Matches in SemOpenAlex for { <https://semopenalex.org/work/W2979156252> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2979156252 abstract "Video anomaly detection is a valuable but challenging task, especially in the field of surveillance videos for public safety. Almost all existing methods tackle the problem under the supervised setting and only a few attempts are conducted on the unsupervised learning. To avoid the cost of labeling training videos, this paper proposes to discriminate anomaly by a novel two-stage framework in a fully unsupervised manner. Unlike previous unsupervised approaches using local change detection to discover abnormality, our method enjoys the global information from video context by considering the pair-wise similarity of all video events. In this way, our method formulates video anomaly detection as an extension of unsupervised one-class learning, which has not been explored in the literature of video anomaly detection. Specifically, our method consists of two stages: The first stage of our kernel-based method, named Low-rank based Unsupervised One-class Learning with Ridge Regression (LR-UOCL-RR), reformulates the optimization goal of UOCL with ridge regression to avoid expensive computation, which enables our method to handle massive unlabeled data from videos. In the second stage, the estimated normal video events from the first stage are fed into the one-class support vector machine to refine the profile around normal events and enhance the performance. The experimental results conducted on two challenging video benchmarks indicate that our method is considerably superior, up to 15:7% AUC gain, to the state-of-the-art methods in the unsupervised anomaly detection task and even better than several supervised approaches." @default.
- W2979156252 created "2019-10-10" @default.
- W2979156252 creator A5036028581 @default.
- W2979156252 creator A5048261783 @default.
- W2979156252 creator A5064317694 @default.
- W2979156252 creator A5069681054 @default.
- W2979156252 creator A5089193327 @default.
- W2979156252 date "2019-07-01" @default.
- W2979156252 modified "2023-09-28" @default.
- W2979156252 title "Two-stage Unsupervised Video Anomaly Detection using Low-rank based Unsupervised One-class Learning with Ridge Regression" @default.
- W2979156252 cites W1967456674 @default.
- W2979156252 cites W1991251598 @default.
- W2979156252 cites W2012931101 @default.
- W2979156252 cites W2122361470 @default.
- W2979156252 cites W2122646361 @default.
- W2979156252 cites W2125309548 @default.
- W2979156252 cites W2132870739 @default.
- W2979156252 cites W2138092272 @default.
- W2979156252 cites W2156017603 @default.
- W2979156252 cites W2163612318 @default.
- W2979156252 cites W2163991508 @default.
- W2979156252 cites W2164261375 @default.
- W2979156252 cites W2164489414 @default.
- W2979156252 cites W2341058432 @default.
- W2979156252 cites W2519730330 @default.
- W2979156252 cites W2520489243 @default.
- W2979156252 cites W2524280059 @default.
- W2979156252 cites W2533858083 @default.
- W2979156252 cites W2609175385 @default.
- W2979156252 cites W2766042539 @default.
- W2979156252 cites W2777288981 @default.
- W2979156252 cites W2777342313 @default.
- W2979156252 cites W2962791923 @default.
- W2979156252 cites W2964232409 @default.
- W2979156252 cites W4229504449 @default.
- W2979156252 doi "https://doi.org/10.1109/ijcnn.2019.8852022" @default.
- W2979156252 hasPublicationYear "2019" @default.
- W2979156252 type Work @default.
- W2979156252 sameAs 2979156252 @default.
- W2979156252 citedByCount "11" @default.
- W2979156252 countsByYear W29791562522020 @default.
- W2979156252 countsByYear W29791562522021 @default.
- W2979156252 countsByYear W29791562522022 @default.
- W2979156252 crossrefType "proceedings-article" @default.
- W2979156252 hasAuthorship W2979156252A5036028581 @default.
- W2979156252 hasAuthorship W2979156252A5048261783 @default.
- W2979156252 hasAuthorship W2979156252A5064317694 @default.
- W2979156252 hasAuthorship W2979156252A5069681054 @default.
- W2979156252 hasAuthorship W2979156252A5089193327 @default.
- W2979156252 hasConcept C119857082 @default.
- W2979156252 hasConcept C12267149 @default.
- W2979156252 hasConcept C136389625 @default.
- W2979156252 hasConcept C151730666 @default.
- W2979156252 hasConcept C153180895 @default.
- W2979156252 hasConcept C154945302 @default.
- W2979156252 hasConcept C2779343474 @default.
- W2979156252 hasConcept C41008148 @default.
- W2979156252 hasConcept C50644808 @default.
- W2979156252 hasConcept C739882 @default.
- W2979156252 hasConcept C8038995 @default.
- W2979156252 hasConcept C86803240 @default.
- W2979156252 hasConceptScore W2979156252C119857082 @default.
- W2979156252 hasConceptScore W2979156252C12267149 @default.
- W2979156252 hasConceptScore W2979156252C136389625 @default.
- W2979156252 hasConceptScore W2979156252C151730666 @default.
- W2979156252 hasConceptScore W2979156252C153180895 @default.
- W2979156252 hasConceptScore W2979156252C154945302 @default.
- W2979156252 hasConceptScore W2979156252C2779343474 @default.
- W2979156252 hasConceptScore W2979156252C41008148 @default.
- W2979156252 hasConceptScore W2979156252C50644808 @default.
- W2979156252 hasConceptScore W2979156252C739882 @default.
- W2979156252 hasConceptScore W2979156252C8038995 @default.
- W2979156252 hasConceptScore W2979156252C86803240 @default.
- W2979156252 hasLocation W29791562521 @default.
- W2979156252 hasOpenAccess W2979156252 @default.
- W2979156252 hasPrimaryLocation W29791562521 @default.
- W2979156252 hasRelatedWork W2112813276 @default.
- W2979156252 hasRelatedWork W2806504660 @default.
- W2979156252 hasRelatedWork W2929676662 @default.
- W2979156252 hasRelatedWork W2964471674 @default.
- W2979156252 hasRelatedWork W2970229296 @default.
- W2979156252 hasRelatedWork W3044412168 @default.
- W2979156252 hasRelatedWork W3154709713 @default.
- W2979156252 hasRelatedWork W3210156800 @default.
- W2979156252 hasRelatedWork W4205478082 @default.
- W2979156252 hasRelatedWork W4281615271 @default.
- W2979156252 isParatext "false" @default.
- W2979156252 isRetracted "false" @default.
- W2979156252 magId "2979156252" @default.
- W2979156252 workType "article" @default.