Matches in SemOpenAlex for { <https://semopenalex.org/work/W3036969905> ?p ?o ?g. }
- W3036969905 abstract "Monocular image-based three-dimensional (3-D) human pose recovery aims to retrieve 3-D poses using the corresponding two-dimensional image features. Therefore, the pose recovery performance highly depends on the image representations. We propose a multispectral embedding-based deep neural network (MSEDNN) to automatically obtain the most discriminative features from multiple deep convolutional neural networks and then embed their penultimate fully connected layers into a low-dimensional manifold. This compact manifold can explore not only the optimum output from multiple deep networks but also the complementary properties of them. Furthermore, the distribution of each hierarchy discriminative manifold is sufficiently smooth so that the training process of our MSEDNN can be effectively implemented only using few labeled data. Our proposed network contains a body joint detector and a human pose regressor that are jointly trained. Extensive experiments conducted on four databases show that our proposed MSEDNN can achieve the best recovery performance compared with the state-of-the-art methods." @default.
- W3036969905 created "2020-06-25" @default.
- W3036969905 creator A5006414413 @default.
- W3036969905 creator A5036476484 @default.
- W3036969905 date "2018-01-31" @default.
- W3036969905 modified "2023-09-27" @default.
- W3036969905 title "Multispectral embedding-based deep neural network for three-dimensional human pose recovery" @default.
- W3036969905 cites W1504905707 @default.
- W3036969905 cites W1943191679 @default.
- W3036969905 cites W1976948919 @default.
- W3036969905 cites W1980768270 @default.
- W3036969905 cites W1994508094 @default.
- W3036969905 cites W1996478295 @default.
- W3036969905 cites W2013627758 @default.
- W3036969905 cites W2022060071 @default.
- W3036969905 cites W2030565780 @default.
- W3036969905 cites W2078224158 @default.
- W3036969905 cites W2079084210 @default.
- W3036969905 cites W2083006716 @default.
- W3036969905 cites W2083623216 @default.
- W3036969905 cites W2086482135 @default.
- W3036969905 cites W2086698077 @default.
- W3036969905 cites W2092817461 @default.
- W3036969905 cites W2099333815 @default.
- W3036969905 cites W2101032778 @default.
- W3036969905 cites W2108069432 @default.
- W3036969905 cites W2111986959 @default.
- W3036969905 cites W2113325037 @default.
- W3036969905 cites W2119350939 @default.
- W3036969905 cites W2123503110 @default.
- W3036969905 cites W2125085157 @default.
- W3036969905 cites W2126314688 @default.
- W3036969905 cites W2128271252 @default.
- W3036969905 cites W2131583851 @default.
- W3036969905 cites W2132914434 @default.
- W3036969905 cites W2141125852 @default.
- W3036969905 cites W2152829748 @default.
- W3036969905 cites W2154660553 @default.
- W3036969905 cites W2160540580 @default.
- W3036969905 cites W2166782149 @default.
- W3036969905 cites W2166815260 @default.
- W3036969905 cites W2785439749 @default.
- W3036969905 cites W3098217967 @default.
- W3036969905 cites W4249407496 @default.
- W3036969905 doi "https://doi.org/10.1117/1.oe.57.1.013107" @default.
- W3036969905 hasPublicationYear "2018" @default.
- W3036969905 type Work @default.
- W3036969905 sameAs 3036969905 @default.
- W3036969905 citedByCount "1" @default.
- W3036969905 countsByYear W30369699052020 @default.
- W3036969905 crossrefType "journal-article" @default.
- W3036969905 hasAuthorship W3036969905A5006414413 @default.
- W3036969905 hasAuthorship W3036969905A5036476484 @default.
- W3036969905 hasConcept C108583219 @default.
- W3036969905 hasConcept C127413603 @default.
- W3036969905 hasConcept C153180895 @default.
- W3036969905 hasConcept C154945302 @default.
- W3036969905 hasConcept C173163844 @default.
- W3036969905 hasConcept C31972630 @default.
- W3036969905 hasConcept C41008148 @default.
- W3036969905 hasConcept C41608201 @default.
- W3036969905 hasConcept C50644808 @default.
- W3036969905 hasConcept C529865628 @default.
- W3036969905 hasConcept C65909025 @default.
- W3036969905 hasConcept C78519656 @default.
- W3036969905 hasConcept C81363708 @default.
- W3036969905 hasConcept C97931131 @default.
- W3036969905 hasConceptScore W3036969905C108583219 @default.
- W3036969905 hasConceptScore W3036969905C127413603 @default.
- W3036969905 hasConceptScore W3036969905C153180895 @default.
- W3036969905 hasConceptScore W3036969905C154945302 @default.
- W3036969905 hasConceptScore W3036969905C173163844 @default.
- W3036969905 hasConceptScore W3036969905C31972630 @default.
- W3036969905 hasConceptScore W3036969905C41008148 @default.
- W3036969905 hasConceptScore W3036969905C41608201 @default.
- W3036969905 hasConceptScore W3036969905C50644808 @default.
- W3036969905 hasConceptScore W3036969905C529865628 @default.
- W3036969905 hasConceptScore W3036969905C65909025 @default.
- W3036969905 hasConceptScore W3036969905C78519656 @default.
- W3036969905 hasConceptScore W3036969905C81363708 @default.
- W3036969905 hasConceptScore W3036969905C97931131 @default.
- W3036969905 hasLocation W30369699051 @default.
- W3036969905 hasOpenAccess W3036969905 @default.
- W3036969905 hasPrimaryLocation W30369699051 @default.
- W3036969905 hasRelatedWork W1593727536 @default.
- W3036969905 hasRelatedWork W1905368000 @default.
- W3036969905 hasRelatedWork W2612319427 @default.
- W3036969905 hasRelatedWork W2765980167 @default.
- W3036969905 hasRelatedWork W2777223338 @default.
- W3036969905 hasRelatedWork W2793326274 @default.
- W3036969905 hasRelatedWork W2897107362 @default.
- W3036969905 hasRelatedWork W2897284294 @default.
- W3036969905 hasRelatedWork W2900273708 @default.
- W3036969905 hasRelatedWork W2938922982 @default.
- W3036969905 hasRelatedWork W2943887089 @default.
- W3036969905 hasRelatedWork W2965210785 @default.
- W3036969905 hasRelatedWork W3001997710 @default.
- W3036969905 hasRelatedWork W3013413160 @default.
- W3036969905 hasRelatedWork W3037982482 @default.
- W3036969905 hasRelatedWork W3112982116 @default.