Canonical Correlation Inference for Mapping Abstract Scenes to Text

Nikolaos Papasarantopoulos; Helen Jiang; Shay Cohen

Canonical Correlation Inference for Mapping Abstract Scenes to Text

Nikolaos Papasarantopoulos, Helen Jiang, Shay Cohen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

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.”

Original language	English
Title of host publication	Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)
Publisher	Association for the Advancement of Artificial Intelligence
Pages	5358-5365
Number of pages	8
ISBN (Print)	978-1-57735-800-8
Publication status	E-pub ahead of print - 7 Dec 2018
Event	Thirty-Second AAAI Conference on Artificial Intelligence - Hilton New Orleans Riverside, New Orleans, United States Duration: 2 Feb 2018 → 7 Feb 2018 https://aaai.org/Conferences/AAAI-18/ https://aaai.org/Conferences/AAAI-18/

Publication series

Name
Publisher	AAAI
ISSN (Electronic)	2374-3468

Conference

Conference	Thirty-Second AAAI Conference on Artificial Intelligence
Abbreviated title	AAAI 2018
Country/Territory	United States
City	New Orleans
Period	2/02/18 → 7/02/18
Internet address	https://aaai.org/Conferences/AAAI-18/ https://aaai.org/Conferences/AAAI-18/

Access to Document

aaai18ccaAccepted author manuscript, 649 KB

https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16365/16088
https://aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16365Licence: All Rights Reserved

SUMMA - Scalable Understanding of Mulitingual Media
Renals, S. (Principal Investigator), Birch-Mayne, A. (Co-investigator) & Cohen, S. (Co-investigator)
EU government bodies
1/02/16 → 31/01/19
Project: Research

Cite this

Papasarantopoulos, N., Jiang, H., & Cohen, S. (2018). Canonical Correlation Inference for Mapping Abstract Scenes to Text. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) (pp. 5358-5365). Association for the Advancement of Artificial Intelligence. Advance online publication. https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16365/16088

@inproceedings{14a893dc9c8b4363b05b8c50f365bfc2,

title = "Canonical Correlation Inference for Mapping Abstract Scenes to Text",

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.”",

author = "Nikolaos Papasarantopoulos and Helen Jiang and Shay Cohen",

year = "2018",

month = dec,

day = "7",

language = "English",

isbn = "978-1-57735-800-8",

publisher = "Association for the Advancement of Artificial Intelligence",

pages = "5358--5365",

booktitle = "Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)",

note = "Thirty-Second AAAI Conference on Artificial Intelligence, AAAI 2018 ; Conference date: 02-02-2018 Through 07-02-2018",

url = "https://aaai.org/Conferences/AAAI-18/, https://aaai.org/Conferences/AAAI-18/",

}

Papasarantopoulos, N, Jiang, H & Cohen, S 2018, Canonical Correlation Inference for Mapping Abstract Scenes to Text. in Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18). Association for the Advancement of Artificial Intelligence, pp. 5358-5365, Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, Louisiana, United States, 2/02/18. <https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16365/16088>

Canonical Correlation Inference for Mapping Abstract Scenes to Text. / Papasarantopoulos, Nikolaos; Jiang, Helen; Cohen, Shay.
Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18). Association for the Advancement of Artificial Intelligence, 2018. p. 5358-5365.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Canonical Correlation Inference for Mapping Abstract Scenes to Text

AU - Papasarantopoulos, Nikolaos

AU - Jiang, Helen

AU - Cohen, Shay

PY - 2018/12/7

Y1 - 2018/12/7

N2 - 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.”

AB - 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.”

M3 - Conference contribution

SN - 978-1-57735-800-8

SP - 5358

EP - 5365

BT - Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)

PB - Association for the Advancement of Artificial Intelligence

T2 - Thirty-Second AAAI Conference on Artificial Intelligence

Y2 - 2 February 2018 through 7 February 2018

ER -

Canonical Correlation Inference for Mapping Abstract Scenes to Text

Abstract

Publication series

Conference

Access to Document

Fingerprint

Projects

SUMMA - Scalable Understanding of Mulitingual Media

Cite this