John M. Gauch
This is a likely match — the affiliation was inferred from OpenAlex, ORCID, and web sources but has not been fully confirmed. Treat with appropriate caution.
Researcher
Also affiliated: Boston University (1992–1993); University of North Carolina at Chapel Hill (1988–1989); Northeastern University (1991–2003); North Carolina State University (2002–2005); University of Kansas (1994–2007); Eaton (United States) (2003); Information Technology Laboratory (2005); University of Kansas Medical Center (2002); J. B. Hunt Transport Services (United States) (2017)
Faculty Researcher
Research Areas
Biomedical Subjects
Biography and Research Information
OverviewAI-generated summary
John M. Gauch's research interests include the application of machine learning techniques to various domains, with recent work focusing on advanced neural network architectures and cross-modal knowledge distillation. He has published on topics such as Orthogonal Channel Attention Networks (OrthoNets) and efficient multi-task perception and planning systems like TinyBEV. His publications also explore unsupervised denoising using unified diffusion and Bayesian risk approaches, as well as unconstrained object tracking via cross-domain adaptation (UTOPIA).
Gauch's work extends to the analysis of historical images and their captions, investigating transfer learning methods for extraction, classification, and searching. His scholarship metrics include an h-index of 20, with 84 total publications and 1,574 citations. He has collaborated with several researchers at the University of Arkansas at Fayetteville, including Reeshad Khan, Pha Nguyen, Ukash Nakarmi, and David Fredrick.
Metrics
- h-index: 20
- Publications: 85
- Citations: 1,579
Selected Publications
-
Adaptive Extensions of Unbiased Risk Estimators for Unsupervised Magnetic Resonance Image Denoising (2026)
-
Beyond Bayer: Task-Optimal Sensor Co-Design for Robust Autonomous-Driving Segmentation (2026)arXiv (Cornell University) OpenAlex
-
TinyBEV: Cross-Modal Knowledge Distillation for Efficient Multi-Task Bird's-Eye-View Perception and Planning (2025)
-
From Noise Estimation to Restoration: A Unified Diffusion and Bayesian Risk Approach for Unsupervised Denoising (2025)
-
OrthoNets: Orthogonal Channel Attention Networks (2023)
-
Transfer Learning Methods for Extracting, Classifying and Searching Large Collections of Historical Images and Their Captions (2021)
-
Detecting Gestures Through a Gesture-Based Interface to Teach Introductory Programming Concepts (2020)
-
Ransac Based Motion Compensated Restoration for Colonoscopy Images (2019)
-
An Automated Technique to Recognize and Extract Images from Scanned Archaeological Documents (2019)
-
Ransac Based Motion Compensated Restoration for Colonoscopy Images (2019)
-
Motion Compensated Restoration of Colonoscopy Images (2019)
-
Teaching Introductory Programming Concepts Through a Gesture-Based Interface (2018)
-
Terahertz Imaging of Three-Dimensional Dehydrated Breast Cancer Tumors (2017)
-
Adaptive enhancement and visualization techniques for 3D THz images of breast cancer tumors (2016)
-
Time of flight THz imaging of 3D ex-vivo breast cancer tumor tissues (2015)
Collaboration Network
Top Collaborators
- From Noise Estimation to Restoration: A Unified Diffusion and Bayesian Risk Approach for Unsupervised Denoising
- TinyBEV: Cross-Modal Knowledge Distillation for Efficient Multi-Task Bird's-Eye-View Perception and Planning
- Transfer Learning Methods for Extracting, Classifying and Searching Large Collections of Historical Images and Their Captions
- Transfer Learning Methods for Extracting, Classifying and Searching Large Collections of Historical Images and Their Captions
- Transfer Learning Methods for Extracting, Classifying and Searching Large Collections of Historical Images and Their Captions
- Transfer Learning Methods for Extracting, Classifying and Searching Large Collections of Historical Images and Their Captions
- OrthoNets: Orthogonal Channel Attention Networks
- OrthoNets: Orthogonal Channel Attention Networks
- OrthoNets: Orthogonal Channel Attention Networks
- From Noise Estimation to Restoration: A Unified Diffusion and Bayesian Risk Approach for Unsupervised Denoising
Similar Researchers
Based on overlapping research topics