Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312774307> ?p ?o ?g. }
- W4312774307 endingPage "104225" @default.
- W4312774307 startingPage "104215" @default.
- W4312774307 abstract "With the advent of self-driving cars and the push by large companies into fully driverless transportation services, monitoring passenger behaviour in vehicles is becoming increasingly important for several reasons, such as ensuring safety and comfort. Although several human action recognition (HAR) methods have been proposed, developing a true HAR system remains a very challenging task. If the dataset used to train a model contains a small number of actors, the model can become biased towards these actors and their unique characteristics. This can cause the model to generalise poorly when confronted with new actors performing the same actions. This limitation is particularly acute when developing models to characterise the activities of vehicle occupants, for which data sets are short and scarce. In this study, we describe and evaluate three different methods that aim to address this actor bias and assess their performance in detecting in-vehicle violence. These methods work by removing specific information about the actor from the model’s features during training or by using data that is independent of the actor, such as information about body posture. The experimental results show improvements over the baseline model when evaluated with real data." @default.
- W4312774307 created "2023-01-05" @default.
- W4312774307 creator A5013827007 @default.
- W4312774307 creator A5016677919 @default.
- W4312774307 creator A5018059656 @default.
- W4312774307 creator A5058749114 @default.
- W4312774307 creator A5076833511 @default.
- W4312774307 creator A5078048279 @default.
- W4312774307 creator A5080307019 @default.
- W4312774307 date "2022-01-01" @default.
- W4312774307 modified "2023-10-14" @default.
- W4312774307 title "Toward Vehicle Occupant-Invariant Models for Activity Characterization" @default.
- W4312774307 cites W1522734439 @default.
- W4312774307 cites W1927052826 @default.
- W4312774307 cites W1983364832 @default.
- W4312774307 cites W2016053056 @default.
- W4312774307 cites W2020163092 @default.
- W4312774307 cites W2105101328 @default.
- W4312774307 cites W2126574503 @default.
- W4312774307 cites W2126579184 @default.
- W4312774307 cites W2142194269 @default.
- W4312774307 cites W2194775991 @default.
- W4312774307 cites W2415469094 @default.
- W4312774307 cites W2625366777 @default.
- W4312774307 cites W2746726611 @default.
- W4312774307 cites W2796633859 @default.
- W4312774307 cites W2798592524 @default.
- W4312774307 cites W2883429621 @default.
- W4312774307 cites W2891244534 @default.
- W4312774307 cites W2895243423 @default.
- W4312774307 cites W2962711930 @default.
- W4312774307 cites W2962934715 @default.
- W4312774307 cites W2963076818 @default.
- W4312774307 cites W2963150697 @default.
- W4312774307 cites W2963155035 @default.
- W4312774307 cites W2963282966 @default.
- W4312774307 cites W2963524571 @default.
- W4312774307 cites W2963820951 @default.
- W4312774307 cites W2982358316 @default.
- W4312774307 cites W2984287396 @default.
- W4312774307 cites W2990503944 @default.
- W4312774307 cites W3003731434 @default.
- W4312774307 cites W3012362498 @default.
- W4312774307 cites W3035225512 @default.
- W4312774307 cites W3098538019 @default.
- W4312774307 cites W3126314169 @default.
- W4312774307 cites W3128299371 @default.
- W4312774307 cites W3128636476 @default.
- W4312774307 cites W4213390819 @default.
- W4312774307 cites W4243437785 @default.
- W4312774307 doi "https://doi.org/10.1109/access.2022.3210973" @default.
- W4312774307 hasPublicationYear "2022" @default.
- W4312774307 type Work @default.
- W4312774307 citedByCount "3" @default.
- W4312774307 countsByYear W43127743072022 @default.
- W4312774307 countsByYear W43127743072023 @default.
- W4312774307 crossrefType "journal-article" @default.
- W4312774307 hasAuthorship W4312774307A5013827007 @default.
- W4312774307 hasAuthorship W4312774307A5016677919 @default.
- W4312774307 hasAuthorship W4312774307A5018059656 @default.
- W4312774307 hasAuthorship W4312774307A5058749114 @default.
- W4312774307 hasAuthorship W4312774307A5076833511 @default.
- W4312774307 hasAuthorship W4312774307A5078048279 @default.
- W4312774307 hasAuthorship W4312774307A5080307019 @default.
- W4312774307 hasBestOaLocation W43127743071 @default.
- W4312774307 hasConcept C107457646 @default.
- W4312774307 hasConcept C111368507 @default.
- W4312774307 hasConcept C119857082 @default.
- W4312774307 hasConcept C121332964 @default.
- W4312774307 hasConcept C12725497 @default.
- W4312774307 hasConcept C127313418 @default.
- W4312774307 hasConcept C127413603 @default.
- W4312774307 hasConcept C154945302 @default.
- W4312774307 hasConcept C18762648 @default.
- W4312774307 hasConcept C201995342 @default.
- W4312774307 hasConcept C2780451532 @default.
- W4312774307 hasConcept C2780791683 @default.
- W4312774307 hasConcept C41008148 @default.
- W4312774307 hasConcept C62520636 @default.
- W4312774307 hasConcept C67186912 @default.
- W4312774307 hasConcept C77088390 @default.
- W4312774307 hasConcept C78519656 @default.
- W4312774307 hasConceptScore W4312774307C107457646 @default.
- W4312774307 hasConceptScore W4312774307C111368507 @default.
- W4312774307 hasConceptScore W4312774307C119857082 @default.
- W4312774307 hasConceptScore W4312774307C121332964 @default.
- W4312774307 hasConceptScore W4312774307C12725497 @default.
- W4312774307 hasConceptScore W4312774307C127313418 @default.
- W4312774307 hasConceptScore W4312774307C127413603 @default.
- W4312774307 hasConceptScore W4312774307C154945302 @default.
- W4312774307 hasConceptScore W4312774307C18762648 @default.
- W4312774307 hasConceptScore W4312774307C201995342 @default.
- W4312774307 hasConceptScore W4312774307C2780451532 @default.
- W4312774307 hasConceptScore W4312774307C2780791683 @default.
- W4312774307 hasConceptScore W4312774307C41008148 @default.
- W4312774307 hasConceptScore W4312774307C62520636 @default.
- W4312774307 hasConceptScore W4312774307C67186912 @default.
- W4312774307 hasConceptScore W4312774307C77088390 @default.