.png){kind=icon}
返回
Fast Visual Tracking With Siamese Oriented Region Proposal Network
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2022.3178656.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Current oriented visual tracking depends on segmentation-driven framework brings about expensive computation cost, which becomes the bottleneck in the practical application. This paper proposes a simple and effective Siamese oriented Region Proposal Network (Siamese-ORPN) for visual tracking. Specifically, we propose to use oriented RPN on the similarity feature maps to directly generate high-quality oriented proposals in a nearly cost-free manner. Moreover, a top-down feature fusion network is proposed as the backbone for feature extraction and feature fusion, which can achieve substantial gains from the diversity of visual-semantic hierarchies. The Siamese-ORPN runs at 85 fps while achieving leading performance on the benchmark datasets including VOT2018 (44.6% EAO) and VOT2019 (39.6% EAO).
Keyword:
Proposals
Feature extraction
Visualization
Convolution
Correlation
Target tracking
Deconvolution
Oriented visual tracking
Siamese network
oriented RPN
feature fusion
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
.png){kind=icon}
分享收藏
查看更多内容