Publications

FCOS: Fully Convolutional One-Stage Object Detection

We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to semantic segmentation. Almost all stat...

Fast Training of Support Vector Machines Using Sequential Minimal Optimization

This chapter describes a new algorithm for training Support Vector Machines: Sequential Minimal Optimization, or SMO. Training a Support Vector Machine (SVM) requires the soluti...

Assembly of long, error-prone reads using repeat graphs

g:Profiler: a web server for functional enrichment analysis and conversions of gene lists (2019 update)

Abstract Biological data analysis often deals with lists of genes arising from various studies. The g:Profiler toolset is widely used for finding biological categories enriched ...

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper...

Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering

Top-down visual attention mechanisms have been used extensively in image captioning and visual question answering (VQA) to enable deeper image understanding through fine-grained...

Quantum theory, the Church–Turing principle and the universal quantum computer

It is argued that underlying the Church–Turing hypothesis there is an implicit physical assertion. Here, this assertion is presented explicitly as a physical principle: ‘every f...

CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features

Regional dropout strategies have been proposed to enhance performance of convolutional neural network classifiers. They have proved to be effective for guiding the model to atte...

Civilization and Its Discontents

During the summer of 1929, Freud worked on what became this seminal volume of twentieth-century thought. It stands as a brilliant summary of the views on culture from a psychoan...

Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression

Bounding box regression is the crucial step in object detection. In existing methods, while ℓn-norm loss is widely adopted for bounding box regression, it is not tailored to the...

PubChem in 2021: new data content and improved web interfaces

Abstract PubChem (https://pubchem.ncbi.nlm.nih.gov) is a popular chemical information resource that serves the scientific community as well as the general public, with millions ...

PCA-SIFT: a more distinctive representation for local image descriptors

Stable local feature detection and representation is a fundamental component of many image registration and object recognition algorithms. Mikolajczyk and Schmid (June 2003) rec...