Prediction of partially observed human activity based on pre-trained deep representation
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Dong-Gyu | - |
dc.contributor.author | Lee, Seong-Whan | - |
dc.date.accessioned | 2021-09-01T22:27:07Z | - |
dc.date.available | 2021-09-01T22:27:07Z | - |
dc.date.created | 2021-06-19 | - |
dc.date.issued | 2019-01 | - |
dc.identifier.issn | 0031-3203 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/68798 | - |
dc.description.abstract | Prediction of complex human activities from a partially observed video is valuable in many practical applications but is a challenging problem. When a video is partially observed, maximizing the representational power of the given video is more important than modeling the temporal dynamics of the activity. In this paper, we propose a novel human activity descriptor for prediction, which can maximize the discriminative power of a system in a compact and efficient way using pre-trained deep networks. Specifically, the proposed descriptor can capture the potentially important pairwise relationships between objects without prior knowledge or preset attributes. The relationship information is automatically reflected during the descriptor construction procedure based on object's participation ratios, local and global motion activations. Pre-trained Convolutional Neural Networks are utilized without additional model training procedure. From a practical point of view, the proposed method is more cost-effective when implementing a smart surveillance system. In the experiments, we evaluate the proposed methods in two cases: (1) prediction accuracy with different observation ratios, and (2) the effect of pre-trained network and layer selection. Experimental results from five public datasets verified the efficacy of the proposed method by outperforming competing methods with stable high-performance regardless of network selection. (C) 2018 Elsevier Ltd. All rights reserved. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | ELSEVIER SCI LTD | - |
dc.subject | RECOGNITION | - |
dc.subject | SPACE | - |
dc.subject | MODEL | - |
dc.title | Prediction of partially observed human activity based on pre-trained deep representation | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Lee, Seong-Whan | - |
dc.identifier.doi | 10.1016/j.patcog.2018.08.006 | - |
dc.identifier.scopusid | 2-s2.0-85052322974 | - |
dc.identifier.wosid | 000447819300017 | - |
dc.identifier.bibliographicCitation | PATTERN RECOGNITION, v.85, pp.198 - 206 | - |
dc.relation.isPartOf | PATTERN RECOGNITION | - |
dc.citation.title | PATTERN RECOGNITION | - |
dc.citation.volume | 85 | - |
dc.citation.startPage | 198 | - |
dc.citation.endPage | 206 | - |
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 | RECOGNITION | - |
dc.subject.keywordPlus | SPACE | - |
dc.subject.keywordPlus | MODEL | - |
dc.subject.keywordAuthor | Pre-trained CNN | - |
dc.subject.keywordAuthor | Human activity prediction | - |
dc.subject.keywordAuthor | Human interaction | - |
dc.subject.keywordAuthor | Sub-volume co-occurrence matrix | - |
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.