A Unified Framework for Retrieving Diverse Social Images
Maia Zaharieva, Patrick M. Schwab · 2014
In this paper we explore the performance of a generic, uni-fied framework for the retrieval of relevant and diverse im-ages from social photo collections. The approach allows for the easy evaluation of different visual and textual im-age descriptions, clustering algorithms, and similarity met-rics. Preliminary results show strong dependance between the choice of underlying technology and similarity metric, and the achieved performance. 1.