TY  - GEN
N1  - This version is the author accepted manuscript. For information on re-use, please refer to the publisher?s terms and conditions.
TI  - Audiovisual, Genre, Neural and Topical Textual Embeddings for TV Programme Content Representation
EP  - 200
Y1  - 2021/01/22/
AV  - public
SP  - 197
CY  - Naples, Italy
KW  - Multimedia systems; Information filtering; Recommender systems; Content-based retrieval
A1  - Nazir, S
A1  - Cagali, T
A1  - Sadrzadeh, M
A1  - Newell, C
ID  - discovery10126932
N2  - TV programmes have their contents described by multiple means: textual subtitles, audiovisual files, and metadata such as genres. In order to represent these contents, we develop vectorial representations for their low-level multimodal features, group them with simple clustering techniques, and combine them using middle and late fusion. For textual features, we use LSI and Doc2Vec neural embeddings; for audio, MFCC's and Bags of Audio Words; for visual, SIFT, and Bags of Visual Words. We apply our model to a dataset of BBC TV programmes and use a standard recommender and pairwise similarity matrices of content vectors to estimate viewers' behaviours. The late fusion of genre, audio and video vectors with both of the textual embeddings significantly increase the precision and diversity of the results.
UR  - https://doi.org/10.1109/ISM.2020.00041
PB  - IEEE
ER  -