FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383532823> ?p ?o ?g. }

• W4383532823 endingPage "102887" @default.
• W4383532823 startingPage "102887" @default.
• W4383532823 abstract "3D human pose estimation is a key component of clinical monitoring systems. The clinical applicability of deep pose estimation models, however, is limited by their poor generalization under domain shifts along with their need for sufficient labeled training data. As a remedy, we present a novel domain adaptation method, adapting a model from a labeled source to a shifted unlabeled target domain. Our method comprises two complementary adaptation strategies based on prior knowledge about human anatomy. First, we guide the learning process in the target domain by constraining predictions to the space of anatomically plausible poses. To this end, we embed the prior knowledge into an anatomical loss function that penalizes asymmetric limb lengths, implausible bone lengths, and implausible joint angles. Second, we propose to filter pseudo labels for self-training according to their anatomical plausibility and incorporate the concept into the Mean Teacher paradigm. We unify both strategies in a point cloud-based framework applicable to unsupervised and source-free domain adaptation. Evaluation is performed for in-bed pose estimation under two adaptation scenarios, using the public SLP dataset and a newly created dataset. Our method consistently outperforms various state-of-the-art domain adaptation methods, surpasses the baseline model by 31%/66%, and reduces the domain gap by 65%/82%. Source code is available at https://github.com/multimodallearning/da-3dhpe-anatomy." @default.
• W4383532823 created "2023-07-08" @default.
• W4383532823 creator A5007770496 @default.
• W4383532823 creator A5011641162 @default.
• W4383532823 creator A5031269872 @default.
• W4383532823 creator A5035877004 @default.
• W4383532823 creator A5060865818 @default.
• W4383532823 creator A5064304390 @default.
• W4383532823 date "2023-10-01" @default.
• W4383532823 modified "2023-10-06" @default.
• W4383532823 title "Anatomy-guided domain adaptation for 3D in-bed human pose estimation" @default.
• W4383532823 cites W1943191679 @default.
• W4383532823 cites W1967554269 @default.
• W4383532823 cites W1970804146 @default.
• W4383532823 cites W2094278526 @default.
• W4383532823 cites W2101032778 @default.
• W4383532823 cites W2288408787 @default.
• W4383532823 cites W2312004824 @default.
• W4383532823 cites W2495373560 @default.
• W4383532823 cites W2593768305 @default.
• W4383532823 cites W2604375920 @default.
• W4383532823 cites W2756050327 @default.
• W4383532823 cites W2786808285 @default.
• W4383532823 cites W2795089319 @default.
• W4383532823 cites W2799191197 @default.
• W4383532823 cites W2799738340 @default.
• W4383532823 cites W2895281799 @default.
• W4383532823 cites W2900753655 @default.
• W4383532823 cites W2903283814 @default.
• W4383532823 cites W2903891898 @default.
• W4383532823 cites W2911933816 @default.
• W4383532823 cites W2915974780 @default.
• W4383532823 cites W2916798096 @default.
• W4383532823 cites W2949813473 @default.
• W4383532823 cites W2962687275 @default.
• W4383532823 cites W2962793481 @default.
• W4383532823 cites W2963107255 @default.
• W4383532823 cites W2963231572 @default.
• W4383532823 cites W2963275094 @default.
• W4383532823 cites W2963402313 @default.
• W4383532823 cites W2963403405 @default.
• W4383532823 cites W2963508807 @default.
• W4383532823 cites W2963509914 @default.
• W4383532823 cites W2964184998 @default.
• W4383532823 cites W2965963311 @default.
• W4383532823 cites W2968634921 @default.
• W4383532823 cites W2969893028 @default.
• W4383532823 cites W2972285644 @default.
• W4383532823 cites W2979548969 @default.
• W4383532823 cites W2979750740 @default.
• W4383532823 cites W2983454547 @default.
• W4383532823 cites W2990231018 @default.
• W4383532823 cites W3000322757 @default.
• W4383532823 cites W3006267297 @default.
• W4383532823 cites W3017324723 @default.
• W4383532823 cites W3021998000 @default.
• W4383532823 cites W3034403720 @default.
• W4383532823 cites W3035069238 @default.
• W4383532823 cites W3091040708 @default.
• W4383532823 cites W3102054705 @default.
• W4383532823 cites W3112175158 @default.
• W4383532823 cites W3118644257 @default.
• W4383532823 cites W3119635706 @default.
• W4383532823 cites W3120575095 @default.
• W4383532823 cites W3133610314 @default.
• W4383532823 cites W3135266094 @default.
• W4383532823 cites W3137531678 @default.
• W4383532823 cites W3166409449 @default.
• W4383532823 cites W3171433839 @default.
• W4383532823 cites W3173453526 @default.
• W4383532823 cites W3175042385 @default.
• W4383532823 cites W3175269419 @default.
• W4383532823 cites W3175712787 @default.
• W4383532823 cites W3196835455 @default.
• W4383532823 cites W3201774370 @default.
• W4383532823 cites W343636949 @default.
• W4383532823 cites W4241368925 @default.
• W4383532823 cites W4242710771 @default.
• W4383532823 cites W4280517343 @default.
• W4383532823 cites W4283374467 @default.
• W4383532823 cites W4283798951 @default.
• W4383532823 cites W4312379726 @default.
• W4383532823 cites W4312897837 @default.
• W4383532823 cites W4313127740 @default.
• W4383532823 doi "https://doi.org/10.1016/j.media.2023.102887" @default.
• W4383532823 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37453235" @default.
• W4383532823 hasPublicationYear "2023" @default.
• W4383532823 type Work @default.
• W4383532823 citedByCount "1" @default.
• W4383532823 crossrefType "journal-article" @default.
• W4383532823 hasAuthorship W4383532823A5007770496 @default.
• W4383532823 hasAuthorship W4383532823A5011641162 @default.
• W4383532823 hasAuthorship W4383532823A5031269872 @default.
• W4383532823 hasAuthorship W4383532823A5035877004 @default.
• W4383532823 hasAuthorship W4383532823A5060865818 @default.
• W4383532823 hasAuthorship W4383532823A5064304390 @default.
• W4383532823 hasBestOaLocation W43835328232 @default.
• W4383532823 hasConcept C111919701 @default.

• next