St Andrews Research Repository

St Andrews University Home
View Item 
  •   St Andrews Research Repository
  • University of St Andrews Research
  • University of St Andrews Research
  • University of St Andrews Research
  • View Item
  •   St Andrews Research Repository
  • University of St Andrews Research
  • University of St Andrews Research
  • University of St Andrews Research
  • View Item
  •   St Andrews Research Repository
  • University of St Andrews Research
  • University of St Andrews Research
  • University of St Andrews Research
  • View Item
  • Register / Login
JavaScript is disabled for your browser. Some features of this site may not work without it.

Few-shot linguistic grounding of visual attributes and relations using gaussian kernels

Thumbnail
View/Open
Koudouna_2021_Few_short_linguistic_VISAPP_146.pdf (4.597Mb)
Date
08/02/2021
Author
Koudouna, Daniel
Terzić, Kasim
Keywords
Few-shot learning
Learning models
Attribute learning
Relation learning
Scene understanding
QA75 Electronic computers. Computer science
3rd-DAS
Metadata
Show full item record
Abstract
Understanding complex visual scenes is one of fundamental problems in computer vision, but learning in this domain is challenging due to the inherent richness of the visual world and the vast number of possible scene configurations. Current state of the art approaches to scene understanding often employ deep networks which require large and densely annotated datasets. This goes against the seemingly intuitive learning abilities of humans and our ability to generalise from few examples to unseen situations. In this paper, we propose a unified framework for learning visual representation of words denoting attributes such as “blue” and relations such as “left of” based on Gaussian models operating in a simple, unified feature space. The strength of our model is that it only requires a small number of weak annotations and is able to generalize easily to unseen situations such as recognizing object relations in unusual configurations. We demonstrate the effectiveness of our model on the pr edicate detection task. Our model is able to outperform the state of the art on this task in both the normal and zero-shot scenarios, while training on a dataset an order of magnitude smaller. (Less)
Citation
Koudouna , D & Terzić , K 2021 , Few-shot linguistic grounding of visual attributes and relations using gaussian kernels . in G M Farinella , P Radeva , J Braz & K Bouatouch (eds) , Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - (Volume 5) . vol. 5 VISAPP , International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications , vol. 5 , SCITEPRESS - Science and Technology Publications , pp. 146-156 , 16th International Conference on Computer Vision Theory and Applications (VISAPP 2021) , 8/02/21 . https://doi.org/10.5220/0010261301460156
 
conference
 
Publication
Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - (Volume 5)
DOI
https://doi.org/10.5220/0010261301460156
ISSN
2184-4321
Type
Conference item
Rights
Copyrightc©2021 by SCITEPRESS – Science and Technology Publications, Lda. This is an open access article under the CC BY-NC-ND license.
Collections
  • University of St Andrews Research
URI
http://hdl.handle.net/10023/21653

Items in the St Andrews Research Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

Advanced Search

Browse

All of RepositoryCommunities & CollectionsBy Issue DateNamesTitlesSubjectsClassificationTypeFunderThis CollectionBy Issue DateNamesTitlesSubjectsClassificationTypeFunder

My Account

Login

Open Access

To find out how you can benefit from open access to research, see our library web pages and Open Access blog. For open access help contact: openaccess@st-andrews.ac.uk.

Accessibility

Read our Accessibility statement.

How to submit research papers

The full text of research papers can be submitted to the repository via Pure, the University's research information system. For help see our guide: How to deposit in Pure.

Electronic thesis deposit

Help with deposit.

Repository help

For repository help contact: Digital-Repository@st-andrews.ac.uk.

Give Feedback

Cookie policy

This site may use cookies. Please see Terms and Conditions.

Usage statistics

COUNTER-compliant statistics on downloads from the repository are available from the IRUS-UK Service. Contact us for information.

© University of St Andrews Library

University of St Andrews is a charity registered in Scotland, No SC013532.

  • Facebook
  • Twitter