Gated attention fusion network for multimodal sentiment classification

作者：

Highlights：

• A novel model named Gated Attention Fusion Network (GAFN) is proposed.

• GAFN uses object detection network to extract fine-grained image features.

• The gated attention mechanism is used to fuse image features and textual features.

• Our approach outperforms the SOTA model VistaNet on Yelp dataset.

摘要

•A novel model named Gated Attention Fusion Network (GAFN) is proposed.•GAFN uses object detection network to extract fine-grained image features.•The gated attention mechanism is used to fuse image features and textual features.•Our approach outperforms the SOTA model VistaNet on Yelp dataset.

论文关键词：Multimodal sentiment classification,Gated attention mechanism,Convolutional neural network,Feature fusion

论文评审过程：Received 29 April 2021, Revised 27 December 2021, Accepted 30 December 2021, Available online 5 January 2022, Version of Record 24 January 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2021.108107