Speed up deep neural network based pedestrian detection by sharing features across multi-scale models
Authors:
- Xiaoheng JiangXJXiaoheng Jiang
- Yanwei PangYPYanwei Pang
- Xuelong LiXLXuelong Li
- Jing PanJPJing Pan
Open Access
- 1 April 2016
- journal article
- Published by Elsevier in Neurocomputing
- Vol. 185, 163-170
Abstract
No abstract availableKeywords
Funding Information
- National Basic Research Program of China (2014CB340400)
- National Natural Science Foundation of China (61172121, 61271412, 61472274, 61222109, 61503274)
- Key Research Program of the Chinese Academy of Sciences (KGZD-EW-T03)
- Excellent Young Scholar of the Tianjin University of Technology and Education (RC14-46)
This publication has 28 references indexed in Scilit:
- An improved radial basis function neural network for object image retrievalNeurocomputing, 2015
- AU-inspired Deep Networks for Facial Expression Feature LearningNeurocomputing, 2015
- Efficient object detection by prediction in 3D spaceSignal Processing, 2015
- Flexible sliding windows with adaptive pixel stridesSignal Processing, 2015
- Caffe2014
- Goal-oriented behavior sequence generation based on semantic commands using multiple timescales recurrent neural network with initial state correctionNeurocomputing, 2014
- Distributed Object Detection With Linear SVMsIEEE Transactions on Cybernetics, 2014
- Fast image scanning with deep max-pooling convolutional neural networks2013
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- Histograms of Oriented Gradients for Human Detection2005