Efficient Convolution Neural Networks for Object Tracking Using Separable Convolution and Filter Pruning

Efficient Convolution Neural Networks for Object Tracking Using Separable Convolution and Filter Pruning

Object tracking based on deep learning is a hot topic in computer vision with many applications. Due to high computation and memory costs, it is difficult to deploy convolutional neural networks (CNNs) for object tracking on embedded systems with limited hardware resources. This paper uses the Siame...

Full description

Bibliographic Details
Main Authors: Yuanhong Mao, Zhanzhuang He, Zhong Ma, Xuehan Tang, Zhuping Wang
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Object tracking
deep learning
separable convolution
filter pruning
Online Access:https://ieeexplore.ieee.org/document/8786196/

Similar Items

Similar Items