A probabilistic topic model for event-based image classification and multi-label annotation

作者：

Highlights：

• Event recognition and image annotation in images using latent topic modeling.

• Supervised latent Dirichlet for modeling events, objects and scenes semantics.

• EM algorithm for simultaneous image classification and annotation.

• Convolutional neural networks for initial label extraction.

摘要

•Event recognition and image annotation in images using latent topic modeling.•Supervised latent Dirichlet for modeling events, objects and scenes semantics.•EM algorithm for simultaneous image classification and annotation.•Convolutional neural networks for initial label extraction.

论文关键词：Event recognition,Image annotation,Topic modeling,Convolutional neural nets

论文评审过程：Received 10 February 2019, Revised 2 May 2019, Accepted 24 May 2019, Available online 28 May 2019, Version of Record 29 May 2019.

论文官网地址：https://doi.org/10.1016/j.image.2019.05.012