TY - JOUR
AU1 - Cornia, Marcella
AU2 - Baraldi, Lorenzo
AU3 - Tavakoli, Hamed R.
AU4 - Cucchiara, Rita
AB - Text-image retrieval has been recently becoming a hot-spot research field, thanks to the development of deeply-learnable architectures which can retrieve visual items given textual queries and vice-versa. The key idea of many state-of-the-art approaches has been that of learning a joint multi-modal embedding space in which text and images could be projected and compared. Here we take a different approach and reformulate the problem of text-image retrieval as that of learning a translation between the textual and visual domain. Our proposal leverages an end-to-end trainable architecture that can translate text into image features and vice versa and regularizes this mapping with a cycle-consistency criterion. Experimental evaluations for text-to-image and image-to-text retrieval, conducted on small, medium and large-scale datasets show consistent improvements over the baselines, thus confirming the appropriateness of using a cycle-consistent constrain for the text-image matching task.
TI - A unified cycle-consistent neural model for text and image retrieval
JF - Multimedia Tools and Applications
DO - 10.1007/s11042-020-09251-4
DA - 2020-09-06
UR - https://www.deepdyve.com/lp/springer-journals/a-unified-cycle-consistent-neural-model-for-text-and-image-retrieval-fFCiOVo0JR
SP - 25697
EP - 25721
VL - 79
IS - 35-36
DP - DeepDyve
ER -