FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2573854917> ?p ?o ?g. }

• W2573854917 endingPage "914" @default.
• W2573854917 startingPage "901" @default.
• W2573854917 abstract "Recovering 3D full-body human pose is a challenging problem with many applications. It has been successfully addressed by motion capture systems with body worn markers and multiple cameras. In this paper, we address the more challenging case of not only using a single camera but also not leveraging markers: going directly from 2D appearance to 3D geometry. Deep learning approaches have shown remarkable abilities to discriminatively learn 2D appearance features. The missing piece is how to integrate 2D, 3D, and temporal information to recover 3D geometry and account for the uncertainties arising from the discriminative model. We introduce a novel approach that treats 2D joint locations as latent variables whose uncertainty distributions are given by a deep fully convolutional neural network. The unknown 3D poses are modeled by a sparse representation and the 3D parameter estimates are realized via an Expectation-Maximization algorithm, where it is shown that the 2D joint location uncertainties can be conveniently marginalized out during inference. Extensive evaluation on benchmark datasets shows that the proposed approach achieves greater accuracy over state-of-the-art baselines. Notably, the proposed approach does not require synchronized 2D-3D data for training and is applicable to in-the-wild images, which is demonstrated with the MPII dataset." @default.
• W2573854917 created "2017-01-26" @default.
• W2573854917 creator A5004780312 @default.
• W2573854917 creator A5019738941 @default.
• W2573854917 creator A5048438237 @default.
• W2573854917 creator A5050660826 @default.
• W2573854917 creator A5052269532 @default.
• W2573854917 creator A5060815622 @default.
• W2573854917 date "2019-04-01" @default.
• W2573854917 modified "2023-10-14" @default.
• W2573854917 title "MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior" @default.
• W2573854917 cites W1903029394 @default.
• W2573854917 cites W1905368000 @default.
• W2573854917 cites W1943191679 @default.
• W2573854917 cites W1950149599 @default.
• W2573854917 cites W1955699725 @default.
• W2573854917 cites W1956126447 @default.
• W2573854917 cites W1994529670 @default.
• W2573854917 cites W1994804971 @default.
• W2573854917 cites W1997500560 @default.
• W2573854917 cites W2013397696 @default.
• W2573854917 cites W2018854916 @default.
• W2573854917 cites W2032682867 @default.
• W2573854917 cites W2038952578 @default.
• W2573854917 cites W2039262381 @default.
• W2573854917 cites W2045091010 @default.
• W2573854917 cites W2045659016 @default.
• W2573854917 cites W2071882725 @default.
• W2573854917 cites W2080873731 @default.
• W2573854917 cites W2088196373 @default.
• W2573854917 cites W2093949207 @default.
• W2573854917 cites W2101032778 @default.
• W2573854917 cites W2102813107 @default.
• W2573854917 cites W2105041273 @default.
• W2573854917 cites W2111446867 @default.
• W2573854917 cites W2111727626 @default.
• W2573854917 cites W2113325037 @default.
• W2573854917 cites W2118025528 @default.
• W2573854917 cites W2119350939 @default.
• W2573854917 cites W2121005842 @default.
• W2573854917 cites W2123503110 @default.
• W2573854917 cites W2124600577 @default.
• W2573854917 cites W2134704262 @default.
• W2573854917 cites W2146020220 @default.
• W2573854917 cites W2152926413 @default.
• W2573854917 cites W2157982431 @default.
• W2573854917 cites W2158866619 @default.
• W2573854917 cites W2162267096 @default.
• W2573854917 cites W2169738563 @default.
• W2573854917 cites W2171125807 @default.
• W2573854917 cites W2172156083 @default.
• W2573854917 cites W2207258529 @default.
• W2573854917 cites W2224625234 @default.
• W2573854917 cites W2256477790 @default.
• W2573854917 cites W2412442946 @default.
• W2573854917 cites W2515603221 @default.
• W2573854917 cites W2962729993 @default.
• W2573854917 cites W2963013806 @default.
• W2573854917 cites W2963592930 @default.
• W2573854917 cites W2963688992 @default.
• W2573854917 cites W48960680 @default.
• W2573854917 cites W602397586 @default.
• W2573854917 doi "https://doi.org/10.1109/tpami.2018.2816031" @default.
• W2573854917 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/29993801" @default.
• W2573854917 hasPublicationYear "2019" @default.
• W2573854917 type Work @default.
• W2573854917 sameAs 2573854917 @default.
• W2573854917 citedByCount "134" @default.
• W2573854917 countsByYear W25738549172017 @default.
• W2573854917 countsByYear W25738549172018 @default.
• W2573854917 countsByYear W25738549172019 @default.
• W2573854917 countsByYear W25738549172020 @default.
• W2573854917 countsByYear W25738549172021 @default.
• W2573854917 countsByYear W25738549172022 @default.
• W2573854917 countsByYear W25738549172023 @default.
• W2573854917 crossrefType "journal-article" @default.
• W2573854917 hasAuthorship W2573854917A5004780312 @default.
• W2573854917 hasAuthorship W2573854917A5019738941 @default.
• W2573854917 hasAuthorship W2573854917A5048438237 @default.
• W2573854917 hasAuthorship W2573854917A5050660826 @default.
• W2573854917 hasAuthorship W2573854917A5052269532 @default.
• W2573854917 hasAuthorship W2573854917A5060815622 @default.
• W2573854917 hasBestOaLocation W25738549172 @default.
• W2573854917 hasConcept C104114177 @default.
• W2573854917 hasConcept C108583219 @default.
• W2573854917 hasConcept C126255220 @default.
• W2573854917 hasConcept C13280743 @default.
• W2573854917 hasConcept C153180895 @default.
• W2573854917 hasConcept C154945302 @default.
• W2573854917 hasConcept C17744445 @default.
• W2573854917 hasConcept C185798385 @default.
• W2573854917 hasConcept C199539241 @default.
• W2573854917 hasConcept C205649164 @default.
• W2573854917 hasConcept C2776214188 @default.
• W2573854917 hasConcept C2776330181 @default.
• W2573854917 hasConcept C2776359362 @default.
• W2573854917 hasConcept C31972630 @default.
• W2573854917 hasConcept C33923547 @default.

• next