Rethinking the Inception Architecture for Computer Vision
Convolutional networks are at the core of most state of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to bec...
Publications
Explore 2,905 academic publications
Showing 12 of
2,905 publications
Institutions, Institutional Change and Economic Performance
Continuing his groundbreaking analysis of economic structures, Douglass North develops an analytical framework for explaining the ways in which institutions and institutional ch...
Society and the Adolescent Self-Image
Over 5,000 high-school students of different social, religious, and national backgrounds were studied to show the effects of family experience, neighborhoods, minority groups, e...
A low-cost, high-efficiency solar cell based on dye-sensitized colloidal TiO2 films
THE large-scale use of photovoltaic devices for electricity generation is prohibitively expensive at present: generation from existing commercial devices costs about ten times m...
The ERA5 global reanalysis
Abstract Within the Copernicus Climate Change Service (C3S), ECMWF is producing the ERA5 reanalysis which, once completed, will embody a detailed record of the global atmosphere...
RoB 2: a revised tool for assessing risk of bias in randomised trials
Assessment of risk of bias is regarded as an essential component of a systematic review on the effects of an intervention. The most commonly used tool for randomised trials is t...
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. Challenges in adapting Transformer ...
Squeeze-and-Excitation Networks
Convolutional neural networks are built upon the convolution operation, which extracts informative features by fusing spatial and channel-wise information together within local ...
IQ-TREE: A Fast and Effective Stochastic Algorithm for Estimating Maximum-Likelihood Phylogenies
Large phylogenomics data sets require fast tree inference methods, especially for maximum-likelihood (ML) phylogenies. Fast programs exist, but due to inherent heuristics to fin...
fastp: an ultra-fast all-in-one FASTQ preprocessor
Abstract Motivation Quality control and preprocessing of FASTQ files are essential to providing clean data for downstream analysis. Traditionally, a different tool is used for e...