Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385399076> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4385399076 endingPage "172" @default.
- W4385399076 startingPage "157" @default.
- W4385399076 abstract "Anomaly detection in real time surveillance videos is a challenging task due to the scenario dependency, duration and multiple occurrences of anomalous events. Typically, weakly supervised video anomaly detection that involves video-level labels is expressed as a multiple instance learning (MIL) problem. The objective is to detect the video clips containing abnormal events, while representing each video as a collection of such clips. Existing MIL classifiers assume that the training videos only have anomalous events of short duration. However, this may not hold true for all real-life anomalies and it cannot be dismissed that there may be multiple occurrences of anomalies in the training videos. In order to detect such anomalies, a novel multi-stream deep neural network (MSDeepNet) is proposed by employing spatio-temporal deep feature extractors along with weakly supervised temporal attention module (WS-TAM). The features extracted from the individual streams are fed to train the modified MIL classifier by employing a novel temporal loss function. Finally, a fuzzy fusion method is used to aggregate the anomaly detection scores. To validate the performance of the proposed method, comprehensive results have been performed on the large-scale benchmark UCF Crime dataset. The suggested multi-stream architecture outperforms state-of-the-art video anomaly detection methods with the frame-level AUC score of 84.72% for detecting anomalous events and lowest false alarm rate of 0.9% for detecting normal events." @default.
- W4385399076 created "2023-07-31" @default.
- W4385399076 creator A5007030882 @default.
- W4385399076 creator A5026459703 @default.
- W4385399076 creator A5035076881 @default.
- W4385399076 date "2023-01-01" @default.
- W4385399076 modified "2023-09-27" @default.
- W4385399076 title "MSDeepNet: A Novel Multi-stream Deep Neural Network for Real-World Anomaly Detection in Surveillance Videos" @default.
- W4385399076 cites W2312198368 @default.
- W4385399076 cites W2341058432 @default.
- W4385399076 cites W2921491036 @default.
- W4385399076 cites W2962791923 @default.
- W4385399076 cites W2963524571 @default.
- W4385399076 cites W2963795951 @default.
- W4385399076 cites W2970271202 @default.
- W4385399076 cites W2981741013 @default.
- W4385399076 cites W3035021504 @default.
- W4385399076 cites W3107664750 @default.
- W4385399076 cites W3135550350 @default.
- W4385399076 cites W3168600998 @default.
- W4385399076 cites W3190308053 @default.
- W4385399076 cites W4205821843 @default.
- W4385399076 cites W4206235228 @default.
- W4385399076 cites W4221027477 @default.
- W4385399076 cites W4225624178 @default.
- W4385399076 cites W4226039588 @default.
- W4385399076 cites W4281478450 @default.
- W4385399076 cites W4283811196 @default.
- W4385399076 cites W4312554543 @default.
- W4385399076 cites W4312790276 @default.
- W4385399076 cites W4316259280 @default.
- W4385399076 cites W4320913379 @default.
- W4385399076 doi "https://doi.org/10.1007/978-3-031-39059-3_11" @default.
- W4385399076 hasPublicationYear "2023" @default.
- W4385399076 type Work @default.
- W4385399076 citedByCount "0" @default.
- W4385399076 crossrefType "book-chapter" @default.
- W4385399076 hasAuthorship W4385399076A5007030882 @default.
- W4385399076 hasAuthorship W4385399076A5026459703 @default.
- W4385399076 hasAuthorship W4385399076A5035076881 @default.
- W4385399076 hasConcept C121332964 @default.
- W4385399076 hasConcept C12997251 @default.
- W4385399076 hasConcept C13280743 @default.
- W4385399076 hasConcept C153180895 @default.
- W4385399076 hasConcept C154945302 @default.
- W4385399076 hasConcept C185798385 @default.
- W4385399076 hasConcept C205649164 @default.
- W4385399076 hasConcept C26873012 @default.
- W4385399076 hasConcept C41008148 @default.
- W4385399076 hasConcept C50644808 @default.
- W4385399076 hasConcept C739882 @default.
- W4385399076 hasConcept C95623464 @default.
- W4385399076 hasConceptScore W4385399076C121332964 @default.
- W4385399076 hasConceptScore W4385399076C12997251 @default.
- W4385399076 hasConceptScore W4385399076C13280743 @default.
- W4385399076 hasConceptScore W4385399076C153180895 @default.
- W4385399076 hasConceptScore W4385399076C154945302 @default.
- W4385399076 hasConceptScore W4385399076C185798385 @default.
- W4385399076 hasConceptScore W4385399076C205649164 @default.
- W4385399076 hasConceptScore W4385399076C26873012 @default.
- W4385399076 hasConceptScore W4385399076C41008148 @default.
- W4385399076 hasConceptScore W4385399076C50644808 @default.
- W4385399076 hasConceptScore W4385399076C739882 @default.
- W4385399076 hasConceptScore W4385399076C95623464 @default.
- W4385399076 hasLocation W43853990761 @default.
- W4385399076 hasOpenAccess W4385399076 @default.
- W4385399076 hasPrimaryLocation W43853990761 @default.
- W4385399076 hasRelatedWork W2076520961 @default.
- W4385399076 hasRelatedWork W2148583977 @default.
- W4385399076 hasRelatedWork W2563096758 @default.
- W4385399076 hasRelatedWork W2950653125 @default.
- W4385399076 hasRelatedWork W3096700136 @default.
- W4385399076 hasRelatedWork W3105816646 @default.
- W4385399076 hasRelatedWork W4205474285 @default.
- W4385399076 hasRelatedWork W4280535515 @default.
- W4385399076 hasRelatedWork W4283314094 @default.
- W4385399076 hasRelatedWork W4378464710 @default.
- W4385399076 isParatext "false" @default.
- W4385399076 isRetracted "false" @default.
- W4385399076 workType "book-chapter" @default.