Cosine Similarity of Multimodal Content Vectors for TV Programmes
This work addresses the challenge of improving recommendation systems for TV viewers by integrating audio, text, and metadata, though it is incremental as it builds on existing fusion techniques.
The paper tackled the problem of representing and combining multimodal content from TV programmes to compute semantic similarities for recommendations, achieving significant improvements in precision and diversity with late fused similarity matrices.
Multimodal information originates from a variety of sources: audiovisual files, textual descriptions, and metadata. We show how one can represent the content encoded by each individual source using vectors, how to combine the vectors via middle and late fusion techniques, and how to compute the semantic similarities between the contents. Our vectorial representations are built from spectral features and Bags of Audio Words, for audio, LSI topics and Doc2vec embeddings for subtitles, and the categorical features, for metadata. We implement our model on a dataset of BBC TV programmes and evaluate the fused representations to provide recommendations. The late fused similarity matrices significantly improve the precision and diversity of recommendations.