FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3186468161> ?p ?o ?g. }

• W3186468161 endingPage "14" @default.
• W3186468161 startingPage "1" @default.
• W3186468161 abstract "Humans and animals can control their bodies to generate a wide range of motions via low-dimensional action signals representing high-level goals. As such, human bodies and faces are prime examples of active objects, which can affect their shape via an internal actuation mechanism. This paper explores the following proposition: given a training set of example poses of an active deformable object, can we learn a low-dimensional control space that could reproduce the training set and generalize to new poses? In contrast to popular machine learning methods for dimensionality reduction such as auto-encoders, we model our active objects in a physics-based way. We utilize a differentiable, quasistatic, physics-based simulation layer and combine it with a decoder-type neural network. Our differentiable physics layer naturally fits into deep learning frameworks and allows the decoder network to learn actuations that reach the desired poses after physics-based simulation. In contrast to modeling approaches where users build anatomical models from first principles, medical literature or medical imaging, we do not presume knowledge of the underlying musculature, but learn the structure and control of the actuation mechanism directly from the input data. We present a training paradigm and several scalability-oriented enhancements that allow us to train effectively while accommodating high-resolution volumetric models, with as many as a quarter million simulation elements. The prime demonstration of the efficacy of our example-driven modeling framework targets facial animation, where we train on a collection of input expressions while generalizing to unseen poses, drive detailed facial animation from sparse motion capture input, and facilitate expression sculpting via direct manipulation." @default.
• W3186468161 created "2021-08-02" @default.
• W3186468161 creator A5013174582 @default.
• W3186468161 creator A5016067326 @default.
• W3186468161 creator A5027214378 @default.
• W3186468161 creator A5028216970 @default.
• W3186468161 creator A5032464233 @default.
• W3186468161 creator A5089697513 @default.
• W3186468161 date "2021-07-19" @default.
• W3186468161 modified "2023-10-14" @default.
• W3186468161 title "Learning active quasistatic physics-based models from data" @default.
• W3186468161 cites W1588539311 @default.
• W3186468161 cites W1969960922 @default.
• W3186468161 cites W1985117280 @default.
• W3186468161 cites W2018231630 @default.
• W3186468161 cites W2022890264 @default.
• W3186468161 cites W2024243735 @default.
• W3186468161 cites W2035104324 @default.
• W3186468161 cites W2041393713 @default.
• W3186468161 cites W2046090405 @default.
• W3186468161 cites W2055035360 @default.
• W3186468161 cites W2055819391 @default.
• W3186468161 cites W2067910404 @default.
• W3186468161 cites W2118080926 @default.
• W3186468161 cites W2134389879 @default.
• W3186468161 cites W2156410578 @default.
• W3186468161 cites W2237250383 @default.
• W3186468161 cites W2738703359 @default.
• W3186468161 cites W2739069563 @default.
• W3186468161 cites W2739193376 @default.
• W3186468161 cites W2799116135 @default.
• W3186468161 cites W2811426698 @default.
• W3186468161 cites W2957926190 @default.
• W3186468161 cites W2965639322 @default.
• W3186468161 cites W2966651785 @default.
• W3186468161 cites W2968042644 @default.
• W3186468161 cites W2979282880 @default.
• W3186468161 cites W2985010153 @default.
• W3186468161 cites W2988986133 @default.
• W3186468161 cites W3015873132 @default.
• W3186468161 cites W3048366741 @default.
• W3186468161 cites W3048381483 @default.
• W3186468161 cites W3108094035 @default.
• W3186468161 cites W3109154889 @default.
• W3186468161 cites W3109952375 @default.
• W3186468161 cites W3138143451 @default.
• W3186468161 cites W3214811308 @default.
• W3186468161 doi "https://doi.org/10.1145/3450626.3459883" @default.
• W3186468161 hasPublicationYear "2021" @default.
• W3186468161 type Work @default.
• W3186468161 sameAs 3186468161 @default.
• W3186468161 citedByCount "7" @default.
• W3186468161 countsByYear W31864681612022 @default.
• W3186468161 countsByYear W31864681612023 @default.
• W3186468161 crossrefType "journal-article" @default.
• W3186468161 hasAuthorship W3186468161A5013174582 @default.
• W3186468161 hasAuthorship W3186468161A5016067326 @default.
• W3186468161 hasAuthorship W3186468161A5027214378 @default.
• W3186468161 hasAuthorship W3186468161A5028216970 @default.
• W3186468161 hasAuthorship W3186468161A5032464233 @default.
• W3186468161 hasAuthorship W3186468161A5089697513 @default.
• W3186468161 hasConcept C108583219 @default.
• W3186468161 hasConcept C111030470 @default.
• W3186468161 hasConcept C154945302 @default.
• W3186468161 hasConcept C177264268 @default.
• W3186468161 hasConcept C190390380 @default.
• W3186468161 hasConcept C199360897 @default.
• W3186468161 hasConcept C41008148 @default.
• W3186468161 hasConcept C48044578 @default.
• W3186468161 hasConcept C50644808 @default.
• W3186468161 hasConcept C77088390 @default.
• W3186468161 hasConceptScore W3186468161C108583219 @default.
• W3186468161 hasConceptScore W3186468161C111030470 @default.
• W3186468161 hasConceptScore W3186468161C154945302 @default.
• W3186468161 hasConceptScore W3186468161C177264268 @default.
• W3186468161 hasConceptScore W3186468161C190390380 @default.
• W3186468161 hasConceptScore W3186468161C199360897 @default.
• W3186468161 hasConceptScore W3186468161C41008148 @default.
• W3186468161 hasConceptScore W3186468161C48044578 @default.
• W3186468161 hasConceptScore W3186468161C50644808 @default.
• W3186468161 hasConceptScore W3186468161C77088390 @default.
• W3186468161 hasIssue "4" @default.
• W3186468161 hasLocation W31864681611 @default.
• W3186468161 hasOpenAccess W3186468161 @default.
• W3186468161 hasPrimaryLocation W31864681611 @default.
• W3186468161 hasRelatedWork W2353505378 @default.
• W3186468161 hasRelatedWork W2355801475 @default.
• W3186468161 hasRelatedWork W2389214306 @default.
• W3186468161 hasRelatedWork W2561617217 @default.
• W3186468161 hasRelatedWork W3097449145 @default.
• W3186468161 hasRelatedWork W4206659427 @default.
• W3186468161 hasRelatedWork W4235240664 @default.
• W3186468161 hasRelatedWork W4294811468 @default.
• W3186468161 hasRelatedWork W4296209631 @default.
• W3186468161 hasRelatedWork W4375867731 @default.
• W3186468161 hasVolume "40" @default.
• W3186468161 isParatext "false" @default.
• W3186468161 isRetracted "false" @default.

• next