no code implementations • 21 Nov 2023 • Paul Scemama, Ariel Kapusta
Bayesian deep learning and conformal prediction are two methods that have been used to convey uncertainty and increase safety in machine learning systems.
no code implementations • 25 Apr 2023 • Siddhartha Kapuria, Tarunraj G. Mohanraj, Nethra Venkatayogi, Ozdemir Can Kara, Yuki Hirata, Patrick Minot, Ariel Kapusta, Naruhiko Ikoma, Farshid Alambeigi
In this study, toward addressing the over-confident outputs of existing artificial intelligence-based colorectal cancer (CRC) polyp classification techniques, we propose a confidence-calibrated residual neural network.
1 code implementation • CVPR 2020 • Henry M. Clever, Zackory Erickson, Ariel Kapusta, Greg Turk, C. Karen Liu, Charles C. Kemp
We describe a physics-based method that simulates human bodies at rest in a bed with a pressure sensing mat, and present PressurePose, a synthetic dataset with 206K pressure images with 3D human poses and shapes.
3D human pose and shape estimation 3D Human Shape Estimation +1
3 code implementations • 10 Oct 2019 • Zackory Erickson, Vamsee Gangaram, Ariel Kapusta, C. Karen Liu, Charles C. Kemp
Assistive Gym models a person's physical capabilities and preferences for assistance, which are used to provide a reward function.
no code implementations • 21 Apr 2018 • Henry M. Clever, Ariel Kapusta, Daehyung Park, Zackory Erickson, Yash Chitalia, Charles C. Kemp
In this work, we present two convolutional neural networks to estimate the 3D joint positions of a person in a configurable bed from a single pressure image.