Survey of convolutional neural networks for image captioning
Saloni Kalra, Alka Leekha · Journal of Information and Optimization Sciences · 2020
Image captioning refers to a machine generatating human-like captions describing the image. With the recent surge of interest in the field, deep learning models have been proved to give state-of-the-art. Unlike most of the models using CNN for image embedding and RNN for language modeling and prediction, there is a small section of models using CNN for language modeling and prediction as well. This paper provides a survey of such models and the advantage that make this section worth exploring.