CASIA OpenIR  > 多模态人工智能系统全国重点实验室  > 视频内容安全
Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking
Gao, Jin1; Lu, Yan2; Qi, Xiaojuan3; Kou, Yutong1; Li, Bing1; Li, Liang4; Yu, Shan1; Hu, Weiming1
Source PublicationIEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN0162-8828
2024
Volume46Issue:3Pages:1881-1897
Corresponding AuthorHu, Weiming(wmhu@nlpr.ia.ac.cn)
Abstract

Tracking visual objects from a single initial exemplar in the testing phase has been broadly cast as a one-/few-shot problem, i.e., one-shot learning for initial adaptation and few-shot learning for online adaptation. The recent few-shot online adaptation methods incorporate the prior knowledge from large amounts of annotated training data via complex meta-learning optimization in the offline phase. This helps the online deep trackers to achieve fast adaptation and reduce overfitting risk in tracking. In this paper, we propose a simple yet effective recursive least-squares estimator-aided online learning approach for few-shot onlineadaptation without requiring offline training. It allows an in-built memory retention mechanism for the model to remember the knowledge about the object seen before, and thus the seen data can be safely removed from training. This also bears certain similarities to the emerging continual learning field in preventing catastrophic forgetting. This mechanism enables us to unveil the power of modern online deep trackers without incurring too much extra computational cost. We evaluate our approach based on two networks in the online learning families for tracking, i.e., multi-layer perceptrons in RT-MDNet and convolutional neural networks in DiMP. The consistent improvements on several challenging tracking benchmarks demonstrate its effectiveness and efficiency.

KeywordVisualization Training Adaptation models Data models Optimization Task analysis Robustness Online learning few-shot online adaptation visual tracking continual learning recursive least-squares estimation
DOI10.1109/TPAMI.2022.3156977
WOS KeywordOBJECT TRACKING ; ROBUST
Indexed BySCI
Language英语
Funding ProjectNational Key R#x0026;D Program of China
Funding OrganizationNational Key R#x0026;D Program of China
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:001174191100027
PublisherIEEE COMPUTER SOC
Sub direction classification目标检测、跟踪与识别
planning direction of the national heavy laboratory实体人工智能系统感认知
Paper associated data
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/57500
Collection多模态人工智能系统全国重点实验室_视频内容安全
Affiliation1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Microsoft Res Asia, Beijing 100080, Peoples R China
3.Univ Hong Kong, Dept Elect & Elect Engn, Hong Kong, Peoples R China
4.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Gao, Jin,Lu, Yan,Qi, Xiaojuan,et al. Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2024,46(3):1881-1897.
APA Gao, Jin.,Lu, Yan.,Qi, Xiaojuan.,Kou, Yutong.,Li, Bing.,...&Hu, Weiming.(2024).Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,46(3),1881-1897.
MLA Gao, Jin,et al."Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 46.3(2024):1881-1897.
Files in This Item: Download All
File Name/Size DocType Version Access License
TPAMI2024.pdf(915KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Gao, Jin]'s Articles
[Lu, Yan]'s Articles
[Qi, Xiaojuan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Gao, Jin]'s Articles
[Lu, Yan]'s Articles
[Qi, Xiaojuan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Gao, Jin]'s Articles
[Lu, Yan]'s Articles
[Qi, Xiaojuan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: TPAMI2024.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.