“…Decoder: Depending on the encoding strategy used, the textual decoders also vary from plain unidirectional RNN [133] generating a word at a time to hierarchical RNN decoders [12] performing this step in multiple levels of granularity. Although a vast majority of neural models focus only on generating textual summary using multi-modal information as input [13,56,57,62,62,83,83], some work also output images as an supplement to the generated summary [12,29,61,133,134]; reinforcing the textual information and improving the user experience. These works either use a post-processing strategy to select the image(s) to become a part of final multi-modal summary [12,133], or they incorporate this functionality in their proposed model [29,61,134].…”