Publications

Cancer statistics, 2020

Abstract Each year, the American Cancer Society estimates the numbers of new cancer cases and deaths that will occur in the United States and compiles the most recent data on po...

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

In this work we address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical ...

Cancer statistics, 2019

Abstract Each year, the American Cancer Society estimates the numbers of new cancer cases and deaths that will occur in the United States and compiles the most recent data on ca...

Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation

Traditional econometric models assume a constant one-period forecast variance. To generalize this implausible assumption, a new class of stochastic processes called autoregressi...

Very high resolution interpolated climate surfaces for global land areas

We developed interpolated climate surfaces for global land areas (excluding Antarctica) at a spatial resolution of 30 arc s (often referred to as 1-km spatial resolution). The c...

Polymorphic transitions in single crystals: A new molecular dynamics method

A new Lagrangian formulation is introduced. It can be used to make molecular dynamics (MD) calculations on systems under the most general, externally applied, conditions of stre...

Another look at the instrumental variable estimation of error-components models

The Pascal Visual Object Classes (VOC) Challenge

YOLO9000: Better, Faster, Stronger

We introduce YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories. First we propose various improvements to the YOLO detec...

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN have reduced the running tim...

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

Rectified activation units (rectifiers) are essential for state-of-the-art neural networks. In this work, we study rectifier neural networks for image classification from two as...

GROMACS: Fast, flexible, and free

Abstract This article describes the software suite GROMACS (Groningen MAchine for Chemical Simulation) that was developed at the University of Groningen, The Netherlands, in the...