High-Performance Discriminative Tracking with Target-Aware Feature Embeddings | |
Yu, Bin2,3; Tang, Ming2; Zheng, Linyu2,3; Zhu, Guibo2,3; Wang, Jinqiao1,2,3; Lu, Hanqing2,3 | |
2021-10-22 | |
会议日期 | 2021-12-19--2021-12-21 |
会议地点 | Zhuhai, Guangdong, China |
关键词 | Object Tracking |
DOI | 10.1007/978-3-030-88004-0_1 |
英文摘要 | Discriminative model-based trackers have made remarkable progress recently. However, due to the extreme imbalance of foreground and background samples, the learned model is hard to fit the training samples well in the online tracking. In this paper, to alleviate the negative influence caused by the imbalance issue, we propose a novel construction scheme of target-aware features for online discriminative tracking. Specifically, we design a sub-network to generate target-aware feature embeddings of foregrounds and backgrounds by projecting the learned feature embeddings into the target-aware feature space. Then, a model |
源文献作者 | CSIG ; CAAI ; CCF ; CAA |
会议录出版者 | Springer |
会议录出版地 | Switzerland |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/48789] |
专题 | 自动化研究所_模式识别国家重点实验室_图像与视频分析团队 |
通讯作者 | Yu, Bin |
作者单位 | 1.ObjectEye Inc., Beijing, China 2.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, No.95, Zhongguancun East Road, Beijing 100190, China 3.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China |
推荐引用方式 GB/T 7714 | Yu, Bin,Tang, Ming,Zheng, Linyu,et al. High-Performance Discriminative Tracking with Target-Aware Feature Embeddings[C]. 见:. Zhuhai, Guangdong, China. 2021-12-19--2021-12-21. |
个性服务 |
查看访问统计 |
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