Using semantic similarity to predict angle and distance of objects in images
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.
|Keywords||Analogy., Creativity, Imagination, Visualization|
|Conference||8th ACM Conference on Creativity and Cognition, C and C 2011|
Somers, S. (Sterling), Gagné, J. (Jonathan), Astudillo, C. (Cesar), & Davies, J. (2011). Using semantic similarity to predict angle and distance of objects in images. In C and C 2011 - Proceedings of the 8th ACM Conference on Creativity and Cognition (pp. 217–222). doi:10.1145/2069618.2069655