Research Overview

My technical 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 intriguing and often unconventional approaches that can be applied to a broad set of areas within artificial intelligence including computer vision, machine learning, and human biometrics. Specifically, my work is looking at open set recognition, extreme value theory models for visual recognition, and biologically-inspired learning algorithms. I'm also a cultural critic and historian, commenting on the social context of emerging technologies from the realistic perspective of a computer scientist.


Walter J. Scheirer

Curriculum Vitae

PDF Format

Postdoctoral Fellows

Steve Cruz (Co-Advised with Jonathan Hauenstein)

Graduate Students

Sophia Abraham

Louisa Conwill

Jin Huang

Derek Prijatelj

Arturo Russell Bernal (Co-Advised with Jane Cleland-Huang)

Abigail Swenor

Teaching

Spring 2025: CSE 40535 Computer Vision

Fall 2024: CSE 40175 Ethical & Professional Issues

Spring 2024: CSE 20176 The Archeology of Hacking

Books

Virtue in Virtual Spaces (Liturgical Press) with Louisa Conwill and Megan Levis

A History of Fake Things on the Internet (Stanford University Press)

A Unifying Framework for Formal Theories of Novelty (Springer-Nature) edited with Terry Boult

Quantitative Intertextuality: Analyzing the Markers of Information Reuse (Springer-Nature) with Christopher W. Forstall

Extreme Value Theory-based Methods for Visual Recognition (Morgan & Claypool Publishers)

Recent Publications (see all)

  1. "This Probably Looks Exactly Like That: An Invertible Prototypical Network,"
    Zachariah Carmichael, Timothy Redgrave, Daniel Gonzalez Cedre, Walter Scheirer,
    Proceedings of the European Conference on Computer Vision (ECCV),
    October 2024.
  2. "Human Activity Recognition in an Open World,"
    Derek Prijatelj, Samuel Grieggs, Jin Huang, Dawei Du, Ameya Shringi, Christopher Funk,
    Adam Kaufman, Eric Robertson, Walter Scheirer,
    Journal of Artificial Intelligence Research,
    Accepted for Publication in September 2024.
  3. "Has the Virtualization of the Face Changed Facial Perception?
    A Study of the Impact of Augmented Reality on Facial Perception,"
    Louisa Conwill, Samuel Anthony, Walter Scheirer,
    Proceedings of the ACM CHI Conference on Human Factors in Computing Systems,
    May 2024.
  4. "Informing Machine Perception With Psychophysics,"
    Justin Dulay, Sonia Poltoratski, Till Hartmann, Samuel Anthony,
    Walter Scheirer,
    Proceedings of the IEEE,
    February 2024.
  5. "C-CLIP: Contrastive Image-Text Encoders to Close the Descriptive-Commentative
    Gap,"
    William Theisen, Walter Scheirer,
    Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision
    (WACV),
    January 2024.
  6. "Pixel-Grounded Prototypical Part Networks,"
    Zachariah Carmichael, Suhas Lohit, Anoop Cherian, Michael Jones, Walter Scheirer,
    Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision
    (WACV),
    January 2024.
  7. "NOMAD: A Natural, Occluded, Multi-scale Aerial Dataset, for Emergency Response
    Scenarios,"
    Arturo Russell Bernal, Jane Cleland-Huang, Walter Scheirer,
    Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision
    (WACV),
    January 2024.
  8. "The Paleographer’s Eye ex machina:
    Using Computer Vision to Assist Humanists in Scribal Hand Identification,"
    Samuel Grieggs, Cai Henderson, Sebastian Sobecki, Alexandra Gillespie, Walter Scheirer,
    Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision
    (WACV),
    January 2024.
  9. "Measuring Human Perception to Improve Open Set Recognition,"
    Jin Huang, Derek Prijatelj, Justin Dulay, Walter Scheirer,
    IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI),
    September 2023.
  10. "Automated Transcription of Gə'əz Manuscripts Using Deep Learning,"
    Samuel Grieggs, Jessica Lockhart, Alexandra Atiya, Suzanne Akbari,
    Eyob Derillo, Jarod Jacobs, Christine Kwon, Michael Gervers, Steve Delamarter,
    Alexandra Gillespie, Walter J. Scheirer,
    Digital Humanities Quarterly,
    August 2023.

New Research in arXiv / bioRxiv

  1. "N-Modal Contrastive Losses with Applications to Social Media Data in
    Trimodal Space,"
    William Theisen, Walter Scheirer,
    March 2024.
  2. "HomOpt: A Homotopy-Based Hyperparameter Optimization Method,"
    Sophia Abraham, Kehelwala Maduranga, Jeffery Kinnison, Zachariah Carmichael,
    Jonathan Hauenstein, Walter Scheirer,
    August 2023.
  3. "On the Effectiveness of Image Manipulation Detection in the Age of Social
    Media,"
    Rosaura G. VidalMata, Priscila Saboia, Daniel Moreira, Grant Jensen,
    Jason Schlessman, Walter Scheirer,
    April 2023.
  4. "Using Human Perception to Regularize Transfer Learning,"
    Justin Dulay, Walter Scheirer,
    November 2022.

Current and Long-Standing Projects (see all)

Open World Recognition

Open World Recognition

Spring 2011 - Present

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

Keywords: novelty, classifiers, architectures, object recognition, activity recognition, handwriting recognition
Psychophysics

Psychophysics for Computer Vision

Fall 2012 - Present

Measuring exemplar-by-exemplar difficulty and the pattern of errors of humans for supervised learning

Keywords: psychology, citizen science, psychophysics, object recognition, face detection, attributes
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 open up new modes of inquiry in the humanities

Keywords: computational linguistics, intertextuality, sound, stylistics, classics, historical document analysis
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
Hyperparameter Optimization: Distributed Hardware-Aware and Homotopy-Based Strategies

Hyperparameter Optimization: Distributed Hardware-Aware and Homotopy-Based Strategies

Spring 2017 - Present

Intelligent mapping of hardware resources to model search tasks making use of homotopy optimization

Keywords: machine learning, hyperparameters, optimization, distributed computing, homotopy
Human-Drone Partnerships for Emergency Response

Human-Drone Partnerships for Emergency Response

Fall 2019 - Present

Semi-autonomous UAVs to support emergency response scenarios, such as fire surveillance and search and rescue

Keywords: drones, software engineering, participatory design, object detection, first responders
When Technology Falls Short

When Technology Falls Short

Fall 2019 - Present

Constructive criticism of emerging technologies, scientific trends, and policies

Keywords: machine learning, facial analysis, election integrity, scientific integrity, peace studies

Selected Talks (see all)

Activities