We introduce a method to segment the visual field into independently mov...
We discover restrained numerical instabilities in current training pract...
Training a deep neural network for semantic segmentation is labor-intens...
We consider the problem of filling in missing spatio-temporal regions of...
We introduce optimization methods for convolutional neural networks that...
We introduce two criteria to regularize the optimization involved in lea...
We consider the problem of detecting objects, as they come into view, fr...
We present a general framework and method for simultaneous detection and...