Advanced

Improving the Detection of Relations Between Objects in an Image Using Textual Semantics

Medved, Dennis LU ; Jiang, Fangyuan LU ; Exner, Peter LU ; Oskarsson, Magnus LU ; Nugues, Pierre LU and Åström, Karl LU (2015) 3rd International Conference on Pattern Recognition Applications an Methods (ICPRAM 2014) In Pattern Recognition Applications and Methods /Lecture Notes in Computer Science 9443. p.133-145
Abstract
In this article, we describe a system that classifies relations between entities extracted from an image. We started from the idea that we could utilize lexical and semantic information from text associated with the image, such as captions or surrounding text, rather than just the geometric and visual characteristics of the entities found in the image. We collected a corpus of images from Wikipedia together with their corresponding articles. In our experimental setup, we extracted two kinds of entities from the images, human beings and horses, and we defined three relations that could exist between them: Ride, Lead,or None. We used geometric features as a baseline to identify the relations between the entities and we describe the... (More)
In this article, we describe a system that classifies relations between entities extracted from an image. We started from the idea that we could utilize lexical and semantic information from text associated with the image, such as captions or surrounding text, rather than just the geometric and visual characteristics of the entities found in the image. We collected a corpus of images from Wikipedia together with their corresponding articles. In our experimental setup, we extracted two kinds of entities from the images, human beings and horses, and we defined three relations that could exist between them: Ride, Lead,or None. We used geometric features as a baseline to identify the relations between the entities and we describe the improvements brought by the addition of bag-of-word features and predicate–argument structures that we extracted from the text. The best semantic model resulted in a relative error reduction of more than 18 % over the baseline (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Semantic parsing, Relation extraction from images, Machine learning
in
Pattern Recognition Applications and Methods /Lecture Notes in Computer Science
editor
Fred, Ana; De Marsico, Maria; Tabbone, Antoine; ; and
volume
9443
pages
13 pages
publisher
Springer
conference name
3rd International Conference on Pattern Recognition Applications an Methods (ICPRAM 2014)
external identifiers
  • scopus:84951860819
  • wos:000374104100009
ISBN
978-3-319-25529-3
978-3-319-25530-9
DOI
10.1007/978-3-319-25530-9_9
language
English
LU publication?
yes
id
dfd30702-58ac-4a52-a127-e62bd8093251 (old id 8260062)
date added to LUP
2015-12-07 11:59:13
date last changed
2017-01-01 08:00:55
@inproceedings{dfd30702-58ac-4a52-a127-e62bd8093251,
  abstract     = {In this article, we describe a system that classifies relations between entities extracted from an image. We started from the idea that we could utilize lexical and semantic information from text associated with the image, such as captions or surrounding text, rather than just the geometric and visual characteristics of the entities found in the image. We collected a corpus of images from Wikipedia together with their corresponding articles. In our experimental setup, we extracted two kinds of entities from the images, human beings and horses, and we defined three relations that could exist between them: Ride, Lead,or None. We used geometric features as a baseline to identify the relations between the entities and we describe the improvements brought by the addition of bag-of-word features and predicate–argument structures that we extracted from the text. The best semantic model resulted in a relative error reduction of more than 18 % over the baseline},
  author       = {Medved, Dennis and Jiang, Fangyuan and Exner, Peter and Oskarsson, Magnus and Nugues, Pierre and Åström, Karl},
  booktitle    = {Pattern Recognition Applications and Methods /Lecture Notes in Computer Science},
  editor       = {Fred, Ana and De Marsico, Maria and Tabbone, Antoine},
  isbn         = {978-3-319-25529-3},
  keyword      = {Semantic parsing,Relation extraction from images,Machine learning},
  language     = {eng},
  pages        = {133--145},
  publisher    = {Springer},
  title        = {Improving the Detection of Relations Between Objects in an Image Using Textual Semantics},
  url          = {http://dx.doi.org/10.1007/978-3-319-25530-9_9},
  volume       = {9443},
  year         = {2015},
}