Kris Ehinger

Image amodal completion: A survey

J Ao, Q Ke, KA Ehinger

Journal article  |  2023  |  Computer Vision and Image Understanding

Existing computer vision systems can compete with humans in understanding the visible parts of objects, but still fall far short o..

Lightness constancy in reality, in virtual reality, and on flat-panel displays

Khushbu Y Patel, Laurie M Wilcox, Laurence T Maloney, Krista A Ehinger, Jaykishan Y Patel, Emma Wiedenmann, Richard F Murray

Journal article  |  2022  |  Journal of Vision

Hiding the Rabbit: Using a genetic algorithm to investigate shape guidance in visual search.

Avi M Aizenman, Krista A Ehinger, Farahnaz A Wick, Ruggero Micheletto, Jungyeon Park, Lucas Jurgensen, Jeremy M Wolfe

Journal article  |  2022  |  J Vis

During visual search, attention is guided by specific features, including shape. Our understanding of shape guidance is limited to..

Role of memory in a Bayesian ideal observer model of visual search in natural images

Shima Rashidi, Krista A Ehinger, Lars Kulik, Andrew Turpin

Journal article  |  2021  |  Journal of Vision

Category systems for real-world scenes

Matt D Anderson, Erich W Graf, James H Elder, Krista A Ehinger, Wendy J Adams

Journal article  |  2021  |  JOURNAL OF VISION

Categorization performance is a popular metric of scene recognition and understanding in behavioral and computational research. Ho..

Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectors

Ruihan Zhang, Prashan Madumal, Tim Miller, Krista A Ehinger, Benjamin IP Rubinstein

Conference Proceedings  |  2021  |  THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE

Convolutional neural network (CNN) models for computer vision are powerful but lack explainability in their most basic form. This ..

A Closer Look at Generalisation in RAVEN

S Spratley, K Ehinger, T Miller

Conference Proceedings  |  2020  |  Computer Vision – ECCV 2020 16th European Conference , Proceedings, Part XXVII

Humans have a remarkable capacity to draw parallels between concepts, generalising their experience to new domains. This skill is ..

Optimal visual search based on a model of target detectability in natural images

Shima Rashidi, Krista Ehinger, Andrew Turpin, Lars Kulik

Conference Proceedings  |  2020  |  Advances in Neural Information Processing Systems 33

To analyse visual systems, the concept of an ideal observer promises an optimal response for a given task. Bayesian ideal observer..

Monocular depth discrimination in natural scenes: Humans vs. deep networks

Kedarnath Vilankar, Hengchao Xiang, Krista Ehinger, Wendy Adams, Erich Graf, James Elder

Journal article  |  2019  |  Journal of Vision

Influence of 2D Shape on Contour Depth Perception

Krista A Ehinger, Yiming Qian, Laurie M Wilcox, James H Elder

Journal article  |  2019  |  Journal of Vision