File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.neucom.2018.05.108
- Scopus: eid_2-s2.0-85051378725
- WOS: WOS:000445934400004
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Discriminative tracking via supervised tensor learning
Title | Discriminative tracking via supervised tensor learning |
---|---|
Authors | |
Keywords | Visual tracking Truncated structured tucker machine Tensor representation Tensor block coordinate descent |
Issue Date | 2018 |
Citation | Neurocomputing, 2018, v. 315, p. 33-47 How to Cite? |
Abstract | © 2018 Elsevier B.V. Discriminative tracking algorithms have witnessed continued progress for distinguishing the target from background in unconstrained environments. The learning and detection task in existing visual tracking methods often convert a multidimensional data array into a vector-based observation. By altering the 2-D spatial structure of the image, transformation variants and global noises influence the discriminative ability of target representation, often result in degradation of performance. Different from vector representations, this paper presents a tensor-based large margin discriminative framework for visual tracking that utilizes the supervised tensor learning. In our method, an online structured support tensor classifier is designed which produces the multi-linear decision function, incorporating the nonlinearity of tensor-based feature over the target. In order to provide better spatial cues of target representation against noises and facilitate online tracking, we further introduce truncated tucker decomposition in structured multi-linear learning. The proposed algorithm poses an effective parameter tensor reconstruction in the classifier updating procedure and has a robust discriminative ability against several video background variants. Furthermore, a tensor block coordinate descent optimization is presented to achieve a closed form solution specific to the proposed truncated structured Tucker machine (TSTM). Experiment results on a recent comprehensive tracking benchmark demonstrate a promising performance of the proposed method subjectively and objectively compared with several state-of-the-art algorithms. |
Persistent Identifier | http://hdl.handle.net/10722/276600 |
ISSN | 2023 Impact Factor: 5.5 2023 SCImago Journal Rankings: 1.815 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Xu, Guoxia | - |
dc.contributor.author | Khan, Sheheryar | - |
dc.contributor.author | Zhu, Hu | - |
dc.contributor.author | Han, Lixin | - |
dc.contributor.author | Ng, Michael K. | - |
dc.contributor.author | Yan, Hong | - |
dc.date.accessioned | 2019-09-18T08:34:06Z | - |
dc.date.available | 2019-09-18T08:34:06Z | - |
dc.date.issued | 2018 | - |
dc.identifier.citation | Neurocomputing, 2018, v. 315, p. 33-47 | - |
dc.identifier.issn | 0925-2312 | - |
dc.identifier.uri | http://hdl.handle.net/10722/276600 | - |
dc.description.abstract | © 2018 Elsevier B.V. Discriminative tracking algorithms have witnessed continued progress for distinguishing the target from background in unconstrained environments. The learning and detection task in existing visual tracking methods often convert a multidimensional data array into a vector-based observation. By altering the 2-D spatial structure of the image, transformation variants and global noises influence the discriminative ability of target representation, often result in degradation of performance. Different from vector representations, this paper presents a tensor-based large margin discriminative framework for visual tracking that utilizes the supervised tensor learning. In our method, an online structured support tensor classifier is designed which produces the multi-linear decision function, incorporating the nonlinearity of tensor-based feature over the target. In order to provide better spatial cues of target representation against noises and facilitate online tracking, we further introduce truncated tucker decomposition in structured multi-linear learning. The proposed algorithm poses an effective parameter tensor reconstruction in the classifier updating procedure and has a robust discriminative ability against several video background variants. Furthermore, a tensor block coordinate descent optimization is presented to achieve a closed form solution specific to the proposed truncated structured Tucker machine (TSTM). Experiment results on a recent comprehensive tracking benchmark demonstrate a promising performance of the proposed method subjectively and objectively compared with several state-of-the-art algorithms. | - |
dc.language | eng | - |
dc.relation.ispartof | Neurocomputing | - |
dc.subject | Visual tracking | - |
dc.subject | Truncated structured tucker machine | - |
dc.subject | Tensor representation | - |
dc.subject | Tensor block coordinate descent | - |
dc.title | Discriminative tracking via supervised tensor learning | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1016/j.neucom.2018.05.108 | - |
dc.identifier.scopus | eid_2-s2.0-85051378725 | - |
dc.identifier.volume | 315 | - |
dc.identifier.spage | 33 | - |
dc.identifier.epage | 47 | - |
dc.identifier.eissn | 1872-8286 | - |
dc.identifier.isi | WOS:000445934400004 | - |
dc.identifier.issnl | 0925-2312 | - |