We propose a simple, efficient, and accurate method for detecting
out-of...
We present new insights and a novel paradigm (StEik) for learning implic...
We discover restrained numerical instabilities in current training pract...
We consider the problem of filling in missing spatio-temporal regions of...
We present Shape-Tailored Deep Neural Networks (ST-DNN). ST-DNN extend
c...
In this paper we present a novel loss function, called class-agnostic
se...
We introduce optimization methods for convolutional neural networks that...
We introduce two criteria to regularize the optimization involved in lea...
We address the problem that state-of-the-art Convolution Neural Networks...
We consider the problem of detecting objects, as they come into view, fr...
We further develop a new framework, called PDE Acceleration, by applying...
We consider the problem of optimization of cost functionals on the
infin...
Following the seminal work of Nesterov, accelerated optimization methods...
We present a general framework and method for simultaneous detection and...
We formulate a general energy and method for segmentation that is design...
In this paper, we propose a method for tracking structures (e.g., ventri...
This paper addresses how to construct features for the problem of image
...
We present a method to track the precise shape of an object in video bas...