David W. Jacobs: Selected Publications

Newer Stuff

• Carlos D. Castillo and David W. Jacobs,"Using Stereo Matching for 2-D Face Recognition Across Pose", IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2007.

• Gaurav Agarwal, Peter Belhumeur, Steven Feiner, David Jacobs , W. John Kress, Ravi Ramamoorthi,  Norman A. Bourg, Nandan Dixit, Haibin Ling, Dhruv Mahajan, Rusty Russell, Sameer Shirdhonkar, Kalyan Sunkavalli, and Sean White ``First Steps Toward an Electronic Field Guide for Plants,'', Taxon, 55(3): 597-610, August, 2006. 

• H. Ling, D. Jacobs ``Deformation Invariant Image Matching,'' ICCV 2005 Copyright (c) 2005 by IEEE.

• H. Ling, D. Jacobs ``Shape Classification Using the Inner-Distance,'' IEEE Trans on Pattern Anal. and Mach. Intell. (PAMI), 29(2):286-299, 2007.  Copyright (c) 2007 by IEEE. 
•   M. Osadchy, D. Jacobs, M. Lindenbaum, ``Surface Dependent Representations for Illumination Insensitive Image Comparison,'' IEEE Trans. on Pattern Analysis and Machine Intelligence, 29(1):98-111, 2007.   Copyright (c) 2007 by IEEE.
• R. Basri, D. Jacobs, I. Kemelmacher, ``Photometric Stereo with General, Unknown Lighting,'' Int'l J. of Computer Vision.  72(3): 239-257, 2007.
• C. H. Lee, A. Varshney, D. Jacobs, ``Mesh Saliency'' SIGGRAPH 2005.

Memory and Learning

D. Jacobs, B. Rokers, A. Rudra, and Z. Liu ``Fragment Completion in Humans and Machines'', NIPS, 2001.
A model of human memory, with experiments on human subjects. Considers simple word memory problems like: '*a*r*l*' (think of a word with an 'a' in it, followed by an 'r', followed by an 'l', with any number of intervening letters between these letters). data

D. Jacobs, D. Weinshall, Y. Gdalyahu, ``Class Representation and Image Retrieval with Non-Metric Distances''.    IEEE Trans. on Pattern Analysis and Machine Intelligence. 22(6):583-600, 2000.  Copyright (c) 2000 by IEEE.
This work considers supervised learning when images are related by distances that don't obey the triangle inequality, such as a distance that considers the centaur to be similar to the man and horse, but considers the man to be very different from the horse.

Illumination (and Recognition)

• M. Osadchy, D. Jacobs, M. Lindenbaum ``On the Equivalence of Common Approaches to Lighting Insensitive Recognition'' ICCV 2005 Copyright (c) 2005 by IEEE.
• M. Osadchy, M. Lindenbaum, D. Jacobs, ``Whitening for Photometric Comparison of Smooth Surfaces under Varying Illumination," ECCV 2004.
• R. Osadchy, D. Jacobs, R. Ramamoorthi, ``Using Specularities for Recognition'', ICCV 2003 Copyright (c) 2003 by IEEE.  This paper is about recognizing shiny objects like:

• R. Basri and D. Jacobs, ``Lambertian Reflectance and Linear Subspaces'', NEC Research Institute Technical Report 2000-172R, Weizmann Institute of Science Technical Report MCS00-21. A version also appeared in ICCV '01, and in PAMI 2003.
  We prove that the set of all reflectance functions (the mapping from surface normals to intensities) produced by Lambertian objects under distant, isotropic lighting lies close to a 9D linear subspace. This explains previous empirical results and leads to new recognition algorithms.

PowerPoint version of my ICCV talk.

Recognition with Regions

• R. Basri and D. Jacobs. ``Projective Alignment with Regions,'' IEEE Trans. on Pattern Analysis and Machine Intelligence, 23(5):519--527, 2001.

Other Recognition

Structure from Motion

Perceptual Organization

• D. Jacobs, ``What Makes Viewpoint Invariant Properties Perceptually Salient?'', JOSA (A), 2003.
• Z. Liu, D. Jacobs, R. Basri ``The role of convexity in perceptual completion -- beyond good continuation''. Vision Research 39: 4244-4257, 1999. 

Graphics and User Interfaces