CASIS: a system for concept-aware social image search

ABSTRACT

Tag-based social image search enables users to formulate queries using keywords. However, as queries are usually very short and users have very different interpretations of a particular tag in annotating and searching images, the returned images to a tag query usually contain a collection of images related to multiple concepts. We demonstrate Casis, a system for concept-aware social image search. Casis detects tag concepts based on the collective knowledge embedded in social tagging from the initial results to a query. A tag concept is a set of tags highly associated with each other and collectively conveys a semantic meaning. Images to a query are then organized by tag concepts. Casis provides intuitive and interactive browsing of search results through a tag concept graph, which visualizes the tags defining each tag concept and their relationships within and across concepts. Supporting multiple retrieval methods and multiple concept detection algorithms, Casis offers superior social image search experiences by choosing the most suitable retrieval methods and concept-aware image organizations.

References

1. S. Ahern, M. Naaman, R. Nair, and J. H.-I. Yang. World explorer: visualizing aggregate data from unstructured text in geo-referenced collections. In JCDL, pages 1--10, 2007.
2. C. Carpineto, S. Osi'nski, G. Romano, and D. Weiss. A survey of web clustering engines. ACM Comput. Surv., 41:17:1--17:38, July 2009.
3. Y. Chen, J. Z. Wang, and R. Krovetz. Content-based image retrieval by clustering. In MIR, pages 193--200, 2003.
4. M. Dubinko, R. Kumar, J. Magnani, J. Novak, P. Raghavan, and A. Tomkins. Visualizing tags over time. In WWW, pages 193--202, 2006.
5. P.-A. Moëllic, J.-E. Haugeard, and G. Pitel. Image clustering based on a shared nearest neighbors approach for tagged collections. In CIVR, pages 269--278, 2008.
6. S. E. Overell, B. Sigurbjörnsson, and R. van Zwol. Classifying tags using open content resources. In WSDM, pages 64--73, 2009.
7. A. Popescu and P.-A. Moëllic. Olive: a conceptual web image search engine. In ACM Multimedia, pages 147--148, 2007.
8. B. Sigurbjörnsson and R. van Zwol. TagExplorer: Faceted browsing of flickr photos. Technical Report YL-2010-005, Yahoo! Research.
9. A. Sun, S. S. Bhowmick, and J.-A. Chong. Social image tag recommendation by concept matching. In ACM Multimedia, pages 1181--1184, 2011.
10. A. Sun, S. S. Bhowmick, K. T. Nam Nguyen, and G. Bai. Tag-based social image retrieval: An empirical evaluation. JASIST, 62(12):2364--2381, 2011.
11. R. van Zwol, B. Sigurbjörnsson, R. Adapala, L. G. Pueyo, A. Katiyar, K. Kurapati, M. Muralidharan, S. Muthu, V. Murdock, P. Ng, A. Ramani, A. Sahai, S. T. Sathish, H. Vasudev, and U. Vuyyuru. Faceted exploration of image search results. In WWW, pages 961--970, 2010.
12. S. Wang, F. Jing, J. He, Q. Du, and L. Zhang. Igroup: presenting web image search results in semantic clusters. In CHI, pages 587--596, 2007.

Index Terms

• Information systems

  • Information retrieval

    • Retrieval tasks and goals

      • Document filtering

      • Information extraction