Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312894597> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4312894597 endingPage "18" @default.
- W4312894597 startingPage "1" @default.
- W4312894597 abstract "We present a learning-based approach for generating 3D facial animations with the motion style of a specific subject from arbitrary audio inputs. The subject style is learned from a video clip (1-2 minutes) either downloaded from the Internet or captured through an ordinary camera. Traditional methods often require many hours of the subject's video to learn a robust audio-driven model and are thus unsuitable for this task. Recent research efforts aim to train a model from video collections of a few subjects but ignore the discrimination between the subject style and underlying speech content within facial motions, leading to inaccurate style or articulation. To solve the problem, we propose a novel framework that disentangles subject-specific style and speech content from facial motions. The disentanglement is enabled by two novel training mechanisms. One is two-pass style swapping between two random subjects, and the other is joint training of the decomposition network and audio-to-motion network with a shared decoder. After training, the disentangled style is combined with arbitrary audio inputs to generate stylized audio-driven 3D facial animations. Compared with start-of-the-art methods, our approach achieves better results qualitatively and quantitatively, especially in difficult cases like bilabial plosive and bilabial nasal phonemes." @default.
- W4312894597 created "2023-01-05" @default.
- W4312894597 creator A5004008347 @default.
- W4312894597 creator A5014397128 @default.
- W4312894597 creator A5032863170 @default.
- W4312894597 creator A5060286507 @default.
- W4312894597 date "2022-01-01" @default.
- W4312894597 modified "2023-09-27" @default.
- W4312894597 title "Personalized Audio-Driven 3D Facial Animation Via Style-Content Disentanglement" @default.
- W4312894597 doi "https://doi.org/10.1109/tvcg.2022.3230541" @default.
- W4312894597 hasPublicationYear "2022" @default.
- W4312894597 type Work @default.
- W4312894597 citedByCount "0" @default.
- W4312894597 crossrefType "journal-article" @default.
- W4312894597 hasAuthorship W4312894597A5004008347 @default.
- W4312894597 hasAuthorship W4312894597A5014397128 @default.
- W4312894597 hasAuthorship W4312894597A5032863170 @default.
- W4312894597 hasAuthorship W4312894597A5060286507 @default.
- W4312894597 hasConcept C104114177 @default.
- W4312894597 hasConcept C121684516 @default.
- W4312894597 hasConcept C127220857 @default.
- W4312894597 hasConcept C138591656 @default.
- W4312894597 hasConcept C13895895 @default.
- W4312894597 hasConcept C154945302 @default.
- W4312894597 hasConcept C160372630 @default.
- W4312894597 hasConcept C161191863 @default.
- W4312894597 hasConcept C166957645 @default.
- W4312894597 hasConcept C17744445 @default.
- W4312894597 hasConcept C199539241 @default.
- W4312894597 hasConcept C2776445246 @default.
- W4312894597 hasConcept C2777855551 @default.
- W4312894597 hasConcept C2779337067 @default.
- W4312894597 hasConcept C28490314 @default.
- W4312894597 hasConcept C41008148 @default.
- W4312894597 hasConcept C49774154 @default.
- W4312894597 hasConcept C502989409 @default.
- W4312894597 hasConcept C64922751 @default.
- W4312894597 hasConcept C69369342 @default.
- W4312894597 hasConcept C94625758 @default.
- W4312894597 hasConcept C95457728 @default.
- W4312894597 hasConceptScore W4312894597C104114177 @default.
- W4312894597 hasConceptScore W4312894597C121684516 @default.
- W4312894597 hasConceptScore W4312894597C127220857 @default.
- W4312894597 hasConceptScore W4312894597C138591656 @default.
- W4312894597 hasConceptScore W4312894597C13895895 @default.
- W4312894597 hasConceptScore W4312894597C154945302 @default.
- W4312894597 hasConceptScore W4312894597C160372630 @default.
- W4312894597 hasConceptScore W4312894597C161191863 @default.
- W4312894597 hasConceptScore W4312894597C166957645 @default.
- W4312894597 hasConceptScore W4312894597C17744445 @default.
- W4312894597 hasConceptScore W4312894597C199539241 @default.
- W4312894597 hasConceptScore W4312894597C2776445246 @default.
- W4312894597 hasConceptScore W4312894597C2777855551 @default.
- W4312894597 hasConceptScore W4312894597C2779337067 @default.
- W4312894597 hasConceptScore W4312894597C28490314 @default.
- W4312894597 hasConceptScore W4312894597C41008148 @default.
- W4312894597 hasConceptScore W4312894597C49774154 @default.
- W4312894597 hasConceptScore W4312894597C502989409 @default.
- W4312894597 hasConceptScore W4312894597C64922751 @default.
- W4312894597 hasConceptScore W4312894597C69369342 @default.
- W4312894597 hasConceptScore W4312894597C94625758 @default.
- W4312894597 hasConceptScore W4312894597C95457728 @default.
- W4312894597 hasLocation W43128945971 @default.
- W4312894597 hasLocation W43128945972 @default.
- W4312894597 hasOpenAccess W4312894597 @default.
- W4312894597 hasPrimaryLocation W43128945971 @default.
- W4312894597 hasRelatedWork W2011968511 @default.
- W4312894597 hasRelatedWork W2128657342 @default.
- W4312894597 hasRelatedWork W2144023833 @default.
- W4312894597 hasRelatedWork W2158197328 @default.
- W4312894597 hasRelatedWork W2188834982 @default.
- W4312894597 hasRelatedWork W2985556488 @default.
- W4312894597 hasRelatedWork W3004910051 @default.
- W4312894597 hasRelatedWork W3169129874 @default.
- W4312894597 hasRelatedWork W4206157754 @default.
- W4312894597 hasRelatedWork W4206511020 @default.
- W4312894597 isParatext "false" @default.
- W4312894597 isRetracted "false" @default.
- W4312894597 workType "article" @default.