You are here
Paper "Movie Genre Classification by Exploiting MEG Brain Signals" is accepted for publication in ICIAP 2015 proceedings
The paper presents joint work by Pouya Ghaemmaghami, Mojtaba Khomami Abadi, Seyed Mostafa Kia, Paolo Avesani, and Nicu Sebe. ICIAP 2015 is the 18th edition the 18th edition of the biannual International Conference on Image Analysis and Processing - a series of conferences organized by the Italian Member Society (GIRPR) of the International Association for Pattern Recognition (IAPR). The conference covers both classic and most recent trends in computer vision, pattern recognition and image processing, addressing both theoretical and applicative aspects.
Genre classification is an essential part of multimedia content recommender systems. In this study, we provide experimental evidence for the possibility of performing genre classification based on brain recorded signals. The brain decoding paradigm is employed to classify magnetoencephalography (MEG) data into four genre classes: Comedy, Romantic, Drama, and Horror. The results show that: 1) there is a significant correlation between audio-visual features of movies and corresponding brain signals specially in the visual and temporal lobes; 2) the genre of movie clips can be classified with an accuracy significantly over the chance level using the MEG signal. On top of that the combination of multimedia features and MEG-based features achieved the best accuracy. The study provides a primary step towards user-centric media content retrieval using brain signals.