Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/85997
Full metadata record
DC FieldValueLanguage
dc.contributor.authorHu, Boen
dc.contributor.authorYuan, Junsongen
dc.contributor.authorWu, Yuweien
dc.date.accessioned2017-10-17T05:22:12Zen
dc.date.accessioned2019-12-06T16:14:04Z-
dc.date.available2017-10-17T05:22:12Zen
dc.date.available2019-12-06T16:14:04Z-
dc.date.issued2016en
dc.identifier.citationHu, B., Yuan, J., & Wu, Y. (2016). Discriminative Action States Discovery for Online Action Recognition. IEEE Signal Processing Letters, 23(10), 1374-1378.en
dc.identifier.issn1070-9908en
dc.identifier.urihttps://hdl.handle.net/10356/85997-
dc.description.abstractIn this paper, we provide an approach for online human action recognition, where the videos are represented by frame-level descriptors. To address the large intraclass variations of frame-level descriptors, we propose an action states discovery method to discover the different distributions of frame-level descriptors while training a classifier. A positive sample set is treated as multiple clusters called action states. The action states model can be effectively learned by clustering the positive samples and optimizing the decision boundary of each state simultaneously. Experimental results show that our method not only outperforms the state-of-the-art methods, but also can predict the video by an on-going process with a real-time speed.en
dc.description.sponsorshipMOE (Min. of Education, S’pore)en
dc.language.isoenen
dc.relation.ispartofseriesIEEE Signal Processing Lettersen
dc.rights© 2016 IEEE.en
dc.subjectAction Statesen
dc.subjectAction Predictionen
dc.titleDiscriminative Action States Discovery for Online Action Recognitionen
dc.typeJournal Articleen
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen
dc.identifier.doi10.1109/LSP.2016.2598878en
item.fulltextNo Fulltext-
item.grantfulltextnone-
Appears in Collections:EEE Journal Articles

SCOPUSTM   
Citations

6
Updated on Sep 2, 2020

PublonsTM
Citations

7
Updated on Feb 23, 2021

Page view(s)

241
Updated on Feb 28, 2021

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.