
978-0-7695-5140-1
DOI :
10.1109/ISM.2013.105
