UPC at MediaEval 2014 Social Event Detection Task

This working notes paper presents the contribution of the UPC team to the Social Event Detection (SED) Subtask 1 in MediaEval 2014. This contribution extends the solution tested in the previous year with a better optimization of the parameters that determine the clustering algorithm, and by introducing an additional pass that considers the merges of all pairs of mini-clusters generated during the two rst passes. Our proposal also addresses the problem of incomplete metadata by generating additional textual tags based on geolocation and natural language processing techniques.

[1]  Patrick Weber,et al.  OpenStreetMap: User-Generated Street Maps , 2008, IEEE Pervasive Computing.

[2]  David D. Cox,et al.  Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures , 2013, ICML.

[3]  Yiannis Kompatsiaris,et al.  Social Event Detection at MediaEval 2012: Challenges, Dataset and Evaluation , 2012, MediaEval.

[4]  Steven Bird,et al.  NLTK: The Natural Language Toolkit , 2002, ACL.

[5]  Daniel Manchon Vizuete,et al.  Photo clustering of social events by extending photoTOC to a rich context , 2014, ICMR 2014.

[6]  Steven Bird,et al.  NLTK: The Natural Language Toolkit , 2002, ACL 2006.

[7]  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.