End-to-End Temporal Action Detection using Bag of Discriminant Snippets (BoDS)

e-Archivo Repository

Show simple item record

dc.contributor.author Murtaza, Fiza
dc.contributor.author Yousaf, Muhammad Haroon
dc.contributor.author Velastin Carroza, Sergio Alejandro
dc.contributor.author Qian, Yu
dc.date.accessioned 2018-12-14T12:23:41Z
dc.date.available 2018-12-14T12:23:41Z
dc.date.issued 2018
dc.identifier.bibliographicCitation Murtaza, F., Yousaf, M.H., Velastin, S. A., Qian, Y. (En prensa). End-to-End Temporal Action Detection using Bag of Discriminant Snippets (BoDS). IEEE Signal Processing Letters.
dc.identifier.issn 1070-9908
dc.identifier.uri http://hdl.handle.net/10016/27820
dc.description.abstract Detecting human actions in long untrimmed videosis a challenging problem. Existing temporal action detectionmethods have difficulties in finding the precise starting andending time of the actions in untrimmed videos. In this letter, wepropose a temporal action detection framework based on a Bagof Discriminant Snippets (BoDS) that can detect multiple actionsin an end-to-end manner. BoDS is based on the observationthat multiple actions and the background classes have similarsnippets, which cause incorrect classification of action regionsand imprecise boundaries. We solve this issue by finding the keysnippetsfrom the training data of each class and compute theirdiscriminative power which is used in BoDS encoding. Duringtesting of an untrimmed video, we find the BoDS representationfor multiple candidate proposals and find their class label basedon a majority voting scheme. We test BoDS on the Thumos14 andActivityNet datasets and obtain state-of-the-art results. For thesports subset of ActivityNet dataset, we obtain a mean AveragePrecision (mAP) value of 29% at 0.7 temporal intersection overunion (tIoU) threshold. For the Thumos14 dataset, we obtain asignificant gain in terms of mAP i.e., improving from 20.8% to31.6% at tIoU=0.7.
dc.description.sponsorship This work was supported by the ASR&TD, University of Engineering and Technology (UET) Taxila, Pakistan. The work of S. A. Velastin was supported by the Universidad Carlos III de Madrid, the European Unions Seventh Framework Program for research, technological development, and demonstration under Grant 600371, el Ministerio de Economia y Competitividad (COFUND2013-51509), and Banco Santander.
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher IEEE
dc.rights ©2018 IEEE
dc.subject.other Temporal Action Detection
dc.subject.other 3D-Convolutional network (C3D)
dc.subject.other Untrimmed videos
dc.subject.other Thumos14
dc.subject.other ActivityNet
dc.subject.other Temporal action proposals
dc.title End-to-End Temporal Action Detection using Bag of Discriminant Snippets (BoDS)
dc.type article
dc.subject.eciencia Informática
dc.relation.projectID Gobierno de España. COFUND2013-51509
dc.relation.projectID info:eu-repo/grantAgreement/EC/FP7/600371
dc.type.version acceptedVersion
dc.identifier.publicationtitle IEEE Signal Processing Letters
dc.identifier.uxxi AR/0000022209
dc.contributor.funder Banco Santander
dc.contributor.funder European Commission
dc.contributor.funder Ministerio de Economía y Competitividad (España)
 Find Full text

Files in this item

*Click on file's image for preview. (Embargoed files's preview is not supported)

This item appears in the following Collection(s)

Show simple item record