Detecting Multimedia Contents of Social Events in Social Networks

Friends visit many social events together, take photos of each other and upload them in several accounts in different types of social media such as Flickr or Facebook. In this chapter we define the different types of events in social media and introduce two approaches in the state of the art of detecting the media content of an event. The first is an ontology-based approach where the metadata is basically used to obtain the content of a well-defined event and the visual features are used to prune the results to finally get the illustrative elements. The second approach exploits a mixture of features (visual, social, structural and metadata) that we also explain in this chapter and fuses them in a probabilistic model to link the media elements of different users and albums to their representative event. We discuss the advantage and disadvantage of each approach and the cases of using each.

[1]  Yiannis Kompatsiaris,et al.  A Joint Content-Event Model for Event-Centric Multimedia Indexing , 2010, 2010 IEEE Fourth International Conference on Semantic Computing.

[2]  Daniel Gatica-Perez,et al.  Analyzing Flickr groups , 2008, CIVR '08.

[3]  Minglun Gong,et al.  Organizing and browsing photos using different feature vectors and their evaluations , 2009, CIVR '09.

[4]  Raphaël Troncy,et al.  Finding media illustrating events , 2011, ICMR '11.

[5]  Ramesh C. Jain,et al.  Automatic Person Annotation of Family Photo Album , 2006, CIVR.

[6]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[7]  Ramesh Jain,et al.  Toward a Common Event Model for Multimedia Applications , 2007, IEEE MultiMedia.

[8]  Marc Gelgon,et al.  Organizing a personal image collection with statistical model-based ICL clustering on spatio-temporal camera phone meta-data , 2004, Journal of Visual Communication and Image Representation.

[9]  Susanne Boll,et al.  Analysing Facebook features to support event detection for photo-based Facebook applications , 2012, ICMR '12.

[10]  Mary Czerwinski,et al.  PhotoTOC: automatic clustering for browsing personal photographs , 2003, Fourth International Conference on Information, Communications and Signal Processing, 2003 and the Fourth Pacific Rim Conference on Multimedia. Proceedings of the 2003 Joint.

[11]  Kazuya Shimizu,et al.  Classification based group photo retrieval with bag of people features , 2012, ICMR '12.

[12]  Trevor Darrell,et al.  Toward Large-Scale Face Recognition Using Social Network Context , 2010, Proceedings of the IEEE.

[13]  Bernard Mérialdo,et al.  Saliency moments for image categorization , 2011, ICMR.

[14]  Tao Mei,et al.  Probabilistic Multimodality Fusion for Event based Home Photo Clustering , 2006, 2006 IEEE International Conference on Multimedia and Expo.

[15]  Susanne Boll,et al.  Automatic creation of photo books from stories in social media , 2011, TOMCCAP.

[16]  Yutaka Matsuo,et al.  Earthquake shakes Twitter users: real-time event detection by social sensors , 2010, WWW '10.

[17]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[18]  Lexing Xie,et al.  Modeling personal and social network context for event annotation in images , 2007, JCDL '07.

[19]  J.E. Gentile,et al.  Profile Face Detection: A Subset Multi-Biometric Approach , 2008, 2008 IEEE Second International Conference on Biometrics: Theory, Applications and Systems.