Automatic sub-category partitioning and parts localization for learning a robust object model

作者：

Highlights：

• The ideas of sub-category and part-based are used to learn a robust object model.

• A novel object representation is proposed based on the topic model.

• An iterative learning process is presented under the semi-supervision way.

摘要

•The ideas of sub-category and part-based are used to learn a robust object model.•A novel object representation is proposed based on the topic model.•An iterative learning process is presented under the semi-supervision way.

论文关键词：Object model,Topic model,Layout topic,Sub-category partitioning,Part localization

论文评审过程：Received 30 November 2012, Revised 10 March 2014, Accepted 26 June 2014, Available online 3 July 2014.

论文官网地址：https://doi.org/10.1016/j.imavis.2014.06.007