Canonical Correlation Inference for Mapping Abstract Scenes to Text

Nikos Papasarantopoulos, Helen Jiang, Shay B. Cohen

AAAI 2018 pp. 5358-5365

doi:10.1609/AAAI.V32I1.11958 /aaai/2018/papasarantopoulos2018aaai-canonical/

Abstract

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".

PDF AAAI Semantic Scholar

Cite

Text

Papasarantopoulos et al. "Canonical Correlation Inference for Mapping Abstract Scenes to Text." AAAI Conference on Artificial Intelligence, 2018. doi:10.1609/AAAI.V32I1.11958

Markdown

[Papasarantopoulos et al. "Canonical Correlation Inference for Mapping Abstract Scenes to Text." AAAI Conference on Artificial Intelligence, 2018.](https://mlanthology.org/aaai/2018/papasarantopoulos2018aaai-canonical/) doi:10.1609/AAAI.V32I1.11958

BibTeX

@inproceedings{papasarantopoulos2018aaai-canonical,
  title     = {{Canonical Correlation Inference for Mapping Abstract Scenes to Text}},
  author    = {Papasarantopoulos, Nikos and Jiang, Helen and Cohen, Shay B.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2018},
  pages     = {5358-5365},
  doi       = {10.1609/AAAI.V32I1.11958},
  url       = {https://mlanthology.org/aaai/2018/papasarantopoulos2018aaai-canonical/}
}