[
home |
resume |
contact |
science |
art |
personal |
email
]
Somers, S., Gagné, J., Astudillo, C., & Davies, J. (2011). Using semantic similarity to predict angle and distance of objects in images. In Proceedings of the 8th ACM Conference on Creativity & Cognition (pp. 217-222). Atlanta, Georgia.
Cite this for:
- SYSTEM: Visuo
- Similarity can be successfully used to predict angle and distance in 2d imagined scenes.
Publisher:
BibTex Entry:
@InProceedings{SomersGagneAstudilloDavies2011,
author = {Somers, Sterling, and Gagn\'{e}, Jonathan, and Astudillo, Cesar, and Davies, Jim},
title = {Proceedings of the 8th ACM Conference on Creativity \& Cognition},
pages = {217-222},
year = {2011},
address = {Atlanta, Georgia}
}
Download: [
PDF ]
From the
Visual Analogy research theme.
Abstract
A presentation of an Artificial Intelligence (AI) called
Visuo that stores and guesses quantitative visual-spatial
magnitudes (e.g., sizes of objects). In this analysis, Visuo is
used to store polar (angle and distance) relationships
between objects in images. It uses a database of tagged
images as its memory and approximates unexperienced
magnitudes by analogy with semantically related concepts.
This shows the transferring of information from high
semantically related concepts yielding significantly higher
accuracy in angle and distance estimations over using
medium or low semantically similar items.
Back to Jim Davies's list of
publications.
JimDavies
(
jim@jimdavies.org
)