Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225526006> ?p ?o ?g. }
- W4225526006 endingPage "36199" @default.
- W4225526006 startingPage "36188" @default.
- W4225526006 abstract "Anomaly detection is an integral part of a number of surveillance applications. However, most of the existing anomaly detection models are statically trained on pre-recorded data from a single source, thus making multiple assumptions about the surrounding environment. As a result, their usefulness is limited to controlled scenarios. In this paper, we fuse information from live streams of audio and video data to detect anomalies in the captured environment. We train a deep learning-based teacher-student network using video, image, and audio information. The pre-trained visual network in the teacher model distills its information to the image and audio networks in the student model. Features from image and audio networks are combined and compressed using principal component analysis. Thus, the teacher-student network produces an image-audio-based light-weight joint representation of the data. The data dynamics are learned in a multivariate adaptive Gaussian mixture model. Empirical results from two audio-visual datasets demonstrate the effectiveness of joint representation over single modalities in the adaptive anomaly detection framework. The proposed framework outperforms the state-of-the-art methods by an average of 15.00 % and 14.52 % in AUC values for dataset 1 and dataset 2, respectively." @default.
- W4225526006 created "2022-05-05" @default.
- W4225526006 creator A5063160375 @default.
- W4225526006 creator A5076590373 @default.
- W4225526006 date "2022-01-01" @default.
- W4225526006 modified "2023-09-30" @default.
- W4225526006 title "An Adaptive Framework for Anomaly Detection in Time-Series Audio-Visual Data" @default.
- W4225526006 cites W1671907758 @default.
- W4225526006 cites W1996118086 @default.
- W4225526006 cites W2009017316 @default.
- W4225526006 cites W2014208121 @default.
- W4225526006 cites W2035890032 @default.
- W4225526006 cites W2053101950 @default.
- W4225526006 cites W2053154970 @default.
- W4225526006 cites W2057746219 @default.
- W4225526006 cites W2083709814 @default.
- W4225526006 cites W2102625004 @default.
- W4225526006 cites W2105594594 @default.
- W4225526006 cites W2122646361 @default.
- W4225526006 cites W2125027820 @default.
- W4225526006 cites W2140647972 @default.
- W4225526006 cites W2155653793 @default.
- W4225526006 cites W2158698691 @default.
- W4225526006 cites W2164777277 @default.
- W4225526006 cites W2409205391 @default.
- W4225526006 cites W2519730330 @default.
- W4225526006 cites W2620661538 @default.
- W4225526006 cites W2758333383 @default.
- W4225526006 cites W2766042539 @default.
- W4225526006 cites W2767290858 @default.
- W4225526006 cites W2799062425 @default.
- W4225526006 cites W2802895140 @default.
- W4225526006 cites W2890135756 @default.
- W4225526006 cites W2896229655 @default.
- W4225526006 cites W2897879219 @default.
- W4225526006 cites W2898143381 @default.
- W4225526006 cites W2963166639 @default.
- W4225526006 cites W2963524571 @default.
- W4225526006 cites W2963610939 @default.
- W4225526006 cites W2963899855 @default.
- W4225526006 cites W2964154847 @default.
- W4225526006 cites W2976852454 @default.
- W4225526006 cites W2981650061 @default.
- W4225526006 cites W3004543888 @default.
- W4225526006 cites W3034658206 @default.
- W4225526006 cites W3035667109 @default.
- W4225526006 cites W3093556084 @default.
- W4225526006 cites W3095028588 @default.
- W4225526006 cites W3107664750 @default.
- W4225526006 cites W3112836416 @default.
- W4225526006 cites W3132761010 @default.
- W4225526006 cites W3139422143 @default.
- W4225526006 cites W3154807520 @default.
- W4225526006 cites W3170135154 @default.
- W4225526006 cites W3192880336 @default.
- W4225526006 cites W4241492760 @default.
- W4225526006 cites W4247229946 @default.
- W4225526006 cites W4255466416 @default.
- W4225526006 doi "https://doi.org/10.1109/access.2022.3164439" @default.
- W4225526006 hasPublicationYear "2022" @default.
- W4225526006 type Work @default.
- W4225526006 citedByCount "3" @default.
- W4225526006 countsByYear W42255260062022 @default.
- W4225526006 countsByYear W42255260062023 @default.
- W4225526006 crossrefType "journal-article" @default.
- W4225526006 hasAuthorship W4225526006A5063160375 @default.
- W4225526006 hasAuthorship W4225526006A5076590373 @default.
- W4225526006 hasBestOaLocation W42255260061 @default.
- W4225526006 hasConcept C121332964 @default.
- W4225526006 hasConcept C124101348 @default.
- W4225526006 hasConcept C12997251 @default.
- W4225526006 hasConcept C153180895 @default.
- W4225526006 hasConcept C154945302 @default.
- W4225526006 hasConcept C17744445 @default.
- W4225526006 hasConcept C199539241 @default.
- W4225526006 hasConcept C26873012 @default.
- W4225526006 hasConcept C2776359362 @default.
- W4225526006 hasConcept C31972630 @default.
- W4225526006 hasConcept C36464697 @default.
- W4225526006 hasConcept C41008148 @default.
- W4225526006 hasConcept C739882 @default.
- W4225526006 hasConcept C94625758 @default.
- W4225526006 hasConceptScore W4225526006C121332964 @default.
- W4225526006 hasConceptScore W4225526006C124101348 @default.
- W4225526006 hasConceptScore W4225526006C12997251 @default.
- W4225526006 hasConceptScore W4225526006C153180895 @default.
- W4225526006 hasConceptScore W4225526006C154945302 @default.
- W4225526006 hasConceptScore W4225526006C17744445 @default.
- W4225526006 hasConceptScore W4225526006C199539241 @default.
- W4225526006 hasConceptScore W4225526006C26873012 @default.
- W4225526006 hasConceptScore W4225526006C2776359362 @default.
- W4225526006 hasConceptScore W4225526006C31972630 @default.
- W4225526006 hasConceptScore W4225526006C36464697 @default.
- W4225526006 hasConceptScore W4225526006C41008148 @default.
- W4225526006 hasConceptScore W4225526006C739882 @default.
- W4225526006 hasConceptScore W4225526006C94625758 @default.
- W4225526006 hasLocation W42255260061 @default.
- W4225526006 hasOpenAccess W4225526006 @default.