Matches in SemOpenAlex for { <https://semopenalex.org/work/W2944133030> ?p ?o ?g. }
- W2944133030 endingPage "56408" @default.
- W2944133030 startingPage "56389" @default.
- W2944133030 abstract "In this paper, we propose a deep generative model named multimodal conditional deep belief network (MCDBN) for cross-modal learning of 3D motion data and their non-injective 2D projections on the image plane. This model has a three-sectional structure, which learns conditional probability distribution of 3D motion data given 2D projections. Two distinct conditional deep belief networks (CDBNs), encode the real-valued spatiotemporal patterns of 2D and 3D motion time series captured from the subjects' movements into compact representations. The third part includes a multimodal restricted Boltzmann machine which in the training process, learns the relationship between the compact representations of data modalities by variation information criteria. As a result, conditioned on a 2D motion data obtained from a video, MCDBN can regenerate 3D motion data in the generation phase. We introduce Pearson correlation coefficient of the ground truth and the regenerated the motion signals as a new evaluation metric in motion reconstruction problems. The model is trained with human motion capture data and the results show that the real and the regenerated signals are highly correlated, which means the model can reproduce the dynamical patterns of the motion accurately." @default.
- W2944133030 created "2019-05-16" @default.
- W2944133030 creator A5001384682 @default.
- W2944133030 creator A5024741305 @default.
- W2944133030 date "2019-01-01" @default.
- W2944133030 modified "2023-09-30" @default.
- W2944133030 title "3D Motion Reconstruction From 2D Motion Data Using Multimodal Conditional Deep Belief Network" @default.
- W2944133030 cites W1993882792 @default.
- W2944133030 cites W2007943671 @default.
- W2944133030 cites W2012706599 @default.
- W2944133030 cites W2013640163 @default.
- W2944133030 cites W2034792058 @default.
- W2944133030 cites W2042492924 @default.
- W2944133030 cites W2086509056 @default.
- W2944133030 cites W2088335308 @default.
- W2944133030 cites W2088998933 @default.
- W2944133030 cites W2100495367 @default.
- W2944133030 cites W2101032778 @default.
- W2944133030 cites W2115096495 @default.
- W2944133030 cites W2124609748 @default.
- W2944133030 cites W2129070834 @default.
- W2944133030 cites W2136922672 @default.
- W2944133030 cites W2150529939 @default.
- W2944133030 cites W2162911105 @default.
- W2944133030 cites W2169738563 @default.
- W2944133030 cites W2256477790 @default.
- W2944133030 cites W2295038166 @default.
- W2944133030 cites W2433636802 @default.
- W2944133030 cites W2474638510 @default.
- W2944133030 cites W2519469348 @default.
- W2944133030 cites W2554247908 @default.
- W2944133030 cites W2573854917 @default.
- W2944133030 cites W2583372902 @default.
- W2944133030 cites W2588127243 @default.
- W2944133030 cites W2593469669 @default.
- W2944133030 cites W2758778552 @default.
- W2944133030 cites W2894766094 @default.
- W2944133030 cites W2962962024 @default.
- W2944133030 cites W2963192057 @default.
- W2944133030 cites W2963202339 @default.
- W2944133030 cites W4231109964 @default.
- W2944133030 doi "https://doi.org/10.1109/access.2019.2904117" @default.
- W2944133030 hasPublicationYear "2019" @default.
- W2944133030 type Work @default.
- W2944133030 sameAs 2944133030 @default.
- W2944133030 citedByCount "2" @default.
- W2944133030 countsByYear W29441330302022 @default.
- W2944133030 countsByYear W29441330302023 @default.
- W2944133030 crossrefType "journal-article" @default.
- W2944133030 hasAuthorship W2944133030A5001384682 @default.
- W2944133030 hasAuthorship W2944133030A5024741305 @default.
- W2944133030 hasBestOaLocation W29441330301 @default.
- W2944133030 hasConcept C10161872 @default.
- W2944133030 hasConcept C104114177 @default.
- W2944133030 hasConcept C105795698 @default.
- W2944133030 hasConcept C108583219 @default.
- W2944133030 hasConcept C146849305 @default.
- W2944133030 hasConcept C153180895 @default.
- W2944133030 hasConcept C154945302 @default.
- W2944133030 hasConcept C162324750 @default.
- W2944133030 hasConcept C167966045 @default.
- W2944133030 hasConcept C176217482 @default.
- W2944133030 hasConcept C192576344 @default.
- W2944133030 hasConcept C21547014 @default.
- W2944133030 hasConcept C31972630 @default.
- W2944133030 hasConcept C33923547 @default.
- W2944133030 hasConcept C39890363 @default.
- W2944133030 hasConcept C41008148 @default.
- W2944133030 hasConcept C43555835 @default.
- W2944133030 hasConcept C48007421 @default.
- W2944133030 hasConcept C97385483 @default.
- W2944133030 hasConceptScore W2944133030C10161872 @default.
- W2944133030 hasConceptScore W2944133030C104114177 @default.
- W2944133030 hasConceptScore W2944133030C105795698 @default.
- W2944133030 hasConceptScore W2944133030C108583219 @default.
- W2944133030 hasConceptScore W2944133030C146849305 @default.
- W2944133030 hasConceptScore W2944133030C153180895 @default.
- W2944133030 hasConceptScore W2944133030C154945302 @default.
- W2944133030 hasConceptScore W2944133030C162324750 @default.
- W2944133030 hasConceptScore W2944133030C167966045 @default.
- W2944133030 hasConceptScore W2944133030C176217482 @default.
- W2944133030 hasConceptScore W2944133030C192576344 @default.
- W2944133030 hasConceptScore W2944133030C21547014 @default.
- W2944133030 hasConceptScore W2944133030C31972630 @default.
- W2944133030 hasConceptScore W2944133030C33923547 @default.
- W2944133030 hasConceptScore W2944133030C39890363 @default.
- W2944133030 hasConceptScore W2944133030C41008148 @default.
- W2944133030 hasConceptScore W2944133030C43555835 @default.
- W2944133030 hasConceptScore W2944133030C48007421 @default.
- W2944133030 hasConceptScore W2944133030C97385483 @default.
- W2944133030 hasLocation W29441330301 @default.
- W2944133030 hasLocation W29441330302 @default.
- W2944133030 hasLocation W29441330303 @default.
- W2944133030 hasOpenAccess W2944133030 @default.
- W2944133030 hasPrimaryLocation W29441330301 @default.
- W2944133030 hasRelatedWork W2096175171 @default.
- W2944133030 hasRelatedWork W2118983851 @default.
- W2944133030 hasRelatedWork W2240647871 @default.