Image Captioning using Visual Attention

This project aims at generating captions for images using neural language models. There has been a substantial increase in number of proposed models for image captioning task since neural language models and convolutional neural networks(CNN) became popular. Our project has its base on one of such works, which uses a variant of Recurrent neural network coupled with a CNN. We intend to enhance this model by making subtle changes to the architecture and using phrases as elementary units instead of words, which may lead to better semantic and syntactical captions.