Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICCV.2013.88
DC FieldValue
dc.titleRobust object tracking with online multi-lifespan dictionary learning
dc.contributor.authorXing, J.
dc.contributor.authorGao, J.
dc.contributor.authorLi, B.
dc.contributor.authorHu, W.
dc.contributor.authorYan, S.
dc.date.accessioned2014-10-07T04:49:20Z
dc.date.available2014-10-07T04:49:20Z
dc.date.issued2013
dc.identifier.citationXing, J., Gao, J., Li, B., Hu, W., Yan, S. (2013). Robust object tracking with online multi-lifespan dictionary learning. Proceedings of the IEEE International Conference on Computer Vision : 665-672. ScholarBank@NUS Repository. https://doi.org/10.1109/ICCV.2013.88
dc.identifier.isbn9781479928392
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/84147
dc.description.abstractRecently, sparse representation has been introduced for robust object tracking. By representing the object sparsely, i.e., using only a few templates via L1-norm minimization, these so-called L1-trackers exhibit promising tracking results. In this work, we address the object template building and updating problem in these L1-tracking approaches, which has not been fully studied. We propose to perform template updating, in a new perspective, as an online incremental dictionary learning problem, which is efficiently solved through an online optimization procedure. To guarantee the robustness and adaptability of the tracking algorithm, we also propose to build a multi-lifespan dictionary model. By building target dictionaries of different life spans, effective object observations can be obtained to deal with the well-known drifting problem in tracking and thus improve the tracking accuracy. We derive effective observation models both generatively and discriminatively based on the online multi-lifespan dictionary learning model and deploy them to the Bayesian sequential estimation framework to perform tracking. The proposed approach has been extensively evaluated on ten challenging video sequences. Experimental results demonstrate the effectiveness of the online learned templates, as well as the state-of-the-art tracking performance of the proposed approach. © 2013 IEEE.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1109/ICCV.2013.88
dc.sourceScopus
dc.subjectdictionary learning
dc.subjectObject tracking
dc.subjectsparse representation
dc.subjecttemplate update
dc.typeConference Paper
dc.contributor.departmentELECTRICAL & COMPUTER ENGINEERING
dc.description.doi10.1109/ICCV.2013.88
dc.description.sourcetitleProceedings of the IEEE International Conference on Computer Vision
dc.description.page665-672
dc.description.codenPICVE
dc.identifier.isiut000351830500083
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

60
checked on Sep 23, 2020

WEB OF SCIENCETM
Citations

46
checked on Sep 23, 2020

Page view(s)

63
checked on Sep 27, 2020

Google ScholarTM

Check

Altmetric


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