Repeated review based image captioning for image evidence review
作者：
Highlights：
•
• A repeated review deep learning model is proposed for image captioning.
• The model employed two word embedding layers to extract the context information.
• A multimodal layer can fuse the source image information and the context information.
• The proposed model performs well on benchmark datasets.
摘要
•A repeated review deep learning model is proposed for image captioning.•The model employed two word embedding layers to extract the context information.•A multimodal layer can fuse the source image information and the context information.•The proposed model performs well on benchmark datasets.
论文关键词：Repeated review,Image captioning,Encoder–decoder,Multimodal layer
论文评审过程：Received 2 December 2017, Revised 31 January 2018, Accepted 5 February 2018, Available online 13 February 2018, Version of Record 16 March 2018.
论文官网地址：https://doi.org/10.1016/j.image.2018.02.005
