Progress on vision through learning: A collaborative effort of George Mason University and University of Maryland

Ryszard S. Michalski, Azriel Rosenfeld, Yannis Aloimonos, Zoran Duric, Marcus A. Maloof, and Qi Zhang

This report briefly reviews research progress on vision through learning conducted as a collaborative effort of the GMU Machine Learning and Inference Laboratory and the UMD Computer Vision Laboratory. The report covers work done on the following projects:
  1. The Multi-level Image Sampling and Transformation (MIST) methodology for learning image descriptions and transformations
  2. Applying the MIST methodology to semantic analysis of outdoor scenes
  3. Recognizing objects in a cluttered environment
  4. Learning in navigation
  5. Intelligent interfaces: Learning in the RADIUS environment
  6. Learning space configuration and homing
  7. Learning object functionality
Our work aims at ultimately developing vision systems that apply a range of symbolic and parametric machine learning methods to solving vision problems.

Paper available in PostScript (gzipped) and PDF.

  author = "Michalski, R.S. and Rosenfeld, A. and Aloimonos, Y.
      Duric, Z. and Maloof, M.A. and Zhang, Q.",
  title = "Progress on vision through learning: A collaborative effort
      of {George Mason University} and {University of Maryland}",
  booktitle = "{Proceedings of the Image Understanding Workshop}",
  year = 1996,
  pages = "177--187",
  address = "San Francisco, CA",
  publisher = "Morgan Kaufmann"