Publications

The Manhattan world assumption: Regularities in scene statistics which enable Bayesian inference. (2000). The Manhattan world assumption: Regularities in scene statistics which enable Bayesian inference. In NIPS (pp. 845–851).

Order Parameters for Minimax Entropy Distributions: When does high level knowledge help?. (2000). Order Parameters for Minimax Entropy Distributions: When does high level knowledge help?. In Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on (Vol. 1, pp. 558–565). IEEE.

Unified framework for performance analysis of Bayesian inference. (2000). Unified framework for performance analysis of Bayesian inference. In AeroSense 2000 (pp. 333–346). International Society for Optics and Photonics.

Bayesian A* tree search with expected O (N) convergence rates for road tracking. (1999). Bayesian A* tree search with expected O (N) convergence rates for road tracking. In Energy Minimization Methods in Computer Vision and Pattern Recognition (pp. 189–204). Springer Berlin Heidelberg.

From Generic to Specific: An Information Theoretic Perspective on the Value of High-Level Information. (1999). From Generic to Specific: An Information Theoretic Perspective on the Value of High-Level Information. Probabilistic Models Of The Brain, 135.

Fundamental bounds on edge detection: An information theoretic evaluation of different edge cues. (1999). Fundamental bounds on edge detection: An information theoretic evaluation of different edge cues. In Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on. (Vol. 1). IEEE.

High-Level and Generic Models for Visual Search: When does high level knowledge help?. (1999). High-Level and Generic Models for Visual Search: When does high level knowledge help?. In Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on. (Vol. 2). IEEE.

Manhattan world: Compass direction from a single image by bayesian inference. (1999). Manhattan world: Compass direction from a single image by bayesian inference. In Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on (Vol. 2, pp. 941–947). IEEE.

A Transparent Interpretation of the EM Algorithm. (1999). A Transparent Interpretation of the EM Algorithm.

Visual search: Fundamental bounds, order parameters, and phase transitions. (1999). Visual search: Fundamental bounds, order parameters, and phase transitions. Proc Ieee Workshop On Statistical And Computational Theories Of Vision. Cvpr 1999. Fort Collins, Co. June 1999.

Computational Vision: Principles of Perceptual Inference. (1998). Computational Vision: Principles of Perceptual Inference.

Convergence rates of algorithms for visual search: detecting visual contours. (1998). Convergence rates of algorithms for visual search: detecting visual contours. In NIPS (pp. 641–647).

Efficient optimization of a deformable template using dynamic programming. (1998). Efficient optimization of a deformable template using dynamic programming. In 2013 IEEE Conference on Computer Vision and Pattern Recognition (pp. 747–747). IEEE Computer Society.

A phase space approach to minimax entropy learning and the minutemax approximations. (1998). A phase space approach to minimax entropy learning and the minutemax approximations. In NIPS (pp. 761–767).

Spline-based image registration. (1997). Spline-based image registration. International Journal Of Computer Vision, 22, 199–218.

Twenty Questions, Focus of Attention, and A*: A theoretical comparison of optimization strategies. (1997). Twenty Questions, Focus of Attention, and A*: A theoretical comparison of optimization strategies. In Energy Minimization Methods in Computer Vision and Pattern Recognition (pp. 195–212). Springer Berlin Heidelberg.

Hierarchical spline-based image registration. (1994). Hierarchical spline-based image registration. In Computer Vision and Pattern Recognition, 1994. Proceedings CVPR'94., 1994 IEEE Computer Society Conference on (pp. 194–201). IEEE.