Learning Fully Convolutional Network for Visual Tracking With Multi-Layer Feature Fusion

Learning Fully Convolutional Network for Visual Tracking With Multi-Layer Feature Fusion

Convolutional neural networks are powerful models that yield hierarchies of features. In the paper, we present a new approach for general object tracking based on the fully convolutional network with multi-layer feature fusion. The designed network combines semantic information from deep, coarse lay...

Full description

Bibliographic Details
Main Authors: Yangliu Kuai, Gongjian Wen, Dongdong Li
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
FCN
feature fusion
pixel-wise objectness
two-step training
updating strategy
Online Access:https://ieeexplore.ieee.org/document/8643772/

Internet

https://ieeexplore.ieee.org/document/8643772/

Similar Items