Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
Tiny SSD: A Tiny Single-Shot Detection Deep Convolutional Neural Network for Real-Time Embedded Object Detection
- A. Wong, M. Shafiee, Francis Li, Brendan Chwyl
- Computer Science
- 15th Conference on Computer and Robot Vision (CRV…
- 19 February 2018
This paper introduces Tiny SSD, a single-shot detection deep convolutional neural network for real-time embedded object detection that is composed of a highly optimized, non-uniform Fire subnetwork stack and a non- uniform sub-network stack of highly optimized SSD-based auxiliary convolutionsal feature layers designed specifically to minimize model size while maintaining object detection performance. Expand
Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in Video
We propose a new framework called Fast YOLO, a fast You Only Look Once framework which accelerates Y OLOv2 to be able to perform object detection in video on embedded devices in a real-time. Expand
Nanosecond pulse electric field activation of platelet-rich plasma reduces myocardial infarct size and improves left ventricular mechanical function in the rabbit heart.
In the current study, we used the novel, nonchemical method of nanosecond pulsed electric fields (nsPEF) to investigate the efficiency of a protocol involving the in vivo treatment of the ischemic… Expand
Simultaneous Projector-Camera Self-Calibration for Three-Dimensional Reconstruction and Projection Mapping
- Francis Li, Hicham Sekkati, +5 authors A. Wong
- Mathematics, Computer Science
- IEEE Transactions on Computational Imaging
- 16 January 2017
We propose a novel optimization approach for geometric calibration of a projector-camera system that estimates the intrinsic, extrinsic, and distortion parameters of both the camera and projector in an automatic fashion using structured light. Expand
SquishedNets: Squishing SqueezeNet further for edge device scenarios via deep evolutionary synthesis
This study explores the utility of combining architectural modifications and an evolutionary synthesis strategy for synthesizing even smaller deep neural architectures based on the more recent SqueezeNet v1.1 macroarchitecture for applications with fewer target classes. Expand
Malnutrition risks and their associated factors among home-living older Chinese adults in Hong Kong: hidden problems in an affluent Chinese community
BackgroundAlthough China is undergoing rapid economic development, it is facing an ageing population. No data exists on malnutrition risks of older adults in an affluent Chinese society. The aim of… Expand
StressedNets: Efficient Feature Representations via Stress-induced Evolutionary Synthesis of Deep Neural Networks
We extend upon the evolutionary synthesis strategy for achieving efficient feature extraction via the introduction of a stress-induced evolutionary synthesis framework, where stress signals are imposed upon the synapses of a deep neural network during training to induce stress and steer the synthesis process towards the production of more efficient deep neural networks over successive generations. Expand
Exploring the Imposition of Synaptic Precision Restrictions For Evolutionary Synthesis of Deep Neural Networks
A key contributing factor to incredible success of deep neural networks has been the significant rise on massively parallel computing devices allowing researchers to greatly increase the size and depth of deep Neural networks, leading to significant improvements in modeling accuracy. Expand
Real-time monitoring and control on deep inspiration breath-hold for lung cancer radiotherapy-Combination of ABC and external marker tracking.
PURPOSE In this article, the breath-hold and gating concepts were combined for application of lung cancer radiation treatment. The tumor movement was immobilized based on deep inspiration breath hold… Expand
Treatment of primary liver cancer using highly-conformal radiotherapy with kV-image guidance and respiratory control.
PURPOSE To implement a reliable, practical and reproducible treatment procedure, based on in-room kV-image guidance and respiratory control, for liver cancer patients treated with high dose conformal… Expand