Edinburgh Research Explorer

Canonical Correlation Inference for Mapping Abstract Scenes to Text

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Related Edinburgh Organisations

Open Access permissions

Open

Original languageEnglish
Title of host publicationProceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)
PublisherAssociation for the Advancement of Artificial Intelligence
Pages5358-5365
Number of pages8
ISBN (Electronic)2374-3468
ISBN (Print)978-1-57735-800-8
Publication statusE-pub ahead of print - 7 Dec 2018
EventThirty-Second AAAI Conference on Artificial Intelligence - Hilton New Orleans Riverside, New Orleans, United States
Duration: 2 Feb 20187 Feb 2018
https://aaai.org/Conferences/AAAI-18/
https://aaai.org/Conferences/AAAI-18/

Conference

ConferenceThirty-Second AAAI Conference on Artificial Intelligence
Abbreviated titleAAAI-18
CountryUnited States
CityNew Orleans
Period2/02/187/02/18
Internet address

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.”

Event

Thirty-Second AAAI Conference on Artificial Intelligence

2/02/187/02/18

New Orleans, United States

Event: Conference

Download statistics

No data available

ID: 50776491