Matches in SemOpenAlex for { <https://semopenalex.org/work/W4307788176> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4307788176 abstract "Text-to-motion generation is an emerging and challenging problem, which aims to synthesize motion with the same semantics as the input text. However, due to the lack of diverse labeled training data, most approaches either limit to specific types of text annotations or require online optimizations to cater to the texts during inference at the cost of efficiency and stability. In this paper, we investigate offline open-vocabulary text-to-motion generation in a zero-shot learning manner that neither requires paired training data nor extra online optimization to adapt for unseen texts. Inspired by the prompt learning in NLP, we pretrain a motion generator that learns to reconstruct the full motion from the masked motion. During inference, instead of changing the motion generator, our method reformulates the input text into a masked motion as the prompt for the motion generator to ``reconstruct'' the motion. In constructing the prompt, the unmasked poses of the prompt are synthesized by a text-to-pose generator. To supervise the optimization of the text-to-pose generator, we propose the first text-pose alignment model for measuring the alignment between texts and 3D poses. And to prevent the pose generator from overfitting to limited training texts, we further propose a novel wordless training mechanism that optimizes the text-to-pose generator without any training texts. The comprehensive experimental results show that our method obtains a significant improvement against the baseline methods. The code is available at https://github.com/junfanlin/oohmg." @default.
- W4307788176 created "2022-11-05" @default.
- W4307788176 creator A5007186226 @default.
- W4307788176 creator A5038083485 @default.
- W4307788176 creator A5042117275 @default.
- W4307788176 creator A5042965510 @default.
- W4307788176 creator A5047455588 @default.
- W4307788176 creator A5058965019 @default.
- W4307788176 creator A5072909513 @default.
- W4307788176 date "2022-10-28" @default.
- W4307788176 modified "2023-10-16" @default.
- W4307788176 title "Being Comes from Not-being: Open-vocabulary Text-to-Motion Generation with Wordless Training" @default.
- W4307788176 doi "https://doi.org/10.48550/arxiv.2210.15929" @default.
- W4307788176 hasPublicationYear "2022" @default.
- W4307788176 type Work @default.
- W4307788176 citedByCount "0" @default.
- W4307788176 crossrefType "posted-content" @default.
- W4307788176 hasAuthorship W4307788176A5007186226 @default.
- W4307788176 hasAuthorship W4307788176A5038083485 @default.
- W4307788176 hasAuthorship W4307788176A5042117275 @default.
- W4307788176 hasAuthorship W4307788176A5042965510 @default.
- W4307788176 hasAuthorship W4307788176A5047455588 @default.
- W4307788176 hasAuthorship W4307788176A5058965019 @default.
- W4307788176 hasAuthorship W4307788176A5072909513 @default.
- W4307788176 hasBestOaLocation W43077881761 @default.
- W4307788176 hasConcept C104114177 @default.
- W4307788176 hasConcept C121332964 @default.
- W4307788176 hasConcept C138885662 @default.
- W4307788176 hasConcept C154945302 @default.
- W4307788176 hasConcept C163258240 @default.
- W4307788176 hasConcept C204321447 @default.
- W4307788176 hasConcept C22019652 @default.
- W4307788176 hasConcept C2776214188 @default.
- W4307788176 hasConcept C2777601683 @default.
- W4307788176 hasConcept C2780992000 @default.
- W4307788176 hasConcept C31972630 @default.
- W4307788176 hasConcept C41008148 @default.
- W4307788176 hasConcept C41895202 @default.
- W4307788176 hasConcept C50644808 @default.
- W4307788176 hasConcept C62520636 @default.
- W4307788176 hasConceptScore W4307788176C104114177 @default.
- W4307788176 hasConceptScore W4307788176C121332964 @default.
- W4307788176 hasConceptScore W4307788176C138885662 @default.
- W4307788176 hasConceptScore W4307788176C154945302 @default.
- W4307788176 hasConceptScore W4307788176C163258240 @default.
- W4307788176 hasConceptScore W4307788176C204321447 @default.
- W4307788176 hasConceptScore W4307788176C22019652 @default.
- W4307788176 hasConceptScore W4307788176C2776214188 @default.
- W4307788176 hasConceptScore W4307788176C2777601683 @default.
- W4307788176 hasConceptScore W4307788176C2780992000 @default.
- W4307788176 hasConceptScore W4307788176C31972630 @default.
- W4307788176 hasConceptScore W4307788176C41008148 @default.
- W4307788176 hasConceptScore W4307788176C41895202 @default.
- W4307788176 hasConceptScore W4307788176C50644808 @default.
- W4307788176 hasConceptScore W4307788176C62520636 @default.
- W4307788176 hasLocation W43077881761 @default.
- W4307788176 hasOpenAccess W4307788176 @default.
- W4307788176 hasPrimaryLocation W43077881761 @default.
- W4307788176 hasRelatedWork W2029249305 @default.
- W4307788176 hasRelatedWork W2115571026 @default.
- W4307788176 hasRelatedWork W2144043954 @default.
- W4307788176 hasRelatedWork W2511137960 @default.
- W4307788176 hasRelatedWork W2604231787 @default.
- W4307788176 hasRelatedWork W2610014769 @default.
- W4307788176 hasRelatedWork W2687972263 @default.
- W4307788176 hasRelatedWork W2895616727 @default.
- W4307788176 hasRelatedWork W3107474891 @default.
- W4307788176 hasRelatedWork W3214088465 @default.
- W4307788176 isParatext "false" @default.
- W4307788176 isRetracted "false" @default.
- W4307788176 workType "article" @default.