Capturing Relevant Context for Visual Tracking
文献类型：期刊论文
| 作者 | Zhang, Yuping2; Ma, Bo2; Wu, Jiahao2; Huang, Lianghua1,3 ; Shen, Jianbing4
|
| 刊名 | IEEE TRANSACTIONS ON MULTIMEDIA
 |
| 出版日期 | 2021 |
| 卷号 | 23页码:4232-4244 |
| 关键词 | Local neighborhood graph long-range dependencies long-term tracking visual object tracking |
| ISSN号 | 1520-9210 |
| DOI | 10.1109/TMM.2020.3038310 |
| 通讯作者 | Ma, Bo(bma000@bit.edu.cn) |
| 英文摘要 | Studies have shown that contextual information can promote the robustness of trackers. However, trackers based on convolutional neural networks (CNNs) only capture local features, which limits their performance. We propose a novel relevant context block (RCB), which employs graph convolutional networks to capture the relevant context. In particular, it selects the k largest contributors as nodes for each query position (unit) that contain meaningful and discriminative contextual information and updates the nodes by aggregating the differences between the query position and its contributors. This operation can be easily incorporated into the existing networks and can be easily end-to-end trained using a standard backpropagation algorithm. To verify the effectiveness of RCB, we apply it to two trackers, SiamFC and GlobalTrack, respectively, and the two improved trackers are referred to as Siam-RCB andGlobalTrack-RCB. Extensive experiments onOTB, VOT, UAV123, LaSOT, TrackingNet, OxUvA, and VOT2018LT show the superiority of our method. For example, our Siam-RCB outperforms SiamFC by a very large margin (up to 11.2% in the success score and 7.8% in the precision score) on the OTB-100 benchmark. |
| WOS关键词 | OBJECT TRACKING |
| 资助项目 | National Key Research and Development Program of China[2020YFC0832502] ; National Natural Science Foundation of China[62072042] ; National Natural Science Foundation of China[61961015] |
| WOS研究方向 | Computer Science ; Telecommunications |
| 语种 | 英语 |
| WOS记录号 | WOS:000720519900025 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Key Research and Development Program of China ; National Natural Science Foundation of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/46473]  |
| 专题 | 智能系统与工程 |
| 通讯作者 | Ma, Bo |
| 作者单位 | 1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 2.Beijing Inst Technol, Sch Comp Sci & Technol, Beijing Lab Intelligent Informat Technol, Beijing 100081, Peoples R China 3.Chinese Acad Sci, Ctr Res Intelligent Syst & Engn, Inst Automat, Beijing 100190, Peoples R China 4.Incept Inst Artificial Intelligence, Abu Dhabi, U Arab Emirates |
| 推荐引用方式 GB/T 7714 | Zhang, Yuping,Ma, Bo,Wu, Jiahao,et al. Capturing Relevant Context for Visual Tracking[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2021,23:4232-4244. |
| APA | Zhang, Yuping,Ma, Bo,Wu, Jiahao,Huang, Lianghua,&Shen, Jianbing.(2021).Capturing Relevant Context for Visual Tracking.IEEE TRANSACTIONS ON MULTIMEDIA,23,4232-4244. |
| MLA | Zhang, Yuping,et al."Capturing Relevant Context for Visual Tracking".IEEE TRANSACTIONS ON MULTIMEDIA 23(2021):4232-4244. |
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。