Exploring The Semantic Gap for Movie Recommendation

Published in Proceedings of the 11th ACM Conference on Recommender Systems, 2017

Recommended citation: Mehdi Elahi, Yashar Deldjoo, Farshad B. Moghaddam, Leonardo Cella, Stefano Cereda, Paolo Cremonesi Proceedings of 11th ACM Conference of Recommender Systems 2017 (RecSys 2017).

[DOI] [PDF] [bibtex]


In the last years, there has been much attention given to the semantic gap problem in multimedia retrieval systems. Much effort has been devoted to bridge this gap by building tools for the extraction of high-level, semantics-based features from multimedia content, as low-level features are not considered useful because they deal primarily with representing the perceived content rather than the semantics of it. In this paper, we explore a different point of view by leveraging the gap between low-level and high-level features. We experiment with a recent approach for movie recommendation that extract low-level Mise-en- Scéne features from multimedia content and combine it with high-level features provided by the wisdom of the crowd.