Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952504680> ?p ?o ?g. }
- W2952504680 abstract "This paper introduces a new architecture for human pose estimation using a multi- layer convolutional network architecture and a modified learning technique that learns low-level features and higher-level weak spatial models. Unconstrained human pose estimation is one of the hardest problems in computer vision, and our new architecture and learning schema shows significant improvement over the current state-of-the-art results. The main contribution of this paper is showing, for the first time, that a specific variation of deep learning is able to outperform all existing traditional architectures on this task. The paper also discusses several lessons learned while researching alternatives, most notably, that it is possible to learn strong low-level feature detectors on features that might even just cover a few pixels in the image. Higher-level spatial models improve somewhat the overall result, but to a much lesser extent then expected. Many researchers previously argued that the kinematic structure and top-down information is crucial for this domain, but with our purely bottom up, and weak spatial model, we could improve other more complicated architectures that currently produce the best results. This mirrors what many other researchers, like those in the speech recognition, object recognition, and other domains have experienced." @default.
- W2952504680 created "2019-06-27" @default.
- W2952504680 creator A5019742155 @default.
- W2952504680 creator A5020328677 @default.
- W2952504680 creator A5034466911 @default.
- W2952504680 creator A5066924496 @default.
- W2952504680 creator A5080976060 @default.
- W2952504680 date "2013-12-27" @default.
- W2952504680 modified "2023-09-27" @default.
- W2952504680 title "Learning Human Pose Estimation Features with Convolutional Networks" @default.
- W2952504680 cites W104184427 @default.
- W2952504680 cites W1551519658 @default.
- W2952504680 cites W1904365287 @default.
- W2952504680 cites W1989191365 @default.
- W2952504680 cites W1997500560 @default.
- W2952504680 cites W2032481801 @default.
- W2952504680 cites W2034792058 @default.
- W2952504680 cites W2092146246 @default.
- W2952504680 cites W2099333815 @default.
- W2952504680 cites W2100526149 @default.
- W2952504680 cites W2112796928 @default.
- W2952504680 cites W2114663654 @default.
- W2952504680 cites W2120419212 @default.
- W2952504680 cites W2121341364 @default.
- W2952504680 cites W2122246689 @default.
- W2952504680 cites W2123503110 @default.
- W2952504680 cites W2124386111 @default.
- W2952504680 cites W2131263044 @default.
- W2952504680 cites W2137940226 @default.
- W2952504680 cites W2140235142 @default.
- W2952504680 cites W2152926413 @default.
- W2952504680 cites W2157939923 @default.
- W2952504680 cites W2158842374 @default.
- W2952504680 cites W2161969291 @default.
- W2952504680 cites W2166440240 @default.
- W2952504680 cites W2168356304 @default.
- W2952504680 cites W2169805405 @default.
- W2952504680 cites W2170837066 @default.
- W2952504680 cites W2172043283 @default.
- W2952504680 cites W2172156083 @default.
- W2952504680 cites W2535410496 @default.
- W2952504680 cites W2950212154 @default.
- W2952504680 cites W2952111767 @default.
- W2952504680 cites W3141021069 @default.
- W2952504680 cites W1993846356 @default.
- W2952504680 hasPublicationYear "2013" @default.
- W2952504680 type Work @default.
- W2952504680 sameAs 2952504680 @default.
- W2952504680 citedByCount "9" @default.
- W2952504680 countsByYear W29525046802014 @default.
- W2952504680 countsByYear W29525046802015 @default.
- W2952504680 countsByYear W29525046802016 @default.
- W2952504680 countsByYear W29525046802017 @default.
- W2952504680 countsByYear W29525046802018 @default.
- W2952504680 countsByYear W29525046802020 @default.
- W2952504680 countsByYear W29525046802021 @default.
- W2952504680 crossrefType "posted-content" @default.
- W2952504680 hasAuthorship W2952504680A5019742155 @default.
- W2952504680 hasAuthorship W2952504680A5020328677 @default.
- W2952504680 hasAuthorship W2952504680A5034466911 @default.
- W2952504680 hasAuthorship W2952504680A5066924496 @default.
- W2952504680 hasAuthorship W2952504680A5080976060 @default.
- W2952504680 hasConcept C108583219 @default.
- W2952504680 hasConcept C119857082 @default.
- W2952504680 hasConcept C121332964 @default.
- W2952504680 hasConcept C123657996 @default.
- W2952504680 hasConcept C138885662 @default.
- W2952504680 hasConcept C153180895 @default.
- W2952504680 hasConcept C154945302 @default.
- W2952504680 hasConcept C166957645 @default.
- W2952504680 hasConcept C205649164 @default.
- W2952504680 hasConcept C2776401178 @default.
- W2952504680 hasConcept C2778334786 @default.
- W2952504680 hasConcept C41008148 @default.
- W2952504680 hasConcept C41895202 @default.
- W2952504680 hasConcept C44870925 @default.
- W2952504680 hasConcept C52102323 @default.
- W2952504680 hasConcept C52146309 @default.
- W2952504680 hasConcept C59404180 @default.
- W2952504680 hasConcept C81363708 @default.
- W2952504680 hasConceptScore W2952504680C108583219 @default.
- W2952504680 hasConceptScore W2952504680C119857082 @default.
- W2952504680 hasConceptScore W2952504680C121332964 @default.
- W2952504680 hasConceptScore W2952504680C123657996 @default.
- W2952504680 hasConceptScore W2952504680C138885662 @default.
- W2952504680 hasConceptScore W2952504680C153180895 @default.
- W2952504680 hasConceptScore W2952504680C154945302 @default.
- W2952504680 hasConceptScore W2952504680C166957645 @default.
- W2952504680 hasConceptScore W2952504680C205649164 @default.
- W2952504680 hasConceptScore W2952504680C2776401178 @default.
- W2952504680 hasConceptScore W2952504680C2778334786 @default.
- W2952504680 hasConceptScore W2952504680C41008148 @default.
- W2952504680 hasConceptScore W2952504680C41895202 @default.
- W2952504680 hasConceptScore W2952504680C44870925 @default.
- W2952504680 hasConceptScore W2952504680C52102323 @default.
- W2952504680 hasConceptScore W2952504680C52146309 @default.
- W2952504680 hasConceptScore W2952504680C59404180 @default.
- W2952504680 hasConceptScore W2952504680C81363708 @default.
- W2952504680 hasLocation W29525046801 @default.
- W2952504680 hasOpenAccess W2952504680 @default.