Matches in SemOpenAlex for { <https://semopenalex.org/work/W2967528476> ?p ?o ?g. }
- W2967528476 abstract "Representations of sequential data are commonly based on the assumption that observed sequences are realizations of an unknown underlying stochastic process, where the learning problem includes determination of the model parameters. In this context the model must be able to capture the multi-modal nature of the data, without blurring between modes. This property is essential for applications like trajectory prediction or human motion modeling. Towards this end, a neural network model for continuous-time stochastic processes usable for sequence prediction is proposed. The model is based on Mixture Density Networks using B'ezier curves with Gaussian random variables as control points (abbrev.: $mathcal{N}$-Curves). Key advantages of the model include the ability of generating smooth multi-mode predictions in a single inference step which reduces the need for Monte Carlo simulation, as required in many multi-step prediction models, based on state-of-the-art neural networks. Essential properties of the proposed approach are illustrated by several toy examples and the task of multi-step sequence prediction. Further, the model performance is evaluated on two real world use-cases, i.e. human trajectory prediction and human motion modeling, outperforming different state-of-the-art models." @default.
- W2967528476 created "2019-08-22" @default.
- W2967528476 creator A5000041406 @default.
- W2967528476 creator A5032146064 @default.
- W2967528476 creator A5052312893 @default.
- W2967528476 date "2019-08-12" @default.
- W2967528476 modified "2023-09-23" @default.
- W2967528476 title "Modeling continuous-time stochastic processes using $mathcal{N}$-Curve mixtures" @default.
- W2967528476 cites W1502922572 @default.
- W2967528476 cites W1506806321 @default.
- W2967528476 cites W1522237958 @default.
- W2967528476 cites W1531532259 @default.
- W2967528476 cites W1554663460 @default.
- W2967528476 cites W1719489212 @default.
- W2967528476 cites W1810943226 @default.
- W2967528476 cites W1959608418 @default.
- W2967528476 cites W2004463884 @default.
- W2967528476 cites W2026430219 @default.
- W2967528476 cites W2037629065 @default.
- W2967528476 cites W2095654324 @default.
- W2967528476 cites W2097545165 @default.
- W2967528476 cites W2099471712 @default.
- W2967528476 cites W2158164339 @default.
- W2967528476 cites W2166063021 @default.
- W2967528476 cites W2173351748 @default.
- W2967528476 cites W2179793346 @default.
- W2967528476 cites W2188365844 @default.
- W2967528476 cites W2424778531 @default.
- W2967528476 cites W2519586580 @default.
- W2967528476 cites W2595142274 @default.
- W2967528476 cites W2606554264 @default.
- W2967528476 cites W2735338621 @default.
- W2967528476 cites W2792764867 @default.
- W2967528476 cites W2793483732 @default.
- W2967528476 cites W2797857424 @default.
- W2967528476 cites W2892035503 @default.
- W2967528476 cites W2908959077 @default.
- W2967528476 cites W2948479456 @default.
- W2967528476 cites W2951266961 @default.
- W2967528476 cites W2962687116 @default.
- W2967528476 cites W2963001155 @default.
- W2967528476 cites W2963711523 @default.
- W2967528476 cites W2963760282 @default.
- W2967528476 cites W2963816519 @default.
- W2967528476 cites W2964059111 @default.
- W2967528476 cites W2964147651 @default.
- W2967528476 cites W2964203186 @default.
- W2967528476 cites W618401109 @default.
- W2967528476 cites W88520345 @default.
- W2967528476 hasPublicationYear "2019" @default.
- W2967528476 type Work @default.
- W2967528476 sameAs 2967528476 @default.
- W2967528476 citedByCount "0" @default.
- W2967528476 crossrefType "posted-content" @default.
- W2967528476 hasAuthorship W2967528476A5000041406 @default.
- W2967528476 hasAuthorship W2967528476A5032146064 @default.
- W2967528476 hasAuthorship W2967528476A5052312893 @default.
- W2967528476 hasConcept C105795698 @default.
- W2967528476 hasConcept C11413529 @default.
- W2967528476 hasConcept C119857082 @default.
- W2967528476 hasConcept C121332964 @default.
- W2967528476 hasConcept C1276947 @default.
- W2967528476 hasConcept C13662910 @default.
- W2967528476 hasConcept C151730666 @default.
- W2967528476 hasConcept C154945302 @default.
- W2967528476 hasConcept C163716315 @default.
- W2967528476 hasConcept C2776214188 @default.
- W2967528476 hasConcept C2778112365 @default.
- W2967528476 hasConcept C2779343474 @default.
- W2967528476 hasConcept C33923547 @default.
- W2967528476 hasConcept C41008148 @default.
- W2967528476 hasConcept C50644808 @default.
- W2967528476 hasConcept C54355233 @default.
- W2967528476 hasConcept C61326573 @default.
- W2967528476 hasConcept C62520636 @default.
- W2967528476 hasConcept C8272713 @default.
- W2967528476 hasConcept C86803240 @default.
- W2967528476 hasConceptScore W2967528476C105795698 @default.
- W2967528476 hasConceptScore W2967528476C11413529 @default.
- W2967528476 hasConceptScore W2967528476C119857082 @default.
- W2967528476 hasConceptScore W2967528476C121332964 @default.
- W2967528476 hasConceptScore W2967528476C1276947 @default.
- W2967528476 hasConceptScore W2967528476C13662910 @default.
- W2967528476 hasConceptScore W2967528476C151730666 @default.
- W2967528476 hasConceptScore W2967528476C154945302 @default.
- W2967528476 hasConceptScore W2967528476C163716315 @default.
- W2967528476 hasConceptScore W2967528476C2776214188 @default.
- W2967528476 hasConceptScore W2967528476C2778112365 @default.
- W2967528476 hasConceptScore W2967528476C2779343474 @default.
- W2967528476 hasConceptScore W2967528476C33923547 @default.
- W2967528476 hasConceptScore W2967528476C41008148 @default.
- W2967528476 hasConceptScore W2967528476C50644808 @default.
- W2967528476 hasConceptScore W2967528476C54355233 @default.
- W2967528476 hasConceptScore W2967528476C61326573 @default.
- W2967528476 hasConceptScore W2967528476C62520636 @default.
- W2967528476 hasConceptScore W2967528476C8272713 @default.
- W2967528476 hasConceptScore W2967528476C86803240 @default.
- W2967528476 hasOpenAccess W2967528476 @default.
- W2967528476 hasRelatedWork W1488285997 @default.
- W2967528476 hasRelatedWork W1968802878 @default.