• Publications
  • Influence
DeepSkeleton: Learning Multi-Task Scale-Associated Deep Side Outputs for Object Skeleton Extraction in Natural Images
TLDR
We present a novel fully convolutional network with multiple scale-associated side outputs to address the unknown scale problem in skeleton extraction from natural images. Expand
  • 50
  • 15
  • PDF
Deep Differentiable Random Forests for Age Estimation
TLDR
We propose two Deep Differentiable Random Forests methods, Deep Label Distribution Learning Forest and Deep Regression Forest, for age estimation. Expand
  • 7
  • PDF
Deep Hough Transform for Semantic Line Detection
TLDR
We propose a one-shot end-to-end framework by incorporating the classical Hough transform into deeply learned representations. Expand
  • 4
  • PDF
Model-Agnostic Structured Sparsification with Learnable Channel Shuffle
TLDR
We propose a model-agnostic and highly compressible structured sparsification method for efficient network compression. Expand
Emergency medical rescue system in China: current status and recommendations
The paper briefed characteristics of emergency medical centers in developed countries, described the current status in China, and analyzed problems found in the emergency medical rescue system in theExpand
Research on Corrosion Characteristics and Performance Degradation of Basalt Fiber Concrete under Sodium Magnesium Sulfate Corrosion Environment
ABSTRACT Wang, Z.-S.; Li, Y.-K.; Lu, J.-L.; Tian, J.-B., and Zhao, K., 2020. Research on corrosion characteristics and performance degradation of basalt fiber concrete under sodium magnesium sulfateExpand
GeoMatch
We develop GeoMatch as a novel, scalable, and efficient big-data pipeline for large-scale map matching on Apache Spark. GeoMatch improves existing spatial big-data solutions by utilizing a novelExpand
Dependency Aware Filter Pruning
TLDR
We propose a principled criteria to identify unimportant convolutional filters based on the local channel importance, and introduce an automaticregularization-control mechanism to dynamically adjust the coefficient of sparsity regularization. Expand
Skeletonization in natural images and its application to object recognition
Abstract Object skeletons are utilized to represent objects because they clarify the structural relationship between various parts of the object. Skeletonization in natural images is a challengingExpand
This is the title of an example SEG abstract using Microsoft Word 11-point bold type
The presence of a hard rugose water bottom, strong near water bottom reflectors, and shallow Tertiary carbonates makes the Dampier sub-basin of Australia’s North West Shelf vulnerable to multipleExpand