Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034581612> ?p ?o ?g. }
- W3034581612 abstract "For monocular 3D pose estimation conditioned on 2D detection, noisy/unreliable input is a key obstacle in this task. Simple structure constraints attempting to tackle this problem, e.g., symmetry loss and joint angle limit, could only provide marginal improvements and are commonly treated as auxiliary losses in previous researches. Thus it still remains challenging about how to effectively utilize the power of human prior knowledge for this task. In this paper, we propose to address above issue in a systematic view. Firstly, we show that optimizing the kinematics structure of noisy 2D inputs is critical to obtain accurate 3D estimations. Secondly, based on corrected 2D joints, we further explicitly decompose articulated motion with human topology, which leads to more compact 3D static structure easier for estimation. Finally, temporal refinement emphasizing the validity of 3D dynamic structure is naturally developed to pursue more accurate result. Above three steps are seamlessly integrated into deep neural models, which form a deep kinematics analysis pipeline concurrently considering the static/dynamic structure of 2D inputs and 3D outputs. Extensive experiments show that proposed framework achieves state-of-the-art performance on two widely used 3D human action datasets. Meanwhile, targeted ablation study shows that each former step is critical for the latter one to obtain promising results." @default.
- W3034581612 created "2020-06-19" @default.
- W3034581612 creator A5014362734 @default.
- W3034581612 creator A5019708391 @default.
- W3034581612 creator A5020501435 @default.
- W3034581612 creator A5061038696 @default.
- W3034581612 creator A5061294954 @default.
- W3034581612 creator A5081117163 @default.
- W3034581612 date "2020-06-01" @default.
- W3034581612 modified "2023-10-12" @default.
- W3034581612 title "Deep Kinematics Analysis for Monocular 3D Human Pose Estimation" @default.
- W3034581612 cites W2064675550 @default.
- W3034581612 cites W2099333815 @default.
- W3034581612 cites W2101032778 @default.
- W3034581612 cites W2554247908 @default.
- W3034581612 cites W2557698284 @default.
- W3034581612 cites W2559085405 @default.
- W3034581612 cites W2583372902 @default.
- W3034581612 cites W2604375920 @default.
- W3034581612 cites W2611932403 @default.
- W3034581612 cites W2612706635 @default.
- W3034581612 cites W2725422033 @default.
- W3034581612 cites W2736334449 @default.
- W3034581612 cites W2742737904 @default.
- W3034581612 cites W2758778552 @default.
- W3034581612 cites W2788865504 @default.
- W3034581612 cites W2797184202 @default.
- W3034581612 cites W2798637590 @default.
- W3034581612 cites W2798646183 @default.
- W3034581612 cites W2808485533 @default.
- W3034581612 cites W2904988869 @default.
- W3034581612 cites W2934361577 @default.
- W3034581612 cites W2962896489 @default.
- W3034581612 cites W2963013806 @default.
- W3034581612 cites W2963057320 @default.
- W3034581612 cites W2963150697 @default.
- W3034581612 cites W2963203809 @default.
- W3034581612 cites W2963383668 @default.
- W3034581612 cites W2963524571 @default.
- W3034581612 cites W2963592930 @default.
- W3034581612 cites W2963688992 @default.
- W3034581612 cites W2963995996 @default.
- W3034581612 cites W2964221239 @default.
- W3034581612 cites W2966735886 @default.
- W3034581612 cites W2968459013 @default.
- W3034581612 cites W2970285700 @default.
- W3034581612 cites W2972662547 @default.
- W3034581612 cites W2979936813 @default.
- W3034581612 cites W2981660954 @default.
- W3034581612 cites W2983098675 @default.
- W3034581612 cites W2989465897 @default.
- W3034581612 cites W2991247554 @default.
- W3034581612 cites W3098612954 @default.
- W3034581612 cites W602397586 @default.
- W3034581612 doi "https://doi.org/10.1109/cvpr42600.2020.00098" @default.
- W3034581612 hasPublicationYear "2020" @default.
- W3034581612 type Work @default.
- W3034581612 sameAs 3034581612 @default.
- W3034581612 citedByCount "105" @default.
- W3034581612 countsByYear W30345816122020 @default.
- W3034581612 countsByYear W30345816122021 @default.
- W3034581612 countsByYear W30345816122022 @default.
- W3034581612 countsByYear W30345816122023 @default.
- W3034581612 crossrefType "proceedings-article" @default.
- W3034581612 hasAuthorship W3034581612A5014362734 @default.
- W3034581612 hasAuthorship W3034581612A5019708391 @default.
- W3034581612 hasAuthorship W3034581612A5020501435 @default.
- W3034581612 hasAuthorship W3034581612A5061038696 @default.
- W3034581612 hasAuthorship W3034581612A5061294954 @default.
- W3034581612 hasAuthorship W3034581612A5081117163 @default.
- W3034581612 hasConcept C108583219 @default.
- W3034581612 hasConcept C11413529 @default.
- W3034581612 hasConcept C114614502 @default.
- W3034581612 hasConcept C121332964 @default.
- W3034581612 hasConcept C127413603 @default.
- W3034581612 hasConcept C154945302 @default.
- W3034581612 hasConcept C184720557 @default.
- W3034581612 hasConcept C199360897 @default.
- W3034581612 hasConcept C201995342 @default.
- W3034581612 hasConcept C2780451532 @default.
- W3034581612 hasConcept C31972630 @default.
- W3034581612 hasConcept C33923547 @default.
- W3034581612 hasConcept C36613465 @default.
- W3034581612 hasConcept C39920418 @default.
- W3034581612 hasConcept C41008148 @default.
- W3034581612 hasConcept C43521106 @default.
- W3034581612 hasConcept C52102323 @default.
- W3034581612 hasConcept C65909025 @default.
- W3034581612 hasConcept C74650414 @default.
- W3034581612 hasConceptScore W3034581612C108583219 @default.
- W3034581612 hasConceptScore W3034581612C11413529 @default.
- W3034581612 hasConceptScore W3034581612C114614502 @default.
- W3034581612 hasConceptScore W3034581612C121332964 @default.
- W3034581612 hasConceptScore W3034581612C127413603 @default.
- W3034581612 hasConceptScore W3034581612C154945302 @default.
- W3034581612 hasConceptScore W3034581612C184720557 @default.
- W3034581612 hasConceptScore W3034581612C199360897 @default.
- W3034581612 hasConceptScore W3034581612C201995342 @default.
- W3034581612 hasConceptScore W3034581612C2780451532 @default.
- W3034581612 hasConceptScore W3034581612C31972630 @default.