John M. Gauch Data-verified

Affiliation confirmed via AI analysis of OpenAlex, ORCID, and web sources.

Researcher

Last publication 2025 Last refreshed 2026-05-09

faculty

20 h-index 84 pubs 1,570 cited

Biography and Research Information

OverviewAI-generated summary

John M. Gauch's research interests lie at the intersection of computer science and various application domains, with a recent emphasis on advanced machine learning techniques. He has published work on novel neural network architectures, such as OrthoNets, which utilize orthogonal channel attention for improved performance. His research also extends to transfer learning, exploring methods for extracting and classifying information from large historical image collections, and developing efficient multi-task learning models like TinyBEV for perception and planning tasks.

Gauch's work also addresses fundamental challenges in machine learning, including unsupervised denoising using unified diffusion and Bayesian risk approaches. Furthermore, he has investigated techniques for unconstrained object tracking through cross-domain adaptation, as demonstrated in his UTOPIA project. His scholarship metrics include an h-index of 20, with 84 total publications and 1,566 citations. He has collaborated with several researchers at the University of Arkansas at Fayetteville, including Pha Nguyen, Ukash Nakarmi, David Fredrick, and Rhodora G. Vennarucci.

Metrics

  • h-index: 20
  • Publications: 84
  • Citations: 1,570

Selected Publications

  • 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)
    34 citations DOI OpenAlex
  • Transfer Learning Methods for Extracting, Classifying and Searching Large Collections of Historical Images and Their Captions (2021)
    3 citations DOI OpenAlex

View all publications on OpenAlex →

Collaborators

Researchers in the database who share publications

Similar Researchers

Based on overlapping research topics