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
Nocal-Siam: Refining Visual Features and Response With Advanced Non-Local Blocks for Real-Time Siamese Tracking

文献类型：期刊论文

作者Tan, Huibin1; Zhang, Xiang4,5; Zhang, Zhipeng3; Lan, Long4,5; Zhang, Wenju2; Luo, Zhigang2
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2021
卷号30页码:2656-2668
关键词Target tracking Visualization Feature extraction Real-time systems Oceans Convolution Task analysis Siamese trackers non-local attention supervisedly attentive
ISSN号1057-7149
DOI10.1109/TIP.2021.3049970
通讯作者Zhang, Xiang(zhangxiang08@nudt.edu.cn) ; Lan, Long(long.lan@nudt.edu.cn)
英文摘要Siamese trackers contain two core stages, i.e., learning the features of both target and search inputs at first and then calculating response maps via the cross-correlation operation, which can also be used for regression and classification to construct typical one-shot detection tracking framework. Although they have drawn continuous interest from the visual tracking community due to the proper trade-off between accuracy and speed, both stages are easily sensitive to the distracters in search branch, thereby inducing unreliable response positions. To fill this gap, we advance Siamese trackers with two novel non-local blocks named Nocal-Siam, which leverages the long-range dependency property of the non-local attention in a supervised fashion from two aspects. First, a target-aware non-local block (T-Nocal) is proposed for learning the target-guided feature weights, which serve to refine visual features of both target and search branches, and thus effectively suppress noisy distracters. This block reinforces the interplay between both target and search branches in the first stage. Second, we further develop a location-aware non-local block (L-Nocal) to associate multiple response maps, which prevents them inducing diverse candidate target positions in the future coming frame. Experiments on five popular benchmarks show that Nocal-Siam performs favorably against well-behaved counterparts both in quantity and quality.
资助项目National Natural Science Foundation of China[61806213] ; National Natural Science Foundation of China[61906210]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000616314200015
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/43193]  
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Zhang, Xiang; Lan, Long
作者单位1.Natl Univ Def Technol, Dept Sci & Technol Parallel & Distributed Proc, Changsha 410073, Peoples R China
2.Natl Univ Def Technol, Sci & Technol Parallel & Distributed Proc, Changsha 410073, Peoples R China
3.Chinese Acad Sci, Inst Automat, Pattern Recognit & Intelligent Syst, Beijing 100190, Peoples R China
4.Natl Univ Def Technol, State Key Lab High Performance Comp, Changsha 410073, Peoples R China
5.Natl Univ Def Technol, Inst Quantum Informat, Changsha 410073, Peoples R China
推荐引用方式
GB/T 7714		 Tan, Huibin,Zhang, Xiang,Zhang, Zhipeng,et al. Nocal-Siam: Refining Visual Features and Response With Advanced Non-Local Blocks for Real-Time Siamese Tracking[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2021,30:2656-2668.
APA Tan, Huibin,Zhang, Xiang,Zhang, Zhipeng,Lan, Long,Zhang, Wenju,&Luo, Zhigang.(2021).Nocal-Siam: Refining Visual Features and Response With Advanced Non-Local Blocks for Real-Time Siamese Tracking.IEEE TRANSACTIONS ON IMAGE PROCESSING,30,2656-2668.
MLA Tan, Huibin,et al."Nocal-Siam: Refining Visual Features and Response With Advanced Non-Local Blocks for Real-Time Siamese Tracking".IEEE TRANSACTIONS ON IMAGE PROCESSING 30(2021):2656-2668.

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。