• Publications
  • Influence
3D Dilated Multi-Fiber Network for Real-time Brain Tumor Segmentation in MRI
TLDR
We propose a highly efficient 3D CNN to achieve real-time dense volumetric segmentation for 3D MRI brain tumor segmentation. Expand
  • 17
  • 1
  • PDF
Efficient Patch-Wise Semantic Segmentation for Large-Scale Remote Sensing Images
TLDR
A novel patch-wise semantic segmentation method with a new training strategy based on fully convolutional networks is presented to process high-resolution and large-scale remote sensing images. Expand
  • 20
  • 1
  • PDF
An Improved Canny Algorithm with Adaptive Threshold Selection
Canny is a classic algorithm of edge detection which has been widely applied in various fields of image processing for years. However, the algorithm has some defects. The most serious defect is thatExpand
  • 8
  • 1
  • PDF
Boosted Transformer for Image Captioning
Image captioning attempts to generate a description given an image, usually taking Convolutional Neural Network as the encoder to extract the visual features and a sequence model, among which theExpand
  • 4
  • 1
  • PDF
A dynamic volume measurement system with structured light vision
  • J. Li, Gang Liu, Y. Liu
  • Computer Science
  • 31st Youth Academic Annual Conference of Chinese…
  • 1 November 2016
TLDR
This paper proposed a dynamic volume measurement system based on the line structured light vision sensor for real-time volume statistics. Expand
  • 6
  • 1
Learning Approaches of Construction Engineering Students: A Comparative Study between Hong Kong and Mainland China
Abstract Hong Kong is a developed city that utilizes innovative technologies. However, students in Hong Kong, especially in recent years, have been criticized for not adopting a deep learningExpand
  • 19
  • 1
Real-time Detection of Steel Strip Surface Defects Based on Improved YOLO Detection Network
Abstract The surface defects of steel strip have diverse and complex features, and surface defects caused by different production lines tend to have different characteristics. Therefore, theExpand
  • 29
Dense Semantic Labeling with Atrous Spatial Pyramid Pooling and Decoder for High-Resolution Remote Sensing Imagery
TLDR
Dense semantic labeling is significant in high-resolution remote sensing imagery research and it has been widely used in land-use analysis and environment protection. Expand
  • 26
  • PDF
Collaborative Deconvolutional Neural Networks for Joint Depth Estimation and Semantic Segmentation
TLDR
We propose a collaborative deconvolutional neural network (C-DCNN) to jointly model semantic segmentation and depth estimation for mutual promotion. Expand
  • 13
The process control system based on LabVIEW in a hardening die steel production line
TLDR
This article discusses the design of a process control system for a hardening production line of die steel in a steel plant in China under the LabVIEW. Expand
  • 4