We describe a technique for structured prediction, based on canonical correlation analysis. Our learning algorithm finds two projections for the input and the output spaces that aim at projecting a given input and its correct output into points close to each other. We demonstrate our technique on a language-vision problem, namely the problem of giving a textual description to an "abstract scene".
@article{arxiv.1608.02784,
title = {Canonical Correlation Inference for Mapping Abstract Scenes to Text},
author = {Nikos Papasarantopoulos and Helen Jiang and Shay B. Cohen},
journal= {arXiv preprint arXiv:1608.02784},
year = {2017}
}