Matches in SemOpenAlex for { <https://semopenalex.org/work/W3137020077> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3137020077 abstract "There are large individual differences in physiological processes, making designing personalized health sensing algorithms challenging. Existing machine learning systems struggle to generalize well to unseen subjects or contexts and can often contain problematic biases. Video-based physiological measurement is no exception. Therefore, learning personalized or customized models from a small number of unlabeled samples is very attractive as it would allow fast calibrations to improve generalization and help correct biases. In this paper, we present a novel meta-learning approach called MetaPhys for personalized video-based cardiac measurement for non-contact pulse and heart rate monitoring. Our method uses only 18-seconds of video for customization and works effectively in both supervised and unsupervised manners. We evaluate our approach on two benchmark datasets and demonstrate superior performance in cross-dataset evaluation with substantial reductions (42% to 44%) in errors compared with state-of-the-art approaches. We also find that our method leads to large reductions in bias due to skin type." @default.
- W3137020077 created "2021-03-29" @default.
- W3137020077 creator A5008448494 @default.
- W3137020077 creator A5011623194 @default.
- W3137020077 creator A5021687717 @default.
- W3137020077 creator A5039879761 @default.
- W3137020077 creator A5040219094 @default.
- W3137020077 creator A5066796307 @default.
- W3137020077 date "2021-04-08" @default.
- W3137020077 modified "2023-10-18" @default.
- W3137020077 title "MetaPhys" @default.
- W3137020077 cites W1984026713 @default.
- W3137020077 cites W1998391547 @default.
- W3137020077 cites W2026347416 @default.
- W3137020077 cites W2037029919 @default.
- W3137020077 cites W2069692225 @default.
- W3137020077 cites W2470957930 @default.
- W3137020077 cites W2520509592 @default.
- W3137020077 cites W2729002305 @default.
- W3137020077 cites W2766766681 @default.
- W3137020077 cites W2945978556 @default.
- W3137020077 cites W2963433879 @default.
- W3137020077 cites W2963499285 @default.
- W3137020077 cites W2964081807 @default.
- W3137020077 cites W2979437880 @default.
- W3137020077 cites W2981352030 @default.
- W3137020077 cites W2983307807 @default.
- W3137020077 cites W2990152177 @default.
- W3137020077 cites W3001042480 @default.
- W3137020077 cites W3001625344 @default.
- W3137020077 cites W3045277594 @default.
- W3137020077 cites W3085129806 @default.
- W3137020077 cites W3108080438 @default.
- W3137020077 doi "https://doi.org/10.1145/3450439.3451870" @default.
- W3137020077 hasPublicationYear "2021" @default.
- W3137020077 type Work @default.
- W3137020077 sameAs 3137020077 @default.
- W3137020077 citedByCount "23" @default.
- W3137020077 countsByYear W31370200772021 @default.
- W3137020077 countsByYear W31370200772022 @default.
- W3137020077 countsByYear W31370200772023 @default.
- W3137020077 crossrefType "proceedings-article" @default.
- W3137020077 hasAuthorship W3137020077A5008448494 @default.
- W3137020077 hasAuthorship W3137020077A5011623194 @default.
- W3137020077 hasAuthorship W3137020077A5021687717 @default.
- W3137020077 hasAuthorship W3137020077A5039879761 @default.
- W3137020077 hasAuthorship W3137020077A5040219094 @default.
- W3137020077 hasAuthorship W3137020077A5066796307 @default.
- W3137020077 hasBestOaLocation W31370200771 @default.
- W3137020077 hasConcept C119857082 @default.
- W3137020077 hasConcept C13280743 @default.
- W3137020077 hasConcept C134306372 @default.
- W3137020077 hasConcept C136764020 @default.
- W3137020077 hasConcept C154945302 @default.
- W3137020077 hasConcept C177148314 @default.
- W3137020077 hasConcept C183003079 @default.
- W3137020077 hasConcept C185798385 @default.
- W3137020077 hasConcept C205649164 @default.
- W3137020077 hasConcept C33923547 @default.
- W3137020077 hasConcept C41008148 @default.
- W3137020077 hasConceptScore W3137020077C119857082 @default.
- W3137020077 hasConceptScore W3137020077C13280743 @default.
- W3137020077 hasConceptScore W3137020077C134306372 @default.
- W3137020077 hasConceptScore W3137020077C136764020 @default.
- W3137020077 hasConceptScore W3137020077C154945302 @default.
- W3137020077 hasConceptScore W3137020077C177148314 @default.
- W3137020077 hasConceptScore W3137020077C183003079 @default.
- W3137020077 hasConceptScore W3137020077C185798385 @default.
- W3137020077 hasConceptScore W3137020077C205649164 @default.
- W3137020077 hasConceptScore W3137020077C33923547 @default.
- W3137020077 hasConceptScore W3137020077C41008148 @default.
- W3137020077 hasLocation W31370200771 @default.
- W3137020077 hasOpenAccess W3137020077 @default.
- W3137020077 hasPrimaryLocation W31370200771 @default.
- W3137020077 hasRelatedWork W112744582 @default.
- W3137020077 hasRelatedWork W1485630101 @default.
- W3137020077 hasRelatedWork W2089594643 @default.
- W3137020077 hasRelatedWork W2108595774 @default.
- W3137020077 hasRelatedWork W2498017833 @default.
- W3137020077 hasRelatedWork W2961085424 @default.
- W3137020077 hasRelatedWork W4221150964 @default.
- W3137020077 hasRelatedWork W4306674287 @default.
- W3137020077 hasRelatedWork W87991986 @default.
- W3137020077 hasRelatedWork W4224009465 @default.
- W3137020077 isParatext "false" @default.
- W3137020077 isRetracted "false" @default.
- W3137020077 magId "3137020077" @default.
- W3137020077 workType "article" @default.