Journal article icon

Journal article

Struck: Structured Output Tracking with Kernels.

Abstract:

Adaptive tracking-by-detection methods are widely used in computer vision for tracking arbitrary objects. Current approaches treat the tracking problem as a classification task and use online learning techniques to update the object model. However, for these updates to happen one needs to convert the estimated object position into a set of labelled training examples, and it is not clear how best to perform this intermediate step. Furthermore, the objective for the classifier (label prediction...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Accepted Manuscript

Actions


Access Document


Files:
Publisher copy:
10.1109/TPAMI.2015.2509974

Authors


More by this author
Department:
Oxford, MPLS, Engineering Science
Saffari, A More by this author
Expand authors...
More from this funder
Funding agency for:
Torr, Philip H. S.
More from this funder
Grant:
ERC-2012-AdG 321162-HELIOS
Publisher:
Institute of Electrical and Electronics Engineers Publisher's website
Journal:
IEEE transactions on pattern analysis and machine intelligence Journal website
Volume:
38
Issue:
10
Pages:
2096-2109
Publication date:
2015-12-17
DOI:
EISSN:
1939-3539
ISSN:
0162-8828
URN:
uuid:a77f001b-8a9c-42fa-af67-267ee52bb3ab
Source identifiers:
588225
Local pid:
pubs:588225

Terms of use


Metrics



If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP