Chris Pal

TL;DR: A fast and accurate fully automatic method for brain tumor segmentation which is competitive both in terms of accuracy and speed compared to the state of the art, and introduces a novel cascaded architecture that allows the system to more accurately model local label dependencies.

TL;DR: The performance of Theano is compared against Torch7 and TensorFlow on several machine learning models and recently-introduced functionalities and improvements are discussed.

TL;DR: In this paper, a spatial temporal 3-D convolutional neural network (3-D CNN) representation of the short temporal dynamics is used for video description, which is trained on video action recognition tasks, so as to produce a representation that is tuned to human motion and behavior.

TL;DR: This paper has constructed a large number of stereo datasets with ground-truth disparities, and a subset of these datasets are used to learn the parameters of conditional random fields (CRFs) and presents experimental results illustrating the potential of this approach for automatically learning the Parameters of models with richer structure than standard hand-tuned MRF models.

TL;DR: The key concepts of deep learning for clinical radiologists are reviewed, technical requirements are discussed, emerging applications in clinical radiology are described, and limitations and future directions in this field are outlined.