Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/141973
Full metadata record
DC FieldValueLanguage
dc.contributor.authorWeng, Junwuen_US
dc.contributor.authorJiang, Xudongen_US
dc.contributor.authorZheng, Wei-Longen_US
dc.contributor.authorYuan, Junsongen_US
dc.date.accessioned2020-06-12T06:50:39Z-
dc.date.available2020-06-12T06:50:39Z-
dc.date.issued2020-
dc.identifier.citationWeng, J., Jiang, X., Zheng, W.-L., & Yuan, J. (2019). Early action recognition with category exclusion using policy-based reinforcement learning. IEEE Transactions on Circuits and Systems for Video Technology, in-press. doi:10.1109/TCSVT.2020.2976789en_US
dc.identifier.issn1051-8215en_US
dc.identifier.urihttps://hdl.handle.net/10356/141973-
dc.description.abstractThe goal of early action recognition is to predict action label when the sequence is partially observed. The existing methods treat the early action recognition task as sequential classification problems on different observation ratios of an action sequence. Since these models are trained by differentiating positive category from all negative classes, the diverse information of different negative categories is ignored, which we believe can be collected to help improve the recognition performance. In this paper, we step towards to a new direction by introducing category exclusion to early action recognition. We model the exclusion as a mask operation on the classification probability output of a pre-trained early action recognition classifier. Specifically, we use policy-based reinforcement learning to train an agent. The agent generates a series of binary masks to exclude interfering negative categories during action execution and hence help improve the recognition accuracy. The proposed method is evaluated on three benchmark recognition datasets, NTU-RGBD, First-Person Hand Action, as well as UCF-101. The proposed method enhances the recognition accuracy consistently over all different observation ratios on the three datasets, where the accuracy improvements on the early stages are especially significant.en_US
dc.description.sponsorshipNRF (Natl Research Foundation, S’pore)en_US
dc.language.isoenen_US
dc.relation.ispartofIEEE Transactions on Circuits and Systems for Video Technologyen_US
dc.rights© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/TCSVT.2020.2976789.en_US
dc.subjectEngineering::Electrical and electronic engineeringen_US
dc.titleEarly action recognition with category exclusion using policy-based reinforcement learningen_US
dc.typeJournal Articleen
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen_US
dc.contributor.researchInstitute for Media Innovation (IMI)en_US
dc.identifier.doi10.1109/TCSVT.2020.2976789-
dc.description.versionAccepted versionen_US
dc.subject.keywordsCategory Exclusionen_US
dc.subject.keywordsEarly Action Recognitionen_US
item.fulltextWith Fulltext-
item.grantfulltextopen-
Appears in Collections:IMI Journal Articles

SCOPUSTM   
Citations 20

23
Updated on Mar 27, 2024

Web of ScienceTM
Citations 20

18
Updated on Oct 25, 2023

Page view(s)

374
Updated on Mar 27, 2024

Download(s) 20

211
Updated on Mar 27, 2024

Google ScholarTM

Check

Altmetric


Plumx

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