Peter N. Belhumeur

PROFESSOR OF COMPUTER SCIENCE

Schapiro Center for Engineering and Physical Science Research (CEPSR)
Room 623

Tel(212) 939-7087
Fax(212) 939-7008

Peter N. Belhumeur is currently a professor in the Department of Computer Science at Columbia University and the director of the Laboratory for the Study of Visual Appearance (VAP LAB). His research focus lies somewhere in the mix of computer vision and machine learning. 

Research Interests

Computer vision, biometrics, face recognition, computational photography, computer graphics, biological species identification, computer science
He is one of the creators of the popular apps Leafsnap (leafsnap.com), Birdsnap (birdsnap.com), and Dogsnap.  These apps were the first to use machine learning technology for species (or breed) identification.
He is a recipient of the Presidential Early Career Award for Scientists and Engineers (PECASE) and the National Science Foundation Career Award. He won both the Siemens Best Paper Award at the IEEE Conference on Computer Vision and Pattern Recognition and the Olympus Prize at the European Conference of Computer Vision.
 
Belhumeur received a ScB in information sciences from Brown University in 1985. He received his PhD in engineering sciences from Harvard University under the direction of David Mumford in 1993. He was a postdoctoral fellow at the University of Cambridge's Isaac Newton Institute for Mathematical Sciences in 1994. He was made assistant, associate and professor of Electrical Engineering at Yale University in 1994, 1998, and 2001, respectively. He joined Columbia University as a professor of Computer Science in 2002.

PROFESSIONAL EXPERIENCE

  • Professor of computer science, Columbia University, 2002
  • Professor of electrical engineering, Yale, 2001
  • Associate professor of electrical engineering, Yale, 1998
  • Assistant professor of electrical engineering, Yale, 1994

HONORS AND AWARDS

  • Edward O. Wilson Biodiversity Technology Pioneer Award, 2011
  • Presidential Early Career Award for Scientists and Engineers (PECASE)
  • National Science Foundation Career Award
  • Siemens Best Paper Award at the IEEE Conference on Computer Vision and Pattern Recognition
  • Olympus Prize at the European Conference of Computer Vision.

SELECTED PUBLICATIONS

  • "Articulated pose estimation using hierarchical exemplar-based models," AAAI'16 Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016. (J. Liu, Y. Li, P. Allen, P. Belhumeur)
  • [PDF]
  • "Part-pair representation for part localization," European Conference on Computer Vision, 2014. (J. Liu, Y. Li, P.N. Belhumeur)
  • [PDF]
  • "Birdsnap: Large-scale fine-grained visual categorization of birds," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014. (T. Berg, J. Liu, S.W. Lee, M.L. Alexander, D.W. Jacobs, P.N. Belhumeur)
  • [PDF]
  • "Localizing parts of faces using a consensus of exemplars," IEEE transactions on pattern analysis and machine intelligence, 2013. (P.N. Belhumeur, D.W. Jacobs, D.J. Kriegman, N. Kumar)
  • [PDF]
  • "From Bikers to Surfers: Visual Recognition of Urban Tribes," British Machine Vision Conference, 2013. (I.S. Kwak, A.C. Murillo, P.N. Belhumeur, D.J. Kriegman, S.J. Belongie)
  • ​[PDF]
  • "How reliable are your visual attributes?," SPIE Defense, Security, and Sensing, 2013. (W.J. Scheirer, N. Kumar, V.N. Iyer, P.N. Belhumeur, T.E. Boult)
  • [PDF]
  • "Compressive structured light for recovering inhomogeneous participating media," IEEE transactions on pattern analysis and machine intelligence, 2013. (J. Gu, S.K. Nayar, E. Grinspun, P.N. Belhumeur, R. Ramamoorthi)
  • [PDF]
  • "Bird part localization using exemplar-based models with enforced pose and subcategory consistency," Proceedings of the IEEE International Conference on Computer Vision, 2013. (J. Liu, P.N. Belhumeur)
  • [PDF]
  • "How do you tell a blackbird from a crow?," Proceedings of the IEEE International Conference on Computer Vision, 2013. (T. Berg, P.N. Belhumeur)
  • [PDF]
  • "Poof: Part-based one-vs.-one features for fine-grained categorization, face verification, and attribute estimation," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2013. (T. Berg, P.N. Belhumeur)
  • [PDF]