Knowledge Commons of Institute of Automation,CAS
SPCNet: Scale Position Correlation Network for End-to-End Visual Tracking | |
Wang, Qiang1,2; Gao, Jin1; Zhang, Mengdan1,2; Xing, Junliang1; Hu, Weiming1 | |
2018 | |
会议名称 | 24th International Conference on Pattern Recognition |
会议日期 | August 20th-24th 2018 |
会议地点 | Beijing, China |
产权排序 | 1 |
摘要 | We present a novel Scale Position CorrelationNetwork (SPCNet) for learning to track objects robustly and efficiently. Different from most previous Correlation Filter (CF) based tracking models, SPCNet unifies the feature representation learning and CF based appearance modeling within one end-to-end learnable framework. In particular, SPCNet learns to track objects within a joint scale-position space, and is very effective in learning features for the accurate prediction of object scale and position. To learn our model from end to end, the SPCNet introduces a differentiable correlation filter layer into a Siamese architecture. Therefore, the localization error can be effectively back-propagated through the whole network, enabling fast adaptation of feature learning and appearance modeling for the objects to be tracked. Such task driven feature learning admits a very lightweight design that can be efficiently pretrained. In addition, the dense appearance modeling in the joint scale-position space is also efficient. It benefits from the computation of gradients within the Fourier frequency domain. Such careful architecture design ensures that SPCNet is effective and efficient with a small model size. Extensive experimental analyses and evaluations on three largest benchmarks, OTB-2013, OTB-2015, and VOT2015, demonstrate its superiority over many state-of-the-art algorithms. |
其他摘要 |
|
收录类别 | EI |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/21613 |
专题 | 多模态人工智能系统全国重点实验室_视频内容安全 |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Wang, Qiang,Gao, Jin,Zhang, Mengdan,et al. SPCNet: Scale Position Correlation Network for End-to-End Visual Tracking[C],2018. |
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 | ||
SPCNet.pdf(846KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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