Kris Ehinger

Kris Ehinger is an Associate Professor in the School of Computing and Information Systems at the University of Melbourne, within the Faculty of Engineering and Information Technology. She earned her PhD in Cognitive Science from the Massachusetts Institute of Technology in 2013, with a thesis on visual features for scene recognition and reorientation under the supervision of Ruth Rosenholtz. Prior to this, she completed a BSc (Hons) in Psychology from the University of Edinburgh in 2007 and a BS in Engineering and Applied Science from the California Institute of Technology in 2003. Her career includes a VISTA Postdoctoral Fellowship at the Centre for Vision Research, York University from 2016 to 2019, and a Postdoctoral Fellowship at Harvard Medical School from 2013 to 2016 under Jeremy Wolfe. She joined the University of Melbourne as Senior Lecturer in Digital Health in 2019, advancing to Associate Professor in 2025. Ehinger has secured significant funding, including ARC Discovery Projects DP240101264 (2024-2028) on cognitive models of image memorability and DP210100433 (2021-2024) on physics-inspired AI for geomaterials, as well as an ONI grant NI220100072 (2022-2025) for machine learning on miniature satellites. She received the National Science Foundation Graduate Research Fellowship (2009-2012), VISTA Postdoctoral Fellowship (2017-2019), Excellence in Research award from the School of Computing and Information Systems in 2023, and second place for best Human Vision poster at ICPV2019.

Her research lies at the intersection of human and computer vision, encompassing scene recognition, visual search, depth perception in natural scenes, and applications in navigation, object detection, and medical imaging. She employs computational modeling, including Bayesian models and deep neural networks, alongside behavioral methods such as psychophysics, eye tracking, and large-scale online experiments. Key publications include 'Raising the Bar: Deep Learning on Comprehensive Database Sets New Benchmark for Automated Fission-Track Detection' (Computers & Geosciences, 2026), 'Deep Learning and Geometric Modeling for 3D Reconstruction of Subsurface Utilities from GPR Data' (Sensors, 2025), 'Tests of a Hybrid-Similarity Exemplar Model of Context-Dependent Memorability' (Journal of Experimental Psychology: General, 2025), 'Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers' (NeurIPS, 2024), 'State-Based Disassembly Planning' (AAAI, 2025), 'TCAM-Diff: Triplane-Aware Cross-Attention Medical Diffusion Model' (AAAI, 2025), 'An active foveated gaze prediction algorithm based on a Bayesian ideal observer' (Pattern Recognition, 2023), and 'Unicode Analogies: An anti-objectivist visual reasoning challenge' (CVPR, 2023). Her work has appeared in premier venues like NeurIPS, CVPR, AAAI, and ECCV, contributing to advancements in explainable AI, amodal completion, and real-world visual processing.

Professional Email: kris.ehinger@unimelb.edu.au