FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2798646183> ?p ?o ?g. }

• W2798646183 abstract "Our ability to train end-to-end systems for 3D human pose estimation from single images is currently constrained by the limited availability of 3D annotations for natural images. Most datasets are captured using Motion Capture (MoCap) systems in a studio setting and it is difficult to reach the variability of 2D human pose datasets, like MPII or LSP. To alleviate the need for accurate 3D ground truth, we propose to use a weaker supervision signal provided by the ordinal depths of human joints. This information can be acquired by human annotators for a wide range of images and poses. We showcase the effectiveness and flexibility of training Convolutional Networks (ConvNets) with these ordinal relations in different settings, always achieving competitive performance with ConvNets trained with accurate 3D joint coordinates. Additionally, to demonstrate the potential of the approach, we augment the popular LSP and MPII datasets with ordinal depth annotations. This extension allows us to present quantitative and qualitative evaluation in non-studio conditions. Simultaneously, these ordinal annotations can be easily incorporated in the training procedure of typical ConvNets for 3D human pose. Through this inclusion we achieve new state-of-the-art performance for the relevant benchmarks and validate the effectiveness of ordinal depth supervision for 3D human pose." @default.
• W2798646183 created "2018-05-07" @default.
• W2798646183 creator A5048438237 @default.
• W2798646183 creator A5050660826 @default.
• W2798646183 creator A5060815622 @default.
• W2798646183 date "2018-06-01" @default.
• W2798646183 modified "2023-10-12" @default.
• W2798646183 title "Ordinal Depth Supervision for 3D Human Pose Estimation" @default.
• W2798646183 cites W1934235358 @default.
• W2798646183 cites W1943191679 @default.
• W2798646183 cites W1956126447 @default.
• W2798646183 cites W1983154976 @default.
• W2798646183 cites W1986123980 @default.
• W2798646183 cites W1991264156 @default.
• W2798646183 cites W2039262381 @default.
• W2798646183 cites W2059001985 @default.
• W2798646183 cites W2076491823 @default.
• W2798646183 cites W2080873731 @default.
• W2798646183 cites W2099333815 @default.
• W2798646183 cites W2101032778 @default.
• W2798646183 cites W2108862644 @default.
• W2798646183 cites W2111446867 @default.
• W2798646183 cites W2134704262 @default.
• W2798646183 cites W2135533529 @default.
• W2798646183 cites W2136024719 @default.
• W2798646183 cites W2143331230 @default.
• W2798646183 cites W2169738563 @default.
• W2798646183 cites W2169852119 @default.
• W2798646183 cites W2175012183 @default.
• W2798646183 cites W2199820243 @default.
• W2798646183 cites W2221366145 @default.
• W2798646183 cites W2314448390 @default.
• W2798646183 cites W2535410496 @default.
• W2798646183 cites W2554247908 @default.
• W2798646183 cites W2557698284 @default.
• W2798646183 cites W2559085405 @default.
• W2798646183 cites W2573098616 @default.
• W2798646183 cites W2576289912 @default.
• W2798646183 cites W2583372902 @default.
• W2798646183 cites W2583585015 @default.
• W2798646183 cites W2585185777 @default.
• W2798646183 cites W2604375920 @default.
• W2798646183 cites W2605947573 @default.
• W2798646183 cites W2611932403 @default.
• W2798646183 cites W2612706635 @default.
• W2798646183 cites W2742737904 @default.
• W2798646183 cites W2756050327 @default.
• W2798646183 cites W2758778552 @default.
• W2798646183 cites W2781181706 @default.
• W2798646183 cites W2962729993 @default.
• W2798646183 cites W2962891704 @default.
• W2798646183 cites W2963013806 @default.
• W2798646183 cites W2963592930 @default.
• W2798646183 cites W2963688992 @default.
• W2798646183 cites W2964291722 @default.
• W2798646183 cites W2964304707 @default.
• W2798646183 cites W602397586 @default.
• W2798646183 doi "https://doi.org/10.1109/cvpr.2018.00763" @default.
• W2798646183 hasPublicationYear "2018" @default.
• W2798646183 type Work @default.
• W2798646183 sameAs 2798646183 @default.
• W2798646183 citedByCount "287" @default.
• W2798646183 countsByYear W27986461832018 @default.
• W2798646183 countsByYear W27986461832019 @default.
• W2798646183 countsByYear W27986461832020 @default.
• W2798646183 countsByYear W27986461832021 @default.
• W2798646183 countsByYear W27986461832022 @default.
• W2798646183 countsByYear W27986461832023 @default.
• W2798646183 crossrefType "proceedings-article" @default.
• W2798646183 hasAuthorship W2798646183A5048438237 @default.
• W2798646183 hasAuthorship W2798646183A5050660826 @default.
• W2798646183 hasAuthorship W2798646183A5060815622 @default.
• W2798646183 hasBestOaLocation W27986461832 @default.
• W2798646183 hasConcept C119857082 @default.
• W2798646183 hasConcept C146849305 @default.
• W2798646183 hasConcept C153180895 @default.
• W2798646183 hasConcept C154945302 @default.
• W2798646183 hasConcept C159985019 @default.
• W2798646183 hasConcept C192562407 @default.
• W2798646183 hasConcept C204323151 @default.
• W2798646183 hasConcept C31972630 @default.
• W2798646183 hasConcept C41008148 @default.
• W2798646183 hasConcept C52102323 @default.
• W2798646183 hasConceptScore W2798646183C119857082 @default.
• W2798646183 hasConceptScore W2798646183C146849305 @default.
• W2798646183 hasConceptScore W2798646183C153180895 @default.
• W2798646183 hasConceptScore W2798646183C154945302 @default.
• W2798646183 hasConceptScore W2798646183C159985019 @default.
• W2798646183 hasConceptScore W2798646183C192562407 @default.
• W2798646183 hasConceptScore W2798646183C204323151 @default.
• W2798646183 hasConceptScore W2798646183C31972630 @default.
• W2798646183 hasConceptScore W2798646183C41008148 @default.
• W2798646183 hasConceptScore W2798646183C52102323 @default.
• W2798646183 hasLocation W27986461831 @default.
• W2798646183 hasLocation W27986461832 @default.
• W2798646183 hasOpenAccess W2798646183 @default.
• W2798646183 hasPrimaryLocation W27986461831 @default.
• W2798646183 hasRelatedWork W1968716783 @default.
• W2798646183 hasRelatedWork W2025164974 @default.
• W2798646183 hasRelatedWork W2128635338 @default.

• next