Visual-textual sentiment classification with bi-directional multi-level attention networks

作者：

Highlights：

• Bi-directional attention to highlight the emotional regions and words.

• Multiple levels to excavate the emotional correlations between image and text.

• The experimental results demonstrate the superiority of the proposed model.

摘要

•Bi-directional attention to highlight the emotional regions and words.•Multiple levels to excavate the emotional correlations between image and text.•The experimental results demonstrate the superiority of the proposed model.

论文关键词：Multi-modal,Social image,Attention model,Sentiment analysis

论文评审过程：Received 28 November 2018, Revised 22 April 2019, Accepted 23 April 2019, Available online 9 May 2019, Version of Record 4 June 2019.

论文官网地址：https://doi.org/10.1016/j.knosys.2019.04.018