The work proposed here addresses the task of organizing the geo-referenced media on Flickr to generate Visual and Thematic Summarization of specified geo-location. The major challenge addressed in this work is: how to use the unstructured and unrestricted community contributed media and annotations to generate knowledge? The social tags associated with social images suffer from various problems such as, “free nature of tags”, “tag relevance”, and “cold start”. To deal with these problems, we consider ternary interrelations and multiple intra-relations among user, image and tag and model the relations using HOSVD, a Tensor Reduction Technique. As a result, context information for geo-location images is generated using user’s potential annotations. Content and context information for geo-location images and probabilistic generative model is utilized for location visualization. The novel visualization scheme proposed here summarizes the geo-location with a rich display landscape and provides location description using location representative tags. Experiments are performed on geo-tagged Flickr images for various geo-locations. The experimental results have validated the proposed method.

Tag Refinement, Tensor Factorization, Geo-Referenced Photos, Summarization, Clustering, Image Search, Collection Visualization

[1] Dimitrios Rafailidis, Petros Daras, (2013), “The TFC Model: Tensor Factorization and Tag Clustering for Item Recommendation in Social Tagging Systems”, IEEE Transactions On Systems, Man, And Cybernetics: Systems, Vol. 43, No. 3, May 2013
[2] Jaffe A, Naaman M, Tassa T, Davis M, (2006), “Generating Summaries And Visualization For large Collections Of Geo-Referenced Photographs”. In: Proceedings of the 8th ACM international workshop on multimedia information retrieval. ACM, New York, pp 89–98.
[3] Jitao Sang, Changsheng Xu, Dongyuan Lu,(2012), “User-Aware Image Tag Refinement via Ternary Semantic Analysis”, IEEE Transactions On Multimedia, Vol. 14, No. 3, June 2012.
[4] Kennedy L, Naaman M (2008) “Generating Diverse and Representative Image Search Results for Landmarks”. In: Proceeding of the 17th international conference on World Wide Web. ACM, New York, pp 297–306.
[5] Yan-Tao Zheng • Zheng-Jun Zha • Tat-Seng Chua (2011), “Research and applications on georeferenced multimedia: a survey," Multimed Tools Appl 51:77–98 DOI 10.1007/s11042-010-0630-z.
[6] Panagiotis Symeonidis, Alexandros Nanopoulos, and Yannis Manolopoulos, (2010), “A Unified Framework for Providing Recommendations in Social Tagging Systems Based on Ternary Semantic Analysis”, IEEE Tra nsactions On Knowledge And Data Engineering, Vol. 22, No. X, 2010 .
[7] Qiang Hao, Rui Cai, Xin-Jing Wang, Jiang-Ming Yang, Yanwei Pang, and Lei Zhang, 2009, “Generating Location Overviews with Images and Tags by Mining User-Generated Travelogues”, MM’09, October 19–24, 2009, Beijing, China.
[8] Quan Fang, Jitao Sang, Changsheng Xu, and Ke Lu, 2013, “Paint the City Colorfully: Location Visualization from Multiple Themes”, MMM 2013, Part I, LNCS 7732, pp. 92–105, 2013.
[9] Stevan Rudinac, Alan Hanjalic, Martha Larson, (2013) “Generating Visual Summaries of Geographic Areas Using Community-Contributed Images”, IEEE Transactions On Multimedia, Vol. 15, No. 4, June 2013.
[10] T. G. Kolda and B. W. Bader, (2009), “Tensor decompositions and applications,” SIAM Rev., vol. 51, no. 3, pp. 455–500, 2009.
[11] Thomas Hofmann, (1999), “Probabilistic Latent Semantic Indexing”. In Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval, SIGIR ’99, pages 50–57, New York, NY, USA, 1999. ACM.
[12] S.A. Takale, P.J. Kulkarni, “Extract Knowledge About Geo-Location Using Context and Content Information of Geo-Tagged Social Media”, LNCS Proceedings, Part I, of the 16th International Conference on Web Information Systems Engineering - WISE 2015 - Volume 9418 Pages 601-615.