Two-stage aware attentional Siamese network for visual tracking
文献类型:期刊论文
作者 | X. L. Sun; G. L. Han; L. H. Guo; H. Yang; X. T. Wu and Q. Q. Li |
刊名 | Pattern Recognition |
出版日期 | 2022 |
卷号 | 124页码:13 |
ISSN号 | 0031-3203 |
DOI | 10.1016/j.patcog.2021.108502 |
英文摘要 | Siamese networks have achieved great success in visual tracking with the advantages of speed and accuracy. However, how to track an object precisely and robustly still remains challenging. One reason is that multiple types of features are required to achieve good precision and robustness, which are unattainable by a single training phase. Moreover, Siamese networks usually struggle with online adaption problem. In this paper, we present a novel two-stage aware attentional Siamese network for tracking (Ta-ASiam). Concretely, we first propose a position-aware and an appearance-aware training strategy to optimize different layers of Siamese network. By introducing diverse training patterns, two types of required features can be captured simultaneously. Then, following the rule of feature distribution, an effective feature selection module is constructed by combining both channel and spatial attention networks to adapt to rapid appearance changes of the object. Extensive experiments on various latest benchmarks have well demonstrated the effectiveness of our method, which significantly outperforms state-of-the-art trackers. (c) 2021 Elsevier Ltd. All rights reserved. |
URL标识 | 查看原文 |
语种 | 英语 |
源URL | [http://ir.ciomp.ac.cn/handle/181722/67204] |
专题 | 中国科学院长春光学精密机械与物理研究所 |
推荐引用方式 GB/T 7714 | X. L. Sun,G. L. Han,L. H. Guo,et al. Two-stage aware attentional Siamese network for visual tracking[J]. Pattern Recognition,2022,124:13. |
APA | X. L. Sun,G. L. Han,L. H. Guo,H. Yang,&X. T. Wu and Q. Q. Li.(2022).Two-stage aware attentional Siamese network for visual tracking.Pattern Recognition,124,13. |
MLA | X. L. Sun,et al."Two-stage aware attentional Siamese network for visual tracking".Pattern Recognition 124(2022):13. |
入库方式: OAI收割
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。