The complementarity of a diverse range of deep learning features extracted from video content for video recommendation

TL;DR

This paper investigates the use of diverse deep learning features from video content, such as visual, audio, and motion information, to improve video recommendation systems, especially for new items, by exploring effective fusion methods.

Contribution

It demonstrates that deep learning features outperform traditional hand-crafted features and that combining multiple modalities enhances recommendation accuracy.

Findings

Deep learning features outperform hand-crafted features.

Audio and action-centric features are particularly effective.

Combining multiple features yields significant recommendation improvements.

Abstract

Following the popularisation of media streaming, a number of video streaming services are continuously buying new video content to mine the potential profit from them. As such, the newly added content has to be handled well to be recommended to suitable users. In this paper, we address the new item cold-start problem by exploring the potential of various deep learning features to provide video recommendations. The deep learning features investigated include features that capture the visual-appearance, audio and motion information from video content. We also explore different fusion methods to evaluate how well these feature modalities can be combined to fully exploit the complementary information captured by them. Experiments on a real-world video dataset for movie recommendations show that deep learning features outperform hand-crafted features. In particular, recommendations generated with deep learning audio features and action-centric deep learning features are superior to MFCC and state-of-the-art iDT features. In addition, the combination of various deep learning features with hand-crafted features and textual metadata yields significant improvement in recommendations compared to combining only the former.