Knowledge Commons of Institute of Automation,CAS
Dynamic fusion of convolutional features based on spatial and temporal attention for visual tracking | |
Zhao, Dongcheng1,2; Zeng, Yi1,2,3,4 | |
2019-09 | |
会议名称 | 2019 International Joint Conference on Neural Networks (IJCNN) |
会议日期 | 14-19 July 2019 |
会议地点 | Budapest, Hungary |
摘要 | Convolutional neural networks (CNN) based trackers have been widely employed in visual object tracking due to their powerful representations. Features from different CNN layers encode different information. Deeper layers contain more semantic information, while the resolution is too coarse to localize the target. Shallower layers carry more detail information but are less robust for appearance variations. In this paper, we propose an algorithm which incorporates the Spatial and Temporal attention to take full advantage of the Hierarchical Convolutional Features for Tracking (STHCFT). We firstly learn correlation filters on each convolutional layer. Based on the spatial attention inspired by the paraventricular thalamus (PVT) in the brain, we choose the most important layer to build the base response, and the others to be the auxiliary responses. In addition, we make full use of the temporal attention to determine the weights of the auxiliary responses. Finally, the target is located by the maximum value of the fused responses. Extensive experimental results on the benchmark OTB-2013 and OTB-2015 have shown the proposed algorithm performs favorably against several state-of-the-art trackers. |
关键词 | Paraventricular Thalamus Spatial Attention Temporal Attention |
DOI | 10.1109/IJCNN.2019.8852301 |
收录类别 | EI |
资助项目 | Major Research Program of Shandong Province[2018CXGC1503] ; CETC Joint Fund[6141B08010103] ; Beijing Municipality of Science and Technology[Z181100001518006] ; Strategic Priority Research Program of Chinese Academy of Sciences[XDB32070100] |
语种 | 英语 |
七大方向——子方向分类 | 类脑模型与计算 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44566 |
专题 | 脑图谱与类脑智能实验室_类脑认知计算 |
通讯作者 | Zeng, Yi |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Res Ctr Brain Inspired Intelligence, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai, Peoples R China 4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China |
第一作者单位 | 类脑智能研究中心 |
通讯作者单位 | 类脑智能研究中心; 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Zhao, Dongcheng,Zeng, Yi. Dynamic fusion of convolutional features based on spatial and temporal attention for visual tracking[C],2019. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
08852301.pdf(1953KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
个性服务 |
推荐该条目 |
保存到收藏夹 |
查看访问统计 |
导出为Endnote文件 |
谷歌学术 |
谷歌学术中相似的文章 |
[Zhao, Dongcheng]的文章 |
[Zeng, Yi]的文章 |
百度学术 |
百度学术中相似的文章 |
[Zhao, Dongcheng]的文章 |
[Zeng, Yi]的文章 |
必应学术 |
必应学术中相似的文章 |
[Zhao, Dongcheng]的文章 |
[Zeng, Yi]的文章 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论