Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387222790> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4387222790 endingPage "1626" @default.
- W4387222790 startingPage "1621" @default.
- W4387222790 abstract "Human motion prediction has always been an interesting research topic in computer vision and robotics. It means forecasting human movements in the future conditioning on historical 3-dimensional human skeleton sequences. Existing predicting algorithms usually rely on extensive annotated or non-annotated motion capture data and are non-adaptive. This paper addresses the problem of few-frame human motion prediction, in the spirit of the recent progress on manifold learning. More precisely, our approach is based on the insight that achieving an accurate prediction relies on a sufficiently linear expression in the latent space from a few training data in observation space. To accomplish this, we propose Regressive Gaussian Process Latent Variable Model (RGPLVM) that introduces a novel regressive kernel function for the model training. By doing so, our model produces a linear mapping from the training data space to the latent space, while effectively transforming the prediction of human motion in physical space to the linear regression analysis in the latent space equivalent. The comparison with two learning motion prediction approaches (the state-of-the-art meta learning and the classical LSTM-3LR) demonstrate that our GPLVM significantly improves the prediction performance on various of actions in the small-sample size regime." @default.
- W4387222790 created "2023-10-01" @default.
- W4387222790 creator A5049714181 @default.
- W4387222790 creator A5057571052 @default.
- W4387222790 date "2023-10-01" @default.
- W4387222790 modified "2023-10-09" @default.
- W4387222790 title "Regressive Gaussian Process Latent Variable Model for Few-Frame Human Motion Prediction" @default.
- W4387222790 cites W1483019628 @default.
- W4387222790 cites W2120405375 @default.
- W4387222790 cites W2124609748 @default.
- W4387222790 cites W2133294540 @default.
- W4387222790 cites W2519882289 @default.
- W4387222790 cites W2594167370 @default.
- W4387222790 cites W2606517404 @default.
- W4387222790 cites W2756154119 @default.
- W4387222790 cites W2887280559 @default.
- W4387222790 cites W2894846593 @default.
- W4387222790 cites W2896588340 @default.
- W4387222790 cites W2963324990 @default.
- W4387222790 cites W2963548793 @default.
- W4387222790 cites W2964203186 @default.
- W4387222790 cites W2968760063 @default.
- W4387222790 cites W2974544900 @default.
- W4387222790 cites W2975420824 @default.
- W4387222790 cites W3035545045 @default.
- W4387222790 cites W3038458306 @default.
- W4387222790 cites W3041133507 @default.
- W4387222790 cites W3154934604 @default.
- W4387222790 cites W3163842339 @default.
- W4387222790 cites W3195823851 @default.
- W4387222790 cites W3198025804 @default.
- W4387222790 doi "https://doi.org/10.1587/transinf.2023pcp0001" @default.
- W4387222790 hasPublicationYear "2023" @default.
- W4387222790 type Work @default.
- W4387222790 citedByCount "0" @default.
- W4387222790 crossrefType "journal-article" @default.
- W4387222790 hasAuthorship W4387222790A5049714181 @default.
- W4387222790 hasAuthorship W4387222790A5057571052 @default.
- W4387222790 hasBestOaLocation W43872227901 @default.
- W4387222790 hasConcept C104114177 @default.
- W4387222790 hasConcept C119857082 @default.
- W4387222790 hasConcept C121332964 @default.
- W4387222790 hasConcept C126042441 @default.
- W4387222790 hasConcept C154945302 @default.
- W4387222790 hasConcept C163716315 @default.
- W4387222790 hasConcept C2986578859 @default.
- W4387222790 hasConcept C41008148 @default.
- W4387222790 hasConcept C51167844 @default.
- W4387222790 hasConcept C61326573 @default.
- W4387222790 hasConcept C62520636 @default.
- W4387222790 hasConcept C76155785 @default.
- W4387222790 hasConcept C81692654 @default.
- W4387222790 hasConceptScore W4387222790C104114177 @default.
- W4387222790 hasConceptScore W4387222790C119857082 @default.
- W4387222790 hasConceptScore W4387222790C121332964 @default.
- W4387222790 hasConceptScore W4387222790C126042441 @default.
- W4387222790 hasConceptScore W4387222790C154945302 @default.
- W4387222790 hasConceptScore W4387222790C163716315 @default.
- W4387222790 hasConceptScore W4387222790C2986578859 @default.
- W4387222790 hasConceptScore W4387222790C41008148 @default.
- W4387222790 hasConceptScore W4387222790C51167844 @default.
- W4387222790 hasConceptScore W4387222790C61326573 @default.
- W4387222790 hasConceptScore W4387222790C62520636 @default.
- W4387222790 hasConceptScore W4387222790C76155785 @default.
- W4387222790 hasConceptScore W4387222790C81692654 @default.
- W4387222790 hasIssue "10" @default.
- W4387222790 hasLocation W43872227901 @default.
- W4387222790 hasOpenAccess W4387222790 @default.
- W4387222790 hasPrimaryLocation W43872227901 @default.
- W4387222790 hasRelatedWork W2056958800 @default.
- W4387222790 hasRelatedWork W2169866437 @default.
- W4387222790 hasRelatedWork W2600092203 @default.
- W4387222790 hasRelatedWork W2803685231 @default.
- W4387222790 hasRelatedWork W2966696655 @default.
- W4387222790 hasRelatedWork W3134152097 @default.
- W4387222790 hasRelatedWork W4293503520 @default.
- W4387222790 hasRelatedWork W4300066510 @default.
- W4387222790 hasRelatedWork W4311388919 @default.
- W4387222790 hasRelatedWork W566010457 @default.
- W4387222790 hasVolume "E106.D" @default.
- W4387222790 isParatext "false" @default.
- W4387222790 isRetracted "false" @default.
- W4387222790 workType "article" @default.