Enhanced movie content similarity based on textual, auditory and visual information

作者：

Highlights：

• Textual, audio, visual features and metadata are used to calculate content similarity.

• A content-based recommendation system to support existing approaches is proposed.

• Proved that low-level features can capture high-level concepts of cinematic styles.

摘要

•Textual, audio, visual features and metadata are used to calculate content similarity.•A content-based recommendation system to support existing approaches is proposed.•Proved that low-level features can capture high-level concepts of cinematic styles.

论文关键词：Content-based movie recommendation,Topic modeling,Movie audio-Visual analysis,Multimodal fusion,Information retrieval

论文评审过程：Received 8 August 2017, Revised 23 November 2017, Accepted 24 November 2017, Available online 28 November 2017, Version of Record 22 December 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.11.050