Model-Building in the Visions System

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.

Cite

Text

Williams et al. "Model-Building in the Visions System." International Joint Conference on Artificial Intelligence, 1977.

Markdown

[Williams et al. "Model-Building in the Visions System." International Joint Conference on Artificial Intelligence, 1977.](https://mlanthology.org/ijcai/1977/williams1977ijcai-model/)

BibTeX

@inproceedings{williams1977ijcai-model,
  title     = {{Model-Building in the Visions System}},
  author    = {Williams, Thomas and Lowrance, John D. and Hanson, Allen R. and Riseman, Edward M.},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {1977},
  pages     = {644-645},
  url       = {https://mlanthology.org/ijcai/1977/williams1977ijcai-model/}
}