• Publications
  • Influence
Thresholding based on variance and intensity contrast
TLDR
Theoretical bounds of the weight are given for the uniformly distributed background and object, followed by the procedure to estimate the weight from prior knowledge. Expand
  • 102
  • 4
  • PDF
Arc-based evaluation and detection of ellipses
  • Y. Qiao, S. Ong
  • Mathematics, Computer Science
  • Pattern Recognit.
  • 1 July 2007
TLDR
We propose the use of elliptic arcs as a reliable criterion for ellipse evaluation and reconstruction. Expand
  • 42
  • 3
Connectivity-based multiple-circle fitting
  • Y. Qiao, S. Ong
  • Mathematics, Computer Science
  • Pattern Recognit.
  • 1 April 2004
This paper proposes a connectivity-based method for circle fitting. The use of pixel connectivity effectively avoids false circle detection, improves the robustness against noise and significantlyExpand
  • 32
  • 1
  • PDF
Efficient Image Super-Resolution Using Pixel Attention
TLDR
This work aims at designing a lightweight convolutional neural network with a newly proposed pixel attention scheme. Expand
  • 5
  • 1
  • PDF
AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results
TLDR
This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results. Expand
  • 15
  • PDF
Combining CNN and MIL to Assist Hotspot Segmentation in Bone Scintigraphy
TLDR
We use sparse autoencoder and convolution neural network to train an image-level classifier that label input image as normal or suspected. Expand
  • 8
Combining CGAN and Mil for Hotspot Segmentation in Bone Scintigraphy
TLDR
We propose a new framework to detect and extract hotspots in thoracic region by integrating the techniques of both conditional generative adversarial networks (cGAN) and multiple instance learning (MIL). Expand
  • 1
Enhanced Quadratic Video Interpolation
TLDR
We further improve the performance of QVI from three facets and propose an enhanced quadratic video interpolation (EQVI) model, which can be regarded as a contextual augmentation process. Expand
  • 2
  • PDF
Pose-Assisted Multi-Camera Collaboration for Active Object Tracking
TLDR
We propose a novel Pose-Assisted Multi-Camera Collaboration System, which enables a camera to cooperate with the others by sharing camera poses for active object tracking. Expand
  • 3
  • PDF
Attention-Driven Dynamic Graph Convolutional Network for Multi-label Image Recognition
TLDR
We propose an Attention-Driven Dynamic Graph Convolutional Network to model the relation of content-aware category representations that are generated by a Semantic Attention Module (SAM). Expand
  • 2
  • PDF