High-Performance Visual Tracking Based on High-Order Pooling Network
Convolution Neural Network (CNN) features have been widely used in visual tracking due to their powerful representation. As an important component of CNN, the pooling layer plays a critical role, but the max/average/min operation only explores the first-order information, which limits the discrimina...
Main Authors: | Xinxi Feng, Lei Pu |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2022-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9899441/ |
Similar Items
-
Second-Order Spatial-Temporal Correlation Filters for Visual Tracking
by: Yufeng Yu, et al.
Published: (2022-02-01) -
Robust Visual Tracking Based on Adaptive Multi-Feature Fusion Using the Tracking Reliability Criterion
by: Lin Zhou, et al.
Published: (2020-12-01) -
Object Tracking Algorithm Based on Dual Color Feature Fusion with Dimension Reduction
by: Shuo Hu, et al.
Published: (2018-12-01) -
A New Video Tracking Algorithm Based on Multi-Complementary Features Fusion
Published: (2019-04-01) -
A Hybrid Visual Tracking Algorithm Based on SOM Network and Correlation Filter
by: Yuanping Zhang, et al.
Published: (2021-04-01)