CAM: A fine-grained vehicle model recognition method based on visual attention model

作者：

Highlights：

• A well-designed fine-grained vehicle model recognition method based on a two-stage attention mechanism CAM.

• CAM includes two parts, one focus on global feature attention weighting and another focus on mining the spatial relationship of local features.

• CAM can enhance the subtle difference of features and their spatial encoding.

摘要

•A well-designed fine-grained vehicle model recognition method based on a two-stage attention mechanism CAM.•CAM includes two parts, one focus on global feature attention weighting and another focus on mining the spatial relationship of local features.•CAM can enhance the subtle difference of features and their spatial encoding.

论文关键词：Vehicle model recognition,Visual attention mechanism,Long short-term memory (LSTM) network,Convolutional LSTM

论文评审过程：Received 24 February 2020, Revised 21 June 2020, Accepted 22 September 2020, Available online 2 October 2020, Version of Record 16 October 2020.

论文官网地址：https://doi.org/10.1016/j.imavis.2020.104027