Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288045115> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4288045115 endingPage "108934" @default.
- W4288045115 startingPage "108934" @default.
- W4288045115 abstract "In monocular image scenes, 3D human pose estimation exhibits inherent ambiguity due to the loss of depth information and occlusions. Simply regressing body joints with high uncertainties will lead to model overfitting and poor generalization. In this paper, we propose an uncertainty-based framework to jointly learn 3D human poses and the uncertainty of each joint. Our proposed joint estimation framework aims to mitigate the adverse effects of training samples with high uncertainties and facilitate the training procedure. To be specific, we model each body joint as a Laplace distribution for uncertainty representation. Since visual joints often exhibit low uncertainties while occluded ones have high uncertainties, we develop an adaptive scaling factor, named the uncertainty-aware scaling factor, to ease the network optimization in accordance with the joint uncertainties. By doing so, our network is able to converge faster and significantly reduce the adverse effects caused by those ambiguous joints. Furthermore, we present an uncertainty-aware graph convolutional network by exploiting the learned joint uncertainties and the relationships among joints to refine the initial joint localization. Extensive experiments on single-person (Human3.6M) and multi-person (MuCo-3DHP & MuPoTS-3D) 3D human pose estimation datasets demonstrate the effectiveness of our method." @default.
- W4288045115 created "2022-07-27" @default.
- W4288045115 creator A5005421447 @default.
- W4288045115 creator A5013734579 @default.
- W4288045115 creator A5026558988 @default.
- W4288045115 creator A5028601916 @default.
- W4288045115 creator A5035295689 @default.
- W4288045115 date "2022-12-01" @default.
- W4288045115 modified "2023-10-18" @default.
- W4288045115 title "Single image based 3D human pose estimation via uncertainty learning" @default.
- W4288045115 cites W2032618685 @default.
- W4288045115 cites W2101032778 @default.
- W4288045115 cites W2573854917 @default.
- W4288045115 cites W2963084622 @default.
- W4288045115 cites W2965604235 @default.
- W4288045115 cites W3025313707 @default.
- W4288045115 cites W3026784707 @default.
- W4288045115 cites W3032008230 @default.
- W4288045115 cites W3039961680 @default.
- W4288045115 cites W3106126861 @default.
- W4288045115 cites W3186885009 @default.
- W4288045115 cites W4205474609 @default.
- W4288045115 doi "https://doi.org/10.1016/j.patcog.2022.108934" @default.
- W4288045115 hasPublicationYear "2022" @default.
- W4288045115 type Work @default.
- W4288045115 citedByCount "4" @default.
- W4288045115 countsByYear W42880451152023 @default.
- W4288045115 crossrefType "journal-article" @default.
- W4288045115 hasAuthorship W4288045115A5005421447 @default.
- W4288045115 hasAuthorship W4288045115A5013734579 @default.
- W4288045115 hasAuthorship W4288045115A5026558988 @default.
- W4288045115 hasAuthorship W4288045115A5028601916 @default.
- W4288045115 hasAuthorship W4288045115A5035295689 @default.
- W4288045115 hasConcept C119857082 @default.
- W4288045115 hasConcept C127413603 @default.
- W4288045115 hasConcept C134306372 @default.
- W4288045115 hasConcept C153180895 @default.
- W4288045115 hasConcept C154945302 @default.
- W4288045115 hasConcept C170154142 @default.
- W4288045115 hasConcept C177148314 @default.
- W4288045115 hasConcept C18555067 @default.
- W4288045115 hasConcept C199360897 @default.
- W4288045115 hasConcept C22019652 @default.
- W4288045115 hasConcept C2780522230 @default.
- W4288045115 hasConcept C31972630 @default.
- W4288045115 hasConcept C33923547 @default.
- W4288045115 hasConcept C36613465 @default.
- W4288045115 hasConcept C41008148 @default.
- W4288045115 hasConcept C50644808 @default.
- W4288045115 hasConcept C52102323 @default.
- W4288045115 hasConcept C65909025 @default.
- W4288045115 hasConceptScore W4288045115C119857082 @default.
- W4288045115 hasConceptScore W4288045115C127413603 @default.
- W4288045115 hasConceptScore W4288045115C134306372 @default.
- W4288045115 hasConceptScore W4288045115C153180895 @default.
- W4288045115 hasConceptScore W4288045115C154945302 @default.
- W4288045115 hasConceptScore W4288045115C170154142 @default.
- W4288045115 hasConceptScore W4288045115C177148314 @default.
- W4288045115 hasConceptScore W4288045115C18555067 @default.
- W4288045115 hasConceptScore W4288045115C199360897 @default.
- W4288045115 hasConceptScore W4288045115C22019652 @default.
- W4288045115 hasConceptScore W4288045115C2780522230 @default.
- W4288045115 hasConceptScore W4288045115C31972630 @default.
- W4288045115 hasConceptScore W4288045115C33923547 @default.
- W4288045115 hasConceptScore W4288045115C36613465 @default.
- W4288045115 hasConceptScore W4288045115C41008148 @default.
- W4288045115 hasConceptScore W4288045115C50644808 @default.
- W4288045115 hasConceptScore W4288045115C52102323 @default.
- W4288045115 hasConceptScore W4288045115C65909025 @default.
- W4288045115 hasFunder F4320321001 @default.
- W4288045115 hasFunder F4320334704 @default.
- W4288045115 hasFunder F4320335787 @default.
- W4288045115 hasLocation W42880451151 @default.
- W4288045115 hasOpenAccess W4288045115 @default.
- W4288045115 hasPrimaryLocation W42880451151 @default.
- W4288045115 hasRelatedWork W1628937209 @default.
- W4288045115 hasRelatedWork W1798868054 @default.
- W4288045115 hasRelatedWork W1968716783 @default.
- W4288045115 hasRelatedWork W2004095265 @default.
- W4288045115 hasRelatedWork W2052286098 @default.
- W4288045115 hasRelatedWork W2129348295 @default.
- W4288045115 hasRelatedWork W2144760288 @default.
- W4288045115 hasRelatedWork W2891001608 @default.
- W4288045115 hasRelatedWork W3102636071 @default.
- W4288045115 hasRelatedWork W4312709684 @default.
- W4288045115 hasVolume "132" @default.
- W4288045115 isParatext "false" @default.
- W4288045115 isRetracted "false" @default.
- W4288045115 workType "article" @default.