Neural attention for image captioning: review of outstanding methods

Image captioning is the task of automatically generating sentences that describe an input image in best way possible. The most successful techniques for captions have recently used attentive deep learning models. There are variations models with attention designed. In this survey, we provide a review literature related to captioning. Instead offering comprehensive all prior work on models, explain various types mechanisms follow encoder-decoder architecture, although there differences these employ mechanisms. Via analysis performance results from different captioning, aim at finding Soft attention, bottom-up and multi-head mechanism widely state-of-the-art At current time, achieved variants attention.