• Publications
  • Influence
CANet: Class-Agnostic Segmentation Networks With Iterative Refinement and Attentive Few-Shot Learning
TLDR
We present CANet, a class-agnostic segmentation network that performs few-shot segmentation on new classes with only a few annotated images available. Expand
  • 71
  • 25
  • PDF
Part-Based Visual Tracking with Online Latent Structural Learning
TLDR
We extend the online algorithm pegasos to the structured prediction case (i.e., predicting the location of bounding boxes) with latent part variables. Expand
  • 202
  • 12
  • PDF
Satellite Remote Sensing of Surface Urban Heat Islands: Progress, Challenges, and Perspectives
TLDR
The surface urban heat island (SUHI), which represents the difference of land surface temperature (LST) in urban relativity to neighboring non-urban surfaces, is usually measured using satellite LST data. Expand
  • 122
  • 8
  • PDF
A novel intelligent diagnosis method using optimal LS-SVM with improved PSO algorithm
TLDR
Improved particle swarm optimization algorithm and least squares support vector machines are introduced into the fault diagnosis to propose a novel intelligent diagnosis method, which is applied to diagnose the faults of motor bearing in this paper. Expand
  • 198
  • 4
Efficient dense labelling of human activity sequences from wearables using fully convolutional networks
TLDR
We propose an efficient method for predicting the label of each sample, which we call dense labelling, in a sequence of activity data of arbitrary length based on a fully convolutional network (FCN) design that overcomes the problems posed by multi-class windows and fixed size sequence partitions imposed during training. Expand
  • 30
  • 4
Optimal Force Distribution Based on Slack Rope Model in the Incompletely Constrained Cable-Driven Parallel Mechanism of FAST Telescope
This paper addressed the determination of the tension distribution in the slack steel wires of the incompletely constrained cable-driven parallel mechanism of FAST telescope. Slack rope hung withExpand
  • 31
  • 4
A Multi-Timescale Quasi-Dynamic Model for Simulation of Cascading Outages
Many blackouts in electric power grids throughout the world are caused by cascading outages, which often involve complex processes in various timescales. The multi-timescale nature of cascadingExpand
  • 49
  • 3
  • PDF
Exploiting Spatial Structure from Parts for Adaptive Kernelized Correlation Filter Tracker
TLDR
We propose a part-based appearance model by exploiting spatial structure from parts. Expand
  • 19
  • 3
Urbanization Effects on Vegetation and Surface Urban Heat Islands in China's Yangtze River Basin
TLDR
In the context of rapid urbanization, systematic research about temporal trends of urbanization effects (UEs) on vegetation and surface urban heat islands (SUHIs) on urban environment is needed. Expand
  • 38
  • 2
  • PDF
Risk Assessment of Multi-Timescale Cascading Outages Based on Markovian Tree Search
TLDR
In the risk assessment of cascading outages, the rationality of simulation and efficiency of computation are both of great significance. Expand
  • 37
  • 2
  • PDF