Adaptive convolutional layer selection based on historical retrospect for visual tracking
Visual tracking has recently gained a great advance with the use of the convolutional neural network (CNN). Usually, existing CNN‐based trackers exploit the features from a single layer or a certain combination of multiple layers. However, these features only characterise an object from an invariabl...
Main Authors: | Fuhui Tang, Xiankai Lu, Xiaoyu Zhang, Lingkun Luo, Shiqiang Hu, Huanlong Zhang |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2019-04-01
|
Series: | IET Computer Vision |
Subjects: | |
Online Access: | https://doi.org/10.1049/iet-cvi.2018.5194 |
Similar Items
-
Deep Motion-Appearance Convolutions for Robust Visual Tracking
by: Haojie Li, et al.
Published: (2019-01-01) -
Rotation Invariance Regularization for Remote Sensing Image Scene Classification with Convolutional Neural Networks
by: Kunlun Qi, et al.
Published: (2021-02-01) -
Convolutional neural networks in automatic control systems: The state-of-the-art
by: Perišić Natalija B., et al.
Published: (2023-01-01) -
Learning to Propose and Refine for Accurate and Robust Tracking via an Alignment Convolution
by: Zhiyi Mo, et al.
Published: (2023-05-01) -
Moving scene object tracking method based on deep convolutional neural network
by: Long Liu, et al.
Published: (2024-01-01)