This is an implementation of the paper Comparative evaluation of CNN architectures forImage Caption Generation which has been accepted in the journal International Journal of Advanced Computer Science and Applications. In this work, we compare the efficacy of different Convolutional Neural Network models for use as encoders for extracting visual information from images which can then be used by the decoder (or the Caption Generator module) to generate the sentence one word at a time.
Note: This is a work in progress. The whole project will be uploaded soon. The paper will be linked as soon as it is published in the upcoming issue.