• Publications
  • Influence
Generative Image Inpainting with Contextual Attention
We present a unified feedforward, fully convolutional neural network with a novel contextual attention layer for image inpainting. Expand
  • 790
  • 169
  • PDF
Live or let die: the cell's response to p53
Compared with many normal tissues, cancer cells are highly sensitized to apoptotic signals, and survive only because they have acquired lesions — such as loss of p53 — that prevent or impede cellExpand
  • 3,147
  • 136
  • PDF
Universal Style Transfer via Feature Transforms
We present a simple yet effective method for universal style transfer, which enjoys the style-agnostic generalization ability with marginally compromised visual quality and execution efficiency. Expand
  • 312
  • 94
  • PDF
Free-Form Image Inpainting With Gated Convolution
We present a generative image inpainting system to complete images with free-form mask and guidance. Expand
  • 370
  • 81
  • PDF
MAttNet: Modular Attention Network for Referring Expression Comprehension
In this paper, we address referring expression comprehension: localizing an image region described by a natural language expression, we propose to decompose them into three modular components related to subject appearance, location, and relationship to other objects. Expand
  • 220
  • 65
  • PDF
The G(0)/G(1) switch gene 2 regulates adipose lipolysis through association with adipose triglyceride lipase.
Adipose triglyceride lipase (ATGL) is the rate-limiting enzyme for triacylglycerol (TAG) hydrolysis in adipocytes. The precise mechanisms whereby ATGL is regulated remain uncertain. Here, weExpand
  • 343
  • 53
  • PDF
RAPID: Rating Pictorial Aesthetics using Deep Learning
We present the RAPID (RAting PIctorial aesthetics using Deep learning) system, which adopts a novel deep convolutional neural network approach to enable automatic feature learning. Expand
  • 243
  • 46
  • PDF
MMDetection: Open MMLab Detection Toolbox and Benchmark
We present MMDetection, an object detection toolbox that contains a rich set of object detection and instance segmentation methods as well as related components and modules. Expand
  • 358
  • 37
  • PDF
Deep Multi-patch Aggregation Network for Image Style, Aesthetics, and Quality Estimation
This paper investigates problems of image style, aesthetics, and quality estimation, which require fine-grained details from high-resolution images, utilizing deep neural network training approach. Expand
  • 189
  • 32
  • PDF
Improved Response to Disasters and Outbreaks by Tracking Population Movements with Mobile Phone Network Data: A Post-Earthquake Geospatial Study in Haiti
Linus Bengtsson and colleagues examine the use of mobile phone positioning data to monitor population movements during disasters and outbreaks, finding that reports on population movements can beExpand
  • 414
  • 22
  • PDF