TR96-37

Learning Bilinear Models for Two-Factor Problems in Vision

    •  W. T. Freeman, J. B. Tenenbaum, "Learning Bilinear Models for Two-Factor Problems in Vision", Tech. Rep. TR96-37, Mitsubishi Electric Research Laboratories, Cambridge, MA, December 1996.
      BibTeX TR96-37 PDF
      • @techreport{MERL_TR96-37,
      • author = {W. T. Freeman, J. B. Tenenbaum},
      • title = {Learning Bilinear Models for Two-Factor Problems in Vision},
      • institution = {MERL - Mitsubishi Electric Research Laboratories},
      • address = {Cambridge, MA 02139},
      • number = {TR96-37},
      • month = dec,
      • year = 1996,
      • url = {https://www.merl.com/publications/TR96-37/}
      • }
  • Research Areas:

    Artificial Intelligence, Computer Vision, Machine Learning

Abstract:

In many vision problems, we want to infer two (or more) hidden factors which interact to produce our observations. We may want to disentangle illuminant and object colors in color constancy; rendering conditions from surface shape in shape-from-shading; face identity and head pose in face recognition; or font and letter class in character recognition. We refer to these two factors generically as \"style\" and \"content\". This paper received Outstanding Paper prize, CVPR \'97.