Research Overview

My research is primarily focused around the problem of recognition, including the representations and algorithms supporting solutions to it. I am particularly interested in features and learning-based methods that apply to both vision and language, thus breaking away from the persistent compartmentalization of recognition tasks (something hinted at by David Marr over 30 years ago). This has led to some interesting, and often unconventional approaches that can be applied to a broad set of areas including computer vision, machine learning, human biometrics, and the digital humanities. Specifically, my work is looking at open set recognition, extreme value theory models for visual recognition, biologically-inspired learning algorithms, and stylometry.

Walter J. Scheirer


I will join the Department of Computer Science and Engineering at the University of Notre Dame as an assistant professor in August 2015. I'm looking for highly motivated students with a strong interest in computer vision and machine learning to join my group. Send me an email if you're interested.

Curriculum Vitae

PDF Format

Recent Publications (see all)

  1. "The Sense of a Connection: Automatic Tracing of Intertextuality by Meaning," (in press)
    Walter J. Scheirer, Christopher W. Forstall, Neil Coffee,
    Literary and Linguistic Computing (LLC),
    Accepted September 2014.
  2. "Probability Models for Open Set Recognition,"
    Walter J. Scheirer, Lalit P. Jain, Terrance E. Boult,
    IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI),
    November 2014.
  3. "Multi-Class Open Set Recognition Using Probability of Inclusion,"
    Lalit P. Jain, Walter J. Scheirer, Terrance E. Boult,
    Proceedings of the European Conference on Computer Vision (ECCV),
    September 2014.
  4. "Perceptual Annotation: Measuring Human Vision to Improve Computer Vision,"
    Walter J. Scheirer, Samuel E. Anthony, Ken Nakayama, David D. Cox,
    IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI),
    August 2014.
  5. "Good Recognition is Non-metric,"
    Walter J. Scheirer, Michael Wilber, Michael Eckmann, Terrance E. Boult,
    Pattern Recognition,
    August 2014.
  6. "Condition-Invariant, Top-Down Visual Place Recognition,"
    Michael Milford, Walter J. Scheirer, Eleonora Vig, Arren Glover, Oliver Baumann, Jason Mattingley, David D. Cox,
    Proceedings of the IEEE International Conference on Robotics and Automation (ICRA),
    June 2014.
  7. "Towards Open Set Recognition,"
    Walter J. Scheirer, Anderson Rocha, Archana Sapkota, Terrance E. Boult,
    IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI),
    July 2013.
  8. "Multi-Attribute Spaces: Calibration for Attribute Fusion and Similarity Search,"
    Walter J. Scheirer, Neeraj Kumar, Peter N. Belhumeur, Terrance E. Boult,
    Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR),
    June 2012.

Recent Projects (see all)

Visual Place Recognition

Visual Place Recognition

Spring 2013 - Present

Condition invariant visual place recognition for robot navigation inspired by vision science

Keywords: robotics, navigation, place recognition, whole image matching, patch matching, calibration
Is good recognition metric?

Good Recognition is Non-metric

Fall 2012 - Spring 2014

A new look at a fundamental question in computer vision: is recognition metric?

Keywords: machine learning, metric learning, recognition, face recognition, object recognition
Perceptual Annotation

Perceptual Annotation

Fall 2012 - Present

Measuring exemplar-by-exemplar dif´Čüculty and the pattern of errors of human annotators for regularization

Keywords: machine learning, psychology, regularization, citizen science, psychophysics, face detection
Open Set Recognition

Open Set Recognition

Spring 2011 - Present

Theory and algorithms that address the difficult problem of training without complete class knowledge

Keywords: machine learning, object recognition, face recognition, support vector machines, 1-vs-set machine
Extreme Value Theory for Visual Recognition

Extreme Value Theory for Visual Recognition

Spring 2008 - Present

The theory and practice of recognition score analysis for prediction and fusion

Keywords: calibration, meta-recognition, score analysis, object recognition, face recognition, attributes
Language and Literature

Language & Literature

Spring 2009 - Present

Machine learning and related statistical methods to improve the process by which intertextuality is studied

Keywords: computational linguistics, intertextuality, sound, stylistics, classics, authorship attribution
Digital Image and Video Forensics

Digital Image and Video Forensics

Spring 2008 - Present

Approaches to steganalysis, forgery detection and sensor fingerprinting

Keywords: forensics, forgery detection, data hiding, source identification, sensor fingerprinting

Recent Talks (see all)