Cross-modal retrieval has been recently becoming an hot-spot research, thanks to the development of deeply-learnable architectures. Such architectures generally learn a joint multi-modal embedding space in which text and images could be projected and compared. Here we investigate a different approach, and reformulate the problem of cross-modal retrieval as that of learning a translation between the textual and visual domain. In particular, we propose an end-to-end trainable model which can translate text into image features and vice versa, and regularizes this mapping with a cycle-consistency criterion. Preliminary experimental evaluations show promising results with respect to ordinary visual-semantic models.
Towards Cycle-Consistent Models for Text and Image Retrieval / Cornia, Marcella; Baraldi, Lorenzo; Rezazadegan Tavakoli, Hamed; Cucchiara, Rita. - (2019). (Intervento presentato al convegno European Conference on Computer Vision (ECCV) Workshops tenutosi a Munich, Germany nel 8-14 September 2018) [10.1007/978-3-030-11018-5_58].