Matches in SemOpenAlex for { <https://semopenalex.org/work/W2079846689> ?p ?o ?g. }
- W2079846689 abstract "We present a novel method for accurate marker-less capture of articulated skeleton motion of several subjects in general scenes, indoors and outdoors, even from input filmed with as few as two cameras. Our approach unites a discriminative image-based joint detection method with a model-based generative motion tracking algorithm through a combined pose optimization energy. The discriminative part-based pose detection method, implemented using Convolutional Networks (ConvNet), estimates unary potentials for each joint of a kinematic skeleton model. These unary potentials are used to probabilistically extract pose constraints for tracking by using weighted sampling from a pose posterior guided by the model. In the final energy, these constraints are combined with an appearance-based model-to-image similarity term. Poses can be computed very efficiently using iterative local optimization, as ConvNet detection is fast, and our formulation yields a combined pose estimation energy with analytic derivatives. In combination, this enables to track full articulated joint angles at state-of-the-art accuracy and temporal stability with a very low number of cameras." @default.
- W2079846689 created "2016-06-24" @default.
- W2079846689 creator A5010680659 @default.
- W2079846689 creator A5019742155 @default.
- W2079846689 creator A5020328677 @default.
- W2079846689 creator A5020664641 @default.
- W2079846689 creator A5037151839 @default.
- W2079846689 creator A5051534545 @default.
- W2079846689 creator A5066924496 @default.
- W2079846689 creator A5073861650 @default.
- W2079846689 creator A5080976060 @default.
- W2079846689 date "2015-06-01" @default.
- W2079846689 modified "2023-09-25" @default.
- W2079846689 title "Efficient ConvNet-based marker-less motion capture in general scenes with a low number of cameras" @default.
- W2079846689 cites W1508437923 @default.
- W2079846689 cites W1975961009 @default.
- W2079846689 cites W1994529670 @default.
- W2079846689 cites W2008009569 @default.
- W2079846689 cites W2009647132 @default.
- W2079846689 cites W2014905483 @default.
- W2079846689 cites W2026753976 @default.
- W2079846689 cites W2030536784 @default.
- W2079846689 cites W2032481801 @default.
- W2079846689 cites W2045798786 @default.
- W2079846689 cites W2071882725 @default.
- W2079846689 cites W2080873731 @default.
- W2079846689 cites W2092146246 @default.
- W2079846689 cites W2099333815 @default.
- W2079846689 cites W2110645484 @default.
- W2079846689 cites W2112324691 @default.
- W2079846689 cites W2112796928 @default.
- W2079846689 cites W2113325037 @default.
- W2079846689 cites W2119350939 @default.
- W2079846689 cites W2127689830 @default.
- W2079846689 cites W2128271252 @default.
- W2079846689 cites W2131263044 @default.
- W2079846689 cites W2135826343 @default.
- W2079846689 cites W2143478373 @default.
- W2079846689 cites W2143487029 @default.
- W2079846689 cites W2146506577 @default.
- W2079846689 cites W2168415715 @default.
- W2079846689 cites W2169738563 @default.
- W2079846689 cites W2171125807 @default.
- W2079846689 cites W2172192658 @default.
- W2079846689 cites W2535410496 @default.
- W2079846689 cites W3141038539 @default.
- W2079846689 cites W4205409207 @default.
- W2079846689 doi "https://doi.org/10.1109/cvpr.2015.7299005" @default.
- W2079846689 hasPublicationYear "2015" @default.
- W2079846689 type Work @default.
- W2079846689 sameAs 2079846689 @default.
- W2079846689 citedByCount "132" @default.
- W2079846689 countsByYear W20798466892015 @default.
- W2079846689 countsByYear W20798466892016 @default.
- W2079846689 countsByYear W20798466892017 @default.
- W2079846689 countsByYear W20798466892018 @default.
- W2079846689 countsByYear W20798466892019 @default.
- W2079846689 countsByYear W20798466892020 @default.
- W2079846689 countsByYear W20798466892021 @default.
- W2079846689 countsByYear W20798466892022 @default.
- W2079846689 countsByYear W20798466892023 @default.
- W2079846689 crossrefType "proceedings-article" @default.
- W2079846689 hasAuthorship W2079846689A5010680659 @default.
- W2079846689 hasAuthorship W2079846689A5019742155 @default.
- W2079846689 hasAuthorship W2079846689A5020328677 @default.
- W2079846689 hasAuthorship W2079846689A5020664641 @default.
- W2079846689 hasAuthorship W2079846689A5037151839 @default.
- W2079846689 hasAuthorship W2079846689A5051534545 @default.
- W2079846689 hasAuthorship W2079846689A5066924496 @default.
- W2079846689 hasAuthorship W2079846689A5073861650 @default.
- W2079846689 hasAuthorship W2079846689A5080976060 @default.
- W2079846689 hasBestOaLocation W20798466892 @default.
- W2079846689 hasConcept C10161872 @default.
- W2079846689 hasConcept C104114177 @default.
- W2079846689 hasConcept C114614502 @default.
- W2079846689 hasConcept C121332964 @default.
- W2079846689 hasConcept C153180895 @default.
- W2079846689 hasConcept C154945302 @default.
- W2079846689 hasConcept C15744967 @default.
- W2079846689 hasConcept C19417346 @default.
- W2079846689 hasConcept C2775936607 @default.
- W2079846689 hasConcept C31972630 @default.
- W2079846689 hasConcept C33923547 @default.
- W2079846689 hasConcept C39920418 @default.
- W2079846689 hasConcept C41008148 @default.
- W2079846689 hasConcept C48007421 @default.
- W2079846689 hasConcept C52102323 @default.
- W2079846689 hasConcept C74650414 @default.
- W2079846689 hasConcept C78023250 @default.
- W2079846689 hasConcept C81363708 @default.
- W2079846689 hasConcept C97931131 @default.
- W2079846689 hasConceptScore W2079846689C10161872 @default.
- W2079846689 hasConceptScore W2079846689C104114177 @default.
- W2079846689 hasConceptScore W2079846689C114614502 @default.
- W2079846689 hasConceptScore W2079846689C121332964 @default.
- W2079846689 hasConceptScore W2079846689C153180895 @default.
- W2079846689 hasConceptScore W2079846689C154945302 @default.
- W2079846689 hasConceptScore W2079846689C15744967 @default.
- W2079846689 hasConceptScore W2079846689C19417346 @default.
- W2079846689 hasConceptScore W2079846689C2775936607 @default.