Full metadata record

DC Field Value Language
dc.contributor.authorThakare, Kamalakar Vijay-
dc.contributor.authorDogra, Debi Prosad-
dc.contributor.authorChoi, Heeseung-
dc.contributor.authorKim, Haksub-
dc.contributor.authorKim, Ig-Jae-
dc.date.accessioned2024-01-19T09:03:25Z-
dc.date.available2024-01-19T09:03:25Z-
dc.date.created2023-05-25-
dc.date.issued2023-08-
dc.identifier.issn0031-3203-
dc.identifier.urihttps://pubs.kist.re.kr/handle/201004/113469-
dc.description.abstractExisting video anomaly detection methods and datasets suffer from restricted anomaly categories contain-ing single-source (CCTV) videos recorded in controlled environment, inadequate annotations, and lack of adequate supervision. To mitigate these problems, we introduce a new dataset (RareAnom) containing 17 rare types of real-world anomalies (2200 videos) recorded using multiple sources (e.g., CCTV, hand-held cameras, dash-cams, and mobile phones) with rich temporal annotations. A new fully unsupervised anomaly detection and classification method has been proposed. It has three stages: training of a 3D Con-volution Autoencoder using pseudo-labelled video segments, anomaly detection using latent features, and classification. Unlike the existing datasets, we have benchmarked RareAnom using three levels of super-vision: fully, weakly, and unsupervised. It has been compared with UCF-Crime and XD-Violence datasets. The proposed anomaly detection and classification method beats the latest unsupervised methods by 4.49%, 8.66%, and 6.77% on RareAnom, UCF-Crime, and XD-violence datasets, respectively.(c) 2023 Elsevier Ltd. All rights reserved.-
dc.languageEnglish-
dc.publisherPergamon Press-
dc.titleRareAnom: A Benchmark Video Dataset for Rare Type Anomalies-
dc.typeArticle-
dc.identifier.doi10.1016/j.patcog.2023.109567-
dc.description.journalClass1-
dc.identifier.bibliographicCitationPattern Recognition, v.140-
dc.citation.titlePattern Recognition-
dc.citation.volume140-
dc.description.isOpenAccessN-
dc.description.journalRegisteredClassscie-
dc.description.journalRegisteredClassscopus-
dc.identifier.wosid000978788000001-
dc.identifier.scopusid2-s2.0-85151693326-
dc.relation.journalWebOfScienceCategoryComputer Science, Artificial Intelligence-
dc.relation.journalWebOfScienceCategoryEngineering, Electrical & Electronic-
dc.relation.journalResearchAreaComputer Science-
dc.relation.journalResearchAreaEngineering-
dc.type.docTypeArticle-
dc.subject.keywordPlusABNORMAL EVENT DETECTION-
dc.subject.keywordPlusLOCALIZATION-
dc.subject.keywordAuthorVideo anomaly detection-
dc.subject.keywordAuthorUnsupervised learning-
dc.subject.keywordAuthorTemporal encoding-
dc.subject.keywordAuthorRare anomalies-
dc.subject.keywordAuthorAnomaly classification-
Appears in Collections:
KIST Article > 2023
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE