Model-building in the visions system

Authors:
Thomas Williams;John Lowrance;Allen Hanson;Edward Riseman
Affiliations:
Computer and Information Science Department, University of Massachusetts, Amherst, Massachusetts;Computer and Information Science Department, University of Massachusetts, Amherst, Massachusetts;Computer and Information Science Department, University of Massachusetts, Amherst, Massachusetts and Hampshire College, Amherst, Massachusetts;Computer and Information Science Department, University of Massachusetts, Amherst, Massachusetts
Venue:
IJCAI'77 Proceedings of the 5th international joint conference on Artificial intelligence - Volume 2
Year:
1977

Citing 0
Cited 1

Identifying the multiple contexts of a situation

MRC'05 Proceedings of the Second international conference on Modeling and Retrieval of Context

Quantified Score

Hi-index	0.01

Visualization

Abstract

The semantic Interpretation system of VISIONS receives a segmentation containing symbolically encoded regions, boundaries and endpoints. The model-builder consists of four major components: 1) multiple levels of representation for both the image-specific model and long-term general knowledge, 2) a set of modular knowledge sources, 3) a hierarchical modular strategy to control application of the knowledge sources, and 4) a tree representing the current state of search through the space of possible models.