中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 视频内容安全团队
Manipulating Template Pixels for Model Adaptation of Siamese Visual Tracking

文献类型：期刊论文

作者Li, Zhenbang2,3; Li, Bing2,3; Gao, Jin2,3; Li, Liang1; Hu, Weiming3,4
刊名IEEE SIGNAL PROCESSING LETTERS
出版日期2020
卷号27页码:1690-1694
关键词Adaptation models Target tracking Task analysis Visualization Feature extraction Object tracking Training Model adaptation siamese networks visual tracking
ISSN号1070-9908
DOI10.1109/LSP.2020.3025406
通讯作者Gao, Jin(jin.gao@nlpr.ia.ac.cn)
英文摘要In this letter, we show that the challenging model adaptation task in visual object tracking can be handled by simply manipulating pixels of the template image in Siamese networks. For a target that is not included in the offline training set, a slight modification of the template image pixels will improve the prediction result of the offline trained Siamese network. The popular adversarial example generation methods can be used to perform template pixel manipulation for model adaptation. Different from current template update methods, which aim to combine the target features from previous frames, we focus on the initial adaptation using target ground-truth in the first frame. Our model adaptation method is pluggable, in the sense that it does not alter the overall architecture of its base tracker. To our knowledge, this work is the first attempt to directly manipulating template pixels for model adaptation in Siamese-based trackers. Extensive experiments on recent benchmarks demonstrate that our method achieves better performance than some other state-of-the-art trackers. Our code is available at https://github.com/lizhenbang56/MTP.
资助项目National Key R&D Program of China[2018AAA0102802] ; National Key R&D Program of China[2018AAA0102803] ; National Key R&D Program of China[2018AAA0102800] ; NSFC-General Technology Collaborative Fund for Basic Research[U1636218] ; Natural Science Foundation of China[61751212] ; Natural Science Foundation of China[61721004] ; Natural Science Foundation of China[61772225] ; Natural Science Foundation of China[61972394] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC040] ; National Natural Science Foundation of Guangdong[2018B030311046]
WOS研究方向Engineering
语种英语
WOS记录号WOS:000576408300008
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key R&D Program of China ; NSFC-General Technology Collaborative Fund for Basic Research ; Natural Science Foundation of China ; Key Research Program of Frontier Sciences, CAS ; National Natural Science Foundation of Guangdong
源URL[http://ir.ia.ac.cn/handle/173211/42087]  
专题自动化研究所_模式识别国家重点实验室_视频内容安全团队
通讯作者Gao, Jin
作者单位1.Beijing Inst Basic Med Sci, Brain Sci Ctr, Beijing 100850, Peoples R China
2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China
4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Li, Zhenbang,Li, Bing,Gao, Jin,et al. Manipulating Template Pixels for Model Adaptation of Siamese Visual Tracking[J]. IEEE SIGNAL PROCESSING LETTERS,2020,27:1690-1694.
APA Li, Zhenbang,Li, Bing,Gao, Jin,Li, Liang,&Hu, Weiming.(2020).Manipulating Template Pixels for Model Adaptation of Siamese Visual Tracking.IEEE SIGNAL PROCESSING LETTERS,27,1690-1694.
MLA Li, Zhenbang,et al."Manipulating Template Pixels for Model Adaptation of Siamese Visual Tracking".IEEE SIGNAL PROCESSING LETTERS 27(2020):1690-1694.

入库方式： OAI收割

来源：自动化研究所

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。