In this paper, we review the recently published work on deformable models. We have chosen to concentrate on 2D deformable models and relate the energy minimization …
Although having achieved great success in medical image segmentation, deep learning- based approaches usually require large amounts of well-annotated data, which can be …
A Kendall, Y Gal - Advances in neural information …, 2017 - proceedings.neurips.cc
There are two major types of uncertainty one can model. Aleatoric uncertainty captures noise inherent in the observations. On the other hand, epistemic uncertainty accounts for …
P Tang, P Yang, D Nie, X Wu, J Zhou… - Knowledge-Based Systems, 2022 - Elsevier
Automatic segmentation is a fundamental task in computer-assisted medical image analysis. Convolutional neural networks (CNNs) have been widely used for medical image …
Humans perceive the three-dimensional structure of the world with apparent ease. However, despite all of the recent advances in computer vision research, the dream of having a …
M Isard, A Blake - International journal of computer vision, 1998 - Springer
The problem of tracking curves in dense visual clutter is challenging. Kalman filtering is inadequate because it is based on Gaussian densities which, being unimo dal, cannot …
The ability to recognize humans and their activities by vision is key for a machine to interact intelligently and effortlessly with a human-inhabited environment. Because of many …
N Wahlström, E Özkan - IEEE Transactions on Signal …, 2015 - ieeexplore.ieee.org
In this paper, we propose using Gaussian processes to track an extended object or group of objects, that generates multiple measurements at each scan. The shape and the kinematics …
While making a tremendous impact in various fields, deep neural networks usually require large amounts of labeled data for training which are expensive to collect in many …