A novel online action detection framework from untrimmed video streams
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yoon, Da-Hye | - |
dc.contributor.author | Cho, Nam-Gyu | - |
dc.contributor.author | Lee, Seong-Whan | - |
dc.date.accessioned | 2021-08-30T13:50:57Z | - |
dc.date.available | 2021-08-30T13:50:57Z | - |
dc.date.created | 2021-06-18 | - |
dc.date.issued | 2020-10 | - |
dc.identifier.issn | 0031-3203 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/53037 | - |
dc.description.abstract | Online temporal action localization from an untrimmed video stream is a challenging problem in computer vision. It is challenging because of i) in an untrimmed video stream, more than one action instance may appear, including background scenes, and ii) in online settings, only past and current information is available. Therefore, temporal priors, such as the average action duration of training data, which have been exploited by previous action detection methods, are not suitable for this task because of the high intra-class variation in human actions. We propose a novel online action detection framework that considers actions as a set of temporally ordered subclasses and leverages a future frame generation network to cope with the limited information issue associated with the problem outlined above. Additionally, we augment our data by varying the lengths of videos to allow the proposed method to learn about the high intra-class variation in human actions. We evaluate our method using two benchmark datasets, THUMOS'14 and ActivityNet, for an online temporal action localization scenario and demonstrate that the performance is comparable to state-of-the-art methods that have been proposed for offline settings. (C) 2020 Elsevier Ltd. All rights reserved. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | ELSEVIER SCI LTD | - |
dc.subject | HUMAN ACTION RECOGNITION | - |
dc.title | A novel online action detection framework from untrimmed video streams | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Lee, Seong-Whan | - |
dc.identifier.doi | 10.1016/j.patcog.2020.107396 | - |
dc.identifier.scopusid | 2-s2.0-85084532250 | - |
dc.identifier.wosid | 000541777200006 | - |
dc.identifier.bibliographicCitation | PATTERN RECOGNITION, v.106 | - |
dc.relation.isPartOf | PATTERN RECOGNITION | - |
dc.citation.title | PATTERN RECOGNITION | - |
dc.citation.volume | 106 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.subject.keywordPlus | HUMAN ACTION RECOGNITION | - |
dc.subject.keywordAuthor | Online action detection | - |
dc.subject.keywordAuthor | Untrimmed video stream | - |
dc.subject.keywordAuthor | Future frame generation | - |
dc.subject.keywordAuthor | 3D convolutional neural network | - |
dc.subject.keywordAuthor | Long short-term memory | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.