A comprehensive survey on image captioning: from handcrafted to deep learning-based techniques, a taxonomy and open research issues

What is it about?

A comprehensive survey of image captioning frameworks starting directly from template based models, followed by retrieval based models to state of the art attention and transformer based models along with a slight introduction of application domains in image captioning.

Featured Image

Why is it important?

For a novice researcher understanding the basic historical timeline of how image captioning frameworks evolved is combined in this single manuscript along with all the architectural advancements and explanations.