Recognizing open-vocabulary relations between objects in images

Masayasu Muraoka, Sumit Maharjan, Masaki Saito, Kota Yamaguchi, Naoaki Okazaki, Takayuki Okatani, Kentaro Inui

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

Abstract

How can we describe the relations between objects in a picture? As recent deep neural networks have exhibited impressive performance in identifying individual entities in a picture, in this study we turn our attention to recognize inter-object relations. To recognize open-domain relations, (a) we propose collecting relational concepts automatically from an image-text corpus. In addition, using collected relational instances, (b) we train a classifier to recognize inter-object relations. A relation recognition experiment conducted in our study suggests that relative information calculated from objects improves relation recognition effectively.

Original languageEnglish
Title of host publicationProceedings of the 30th Pacific Asia Conference on Language, Information and Computation, PACLIC 2016
EditorsJong C. Park, Jin-Woo Chung
PublisherInstitute for the Study of Language and Information
Pages239-248
Number of pages10
ISBN (Electronic)9788968174285
Publication statusPublished - 2016 Jan 1
Event30th Pacific Asia Conference on Language, Information and Computation, PACLIC 2016 - Seoul, Korea, Republic of
Duration: 2016 Oct 282016 Oct 30

Publication series

NameProceedings of the 30th Pacific Asia Conference on Language, Information and Computation, PACLIC 2016

Other

Other30th Pacific Asia Conference on Language, Information and Computation, PACLIC 2016
Country/TerritoryKorea, Republic of
CitySeoul
Period16/10/2816/10/30

ASJC Scopus subject areas

  • Language and Linguistics
  • Computer Science (miscellaneous)
  • Information Systems

Fingerprint

Dive into the research topics of 'Recognizing open-vocabulary relations between objects in images'. Together they form a unique fingerprint.

Cite this