Matches in SemOpenAlex for { <https://semopenalex.org/work/W2953216610> ?p ?o ?g. }
- W2953216610 abstract "3D human pose estimation from a single image is a challenging problem, especially for in-the-wild settings due to the lack of 3D annotated data. We propose two anatomically inspired loss functions and use them with a weakly-supervised learning framework to jointly learn from large-scale in-the-wild 2D and indoor/synthetic 3D data. We also present a simple temporal network that exploits temporal and structural cues present in predicted pose sequences to temporally harmonize the pose estimations. We carefully analyze the proposed contributions through loss surface visualizations and sensitivity analysis to facilitate deeper understanding of their working mechanism. Our complete pipeline improves the state-of-the-art by 11.8% and 12% on Human3.6M and MPI-INF-3DHP, respectively, and runs at 30 FPS on a commodity graphics card." @default.
- W2953216610 created "2019-06-27" @default.
- W2953216610 creator A5010569734 @default.
- W2953216610 creator A5019742155 @default.
- W2953216610 creator A5028267869 @default.
- W2953216610 creator A5051286077 @default.
- W2953216610 creator A5076249543 @default.
- W2953216610 creator A5089712643 @default.
- W2953216610 date "2017-11-25" @default.
- W2953216610 modified "2023-09-27" @default.
- W2953216610 title "Learning 3D Human Pose from Structure and Motion" @default.
- W2953216610 cites W1565544260 @default.
- W2953216610 cites W1943191679 @default.
- W2953216610 cites W1967554269 @default.
- W2953216610 cites W1970565565 @default.
- W2953216610 cites W2004987096 @default.
- W2953216610 cites W2006262794 @default.
- W2953216610 cites W2025647058 @default.
- W2953216610 cites W2027222744 @default.
- W2953216610 cites W2080873731 @default.
- W2953216610 cites W2080900945 @default.
- W2953216610 cites W2101032778 @default.
- W2953216610 cites W2155196764 @default.
- W2953216610 cites W2194775991 @default.
- W2953216610 cites W2293220651 @default.
- W2953216610 cites W2467838519 @default.
- W2953216610 cites W2483862638 @default.
- W2953216610 cites W2515603221 @default.
- W2953216610 cites W2522527348 @default.
- W2953216610 cites W2524613005 @default.
- W2953216610 cites W2557698284 @default.
- W2953216610 cites W2583372902 @default.
- W2953216610 cites W2586735627 @default.
- W2953216610 cites W2611932403 @default.
- W2953216610 cites W2746791238 @default.
- W2953216610 cites W2781181706 @default.
- W2953216610 cites W2797184202 @default.
- W2953216610 cites W2950762923 @default.
- W2953216610 cites W2950977907 @default.
- W2953216610 cites W2952122856 @default.
- W2953216610 cites W2952504680 @default.
- W2953216610 cites W2953139137 @default.
- W2953216610 cites W2953258117 @default.
- W2953216610 cites W2962729993 @default.
- W2953216610 cites W2963013806 @default.
- W2953216610 cites W2963383668 @default.
- W2953216610 cites W2963688992 @default.
- W2953216610 cites W2964121744 @default.
- W2953216610 cites W753012316 @default.
- W2953216610 hasPublicationYear "2017" @default.
- W2953216610 type Work @default.
- W2953216610 sameAs 2953216610 @default.
- W2953216610 citedByCount "7" @default.
- W2953216610 countsByYear W29532166102017 @default.
- W2953216610 countsByYear W29532166102018 @default.
- W2953216610 countsByYear W29532166102019 @default.
- W2953216610 countsByYear W29532166102020 @default.
- W2953216610 crossrefType "posted-content" @default.
- W2953216610 hasAuthorship W2953216610A5010569734 @default.
- W2953216610 hasAuthorship W2953216610A5019742155 @default.
- W2953216610 hasAuthorship W2953216610A5028267869 @default.
- W2953216610 hasAuthorship W2953216610A5051286077 @default.
- W2953216610 hasAuthorship W2953216610A5076249543 @default.
- W2953216610 hasAuthorship W2953216610A5089712643 @default.
- W2953216610 hasConcept C108583219 @default.
- W2953216610 hasConcept C119857082 @default.
- W2953216610 hasConcept C121684516 @default.
- W2953216610 hasConcept C127413603 @default.
- W2953216610 hasConcept C153180895 @default.
- W2953216610 hasConcept C154945302 @default.
- W2953216610 hasConcept C165696696 @default.
- W2953216610 hasConcept C199360897 @default.
- W2953216610 hasConcept C21200559 @default.
- W2953216610 hasConcept C21442007 @default.
- W2953216610 hasConcept C24326235 @default.
- W2953216610 hasConcept C31972630 @default.
- W2953216610 hasConcept C38652104 @default.
- W2953216610 hasConcept C41008148 @default.
- W2953216610 hasConcept C43521106 @default.
- W2953216610 hasConcept C52102323 @default.
- W2953216610 hasConcept C77660652 @default.
- W2953216610 hasConceptScore W2953216610C108583219 @default.
- W2953216610 hasConceptScore W2953216610C119857082 @default.
- W2953216610 hasConceptScore W2953216610C121684516 @default.
- W2953216610 hasConceptScore W2953216610C127413603 @default.
- W2953216610 hasConceptScore W2953216610C153180895 @default.
- W2953216610 hasConceptScore W2953216610C154945302 @default.
- W2953216610 hasConceptScore W2953216610C165696696 @default.
- W2953216610 hasConceptScore W2953216610C199360897 @default.
- W2953216610 hasConceptScore W2953216610C21200559 @default.
- W2953216610 hasConceptScore W2953216610C21442007 @default.
- W2953216610 hasConceptScore W2953216610C24326235 @default.
- W2953216610 hasConceptScore W2953216610C31972630 @default.
- W2953216610 hasConceptScore W2953216610C38652104 @default.
- W2953216610 hasConceptScore W2953216610C41008148 @default.
- W2953216610 hasConceptScore W2953216610C43521106 @default.
- W2953216610 hasConceptScore W2953216610C52102323 @default.
- W2953216610 hasConceptScore W2953216610C77660652 @default.
- W2953216610 hasLocation W29532166101 @default.
- W2953216610 hasOpenAccess W2953216610 @default.