FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3198373084> ?p ?o ?g. }

• W3198373084 abstract "Detecting distracted driving behaviours is important to reduce millions of deaths and injuries occurring worldwide. Distracted or anomalous driving behaviours are deviations from the 'normal' driving that need to be identified correctly to alert the driver. However, these driving behaviours do not comprise of one specific type of driving style and their distribution can be different during training and testing phases of a classifier. We formulate this problem as a supervised contrastive learning approach to learn a visual representation to detect normal, and seen and unseen anomalous driving behaviours. We made a change to the standard contrastive loss function to adjust the similarity of negative pairs to aid the optimization. Normally, the (self) supervised contrastive framework contains an encoder followed by a projection head, which is omitted during testing phase as the encoding layers are considered to contain general visual representative information. However, we assert that for supervised contrastive learning task, including projection head will be beneficial. We showed our results on a Driver Anomaly Detection dataset that contains 783 minutes of video recordings of normal and anomalous driving behaviours of 31 drivers from various from top and front cameras (both depth and infrared). We also performed an extra step of fine tuning the labels in this dataset. Out of 9 video modalities combinations, our modified contrastive approach improved the ROC AUC on 7 in comparison to the baseline models (from 3.12% to 8.91% for different modalities); the remaining two models also had manual labelling. We performed statistical tests that showed evidence that our modifications perform better than the baseline contrastive models. Finally, the results showed that the fusion of depth and infrared modalities from top and front view achieved the best AUC ROC of 0.9738 and AUC PR of 0.9772." @default.
• W3198373084 created "2021-09-13" @default.
• W3198373084 creator A5036208820 @default.
• W3198373084 creator A5045267281 @default.
• W3198373084 creator A5048520383 @default.
• W3198373084 creator A5054153276 @default.
• W3198373084 creator A5079918071 @default.
• W3198373084 date "2021-09-09" @default.
• W3198373084 modified "2023-09-27" @default.
• W3198373084 title "Modified Supervised Contrastive Learning for Detecting Anomalous Driving Behaviours." @default.
• W3198373084 cites W1598209419 @default.
• W3198373084 cites W1914645703 @default.
• W3198373084 cites W1965455921 @default.
• W3198373084 cites W1983364832 @default.
• W3198373084 cites W2138621090 @default.
• W3198373084 cites W2161565164 @default.
• W3198373084 cites W2343897680 @default.
• W3198373084 cites W2594788739 @default.
• W3198373084 cites W2737146145 @default.
• W3198373084 cites W2901773810 @default.
• W3198373084 cites W2904013130 @default.
• W3198373084 cites W2963563276 @default.
• W3198373084 cites W2963794138 @default.
• W3198373084 cites W2970106338 @default.
• W3198373084 cites W2996492278 @default.
• W3198373084 cites W3034637297 @default.
• W3198373084 cites W3034978746 @default.
• W3198373084 cites W3092920241 @default.
• W3198373084 cites W3100345210 @default.
• W3198373084 cites W3120702710 @default.
• W3198373084 cites W3128640141 @default.
• W3198373084 cites W3163741538 @default.
• W3198373084 cites W3177187266 @default.
• W3198373084 cites W3206326321 @default.
• W3198373084 hasPublicationYear "2021" @default.
• W3198373084 type Work @default.
• W3198373084 sameAs 3198373084 @default.
• W3198373084 citedByCount "0" @default.
• W3198373084 crossrefType "posted-content" @default.
• W3198373084 hasAuthorship W3198373084A5036208820 @default.
• W3198373084 hasAuthorship W3198373084A5045267281 @default.
• W3198373084 hasAuthorship W3198373084A5048520383 @default.
• W3198373084 hasAuthorship W3198373084A5054153276 @default.
• W3198373084 hasAuthorship W3198373084A5079918071 @default.
• W3198373084 hasConcept C119857082 @default.
• W3198373084 hasConcept C136389625 @default.
• W3198373084 hasConcept C144024400 @default.
• W3198373084 hasConcept C153180895 @default.
• W3198373084 hasConcept C154945302 @default.
• W3198373084 hasConcept C2779903281 @default.
• W3198373084 hasConcept C36289849 @default.
• W3198373084 hasConcept C41008148 @default.
• W3198373084 hasConcept C50644808 @default.
• W3198373084 hasConcept C95623464 @default.
• W3198373084 hasConceptScore W3198373084C119857082 @default.
• W3198373084 hasConceptScore W3198373084C136389625 @default.
• W3198373084 hasConceptScore W3198373084C144024400 @default.
• W3198373084 hasConceptScore W3198373084C153180895 @default.
• W3198373084 hasConceptScore W3198373084C154945302 @default.
• W3198373084 hasConceptScore W3198373084C2779903281 @default.
• W3198373084 hasConceptScore W3198373084C36289849 @default.
• W3198373084 hasConceptScore W3198373084C41008148 @default.
• W3198373084 hasConceptScore W3198373084C50644808 @default.
• W3198373084 hasConceptScore W3198373084C95623464 @default.
• W3198373084 hasLocation W31983730841 @default.
• W3198373084 hasOpenAccess W3198373084 @default.
• W3198373084 hasPrimaryLocation W31983730841 @default.
• W3198373084 hasRelatedWork W1563900760 @default.
• W3198373084 hasRelatedWork W2014161209 @default.
• W3198373084 hasRelatedWork W2178271665 @default.
• W3198373084 hasRelatedWork W2578674746 @default.
• W3198373084 hasRelatedWork W2586373797 @default.
• W3198373084 hasRelatedWork W2795493767 @default.
• W3198373084 hasRelatedWork W2795547633 @default.
• W3198373084 hasRelatedWork W2896504492 @default.
• W3198373084 hasRelatedWork W2907750296 @default.
• W3198373084 hasRelatedWork W2948328757 @default.
• W3198373084 hasRelatedWork W2987554102 @default.
• W3198373084 hasRelatedWork W3025937546 @default.
• W3198373084 hasRelatedWork W3154778997 @default.
• W3198373084 hasRelatedWork W3159455875 @default.
• W3198373084 hasRelatedWork W3162154991 @default.
• W3198373084 hasRelatedWork W3180713837 @default.
• W3198373084 hasRelatedWork W3211744929 @default.
• W3198373084 hasRelatedWork W1833035053 @default.
• W3198373084 hasRelatedWork W2188670000 @default.
• W3198373084 hasRelatedWork W3116516159 @default.
• W3198373084 isParatext "false" @default.
• W3198373084 isRetracted "false" @default.
• W3198373084 magId "3198373084" @default.
• W3198373084 workType "article" @default.