FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2082133630> ?p ?o ?g. }

• W2082133630 abstract "Person re-identification from facial captures remains a challenging problem in video surveillance, in largepart due to variations in capture conditions over time. The facial model of a target individual is typicallydesigned during an enrolment phase, using a limited number of reference samples, and may be adapted as newreference videos become available. However incremental learning of classifiers in changing capture conditionsmay lead to knowledge corruption. This paper presents an active framework for an adaptive multi-classifiersystem for video-to-video face recognition in changing surveillance environments. To estimate a facial modelduring the enrolment of an individual, facial captures extracted from a reference video are employed to trainan individual-specific incremental classifier. To sustain a high level of performance over time, a facial modelis adapted in response to new reference videos according the type of concept change. If the system detectsthat the facial captures of an individual incorporate a gradual pattern of change, the corresponding classifier(s)are adapted through incremental learning. In contrast, to avoid knowledge corruption, if an abrupt patternof change is detected, a new classifier is trained on the new video data, and combined with the individual’spreviously-trained classifiers. For validation, a specific implementation is proposed, with ARTMAP classifiersupdated using an incremental learning strategy based on Particle Swarm Optimization, and the Hellinger DriftDetection Method is used for change detection. Simulation results produced with Faces in Action video dataindicate that the proposed system allows for scalable architectures that maintains a significantly higher level ofaccuracy over time than a reference passive system and an adaptive Transduction Confidence Machine-kNNclassifier, while controlling computational complexity." @default.
• W2082133630 created "2016-06-24" @default.
• W2082133630 creator A5002366419 @default.
• W2082133630 creator A5006937759 @default.
• W2082133630 creator A5026340083 @default.
• W2082133630 creator A5052580047 @default.
• W2082133630 creator A5065359946 @default.
• W2082133630 date "2015-01-01" @default.
• W2082133630 modified "2023-10-03" @default.
• W2082133630 title "Adaptive Classification for Person Re-identification Driven by Change Detection" @default.
• W2082133630 cites W1563249575 @default.
• W2082133630 cites W1909591079 @default.
• W2082133630 cites W2019378149 @default.
• W2082133630 cites W2020779941 @default.
• W2082133630 cites W2103753221 @default.
• W2082133630 cites W2105087447 @default.
• W2082133630 cites W2109364787 @default.
• W2082133630 cites W2119762490 @default.
• W2082133630 cites W2122558050 @default.
• W2082133630 cites W2123003172 @default.
• W2082133630 cites W2128835939 @default.
• W2082133630 cites W2130275572 @default.
• W2082133630 cites W2139327121 @default.
• W2082133630 cites W2150416479 @default.
• W2082133630 cites W2151587330 @default.
• W2082133630 cites W2152052718 @default.
• W2082133630 cites W2157103390 @default.
• W2082133630 cites W2163808566 @default.
• W2082133630 cites W2165313956 @default.
• W2082133630 cites W2166280719 @default.
• W2082133630 cites W2318628205 @default.
• W2082133630 cites W3097096317 @default.
• W2082133630 cites W96376781 @default.
• W2082133630 doi "https://doi.org/10.5220/0005184700450055" @default.
• W2082133630 hasPublicationYear "2015" @default.
• W2082133630 type Work @default.
• W2082133630 sameAs 2082133630 @default.
• W2082133630 citedByCount "1" @default.
• W2082133630 countsByYear W20821336302023 @default.
• W2082133630 crossrefType "proceedings-article" @default.
• W2082133630 hasAuthorship W2082133630A5002366419 @default.
• W2082133630 hasAuthorship W2082133630A5006937759 @default.
• W2082133630 hasAuthorship W2082133630A5026340083 @default.
• W2082133630 hasAuthorship W2082133630A5052580047 @default.
• W2082133630 hasAuthorship W2082133630A5065359946 @default.
• W2082133630 hasConcept C116834253 @default.
• W2082133630 hasConcept C119857082 @default.
• W2082133630 hasConcept C153180895 @default.
• W2082133630 hasConcept C154945302 @default.
• W2082133630 hasConcept C203595873 @default.
• W2082133630 hasConcept C41008148 @default.
• W2082133630 hasConcept C59822182 @default.
• W2082133630 hasConcept C86803240 @default.
• W2082133630 hasConceptScore W2082133630C116834253 @default.
• W2082133630 hasConceptScore W2082133630C119857082 @default.
• W2082133630 hasConceptScore W2082133630C153180895 @default.
• W2082133630 hasConceptScore W2082133630C154945302 @default.
• W2082133630 hasConceptScore W2082133630C203595873 @default.
• W2082133630 hasConceptScore W2082133630C41008148 @default.
• W2082133630 hasConceptScore W2082133630C59822182 @default.
• W2082133630 hasConceptScore W2082133630C86803240 @default.
• W2082133630 hasLocation W20821336301 @default.
• W2082133630 hasOpenAccess W2082133630 @default.
• W2082133630 hasPrimaryLocation W20821336301 @default.
• W2082133630 hasRelatedWork W2961085424 @default.
• W2082133630 hasRelatedWork W3046775127 @default.
• W2082133630 hasRelatedWork W3170094116 @default.
• W2082133630 hasRelatedWork W3199009818 @default.
• W2082133630 hasRelatedWork W4285260836 @default.
• W2082133630 hasRelatedWork W4285323898 @default.
• W2082133630 hasRelatedWork W4286629047 @default.
• W2082133630 hasRelatedWork W4306321456 @default.
• W2082133630 hasRelatedWork W4306674287 @default.
• W2082133630 hasRelatedWork W4224009465 @default.
• W2082133630 isParatext "false" @default.
• W2082133630 isRetracted "false" @default.
• W2082133630 magId "2082133630" @default.
• W2082133630 workType "article" @default.