Matches in SemOpenAlex for { <https://semopenalex.org/work/W4298054031> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4298054031 abstract "Image animation aims to animate a source image by using motion learned from a driving video. Current state-of-the-art methods typically use convolutional neural networks (CNNs) to predict motion information, such as motion keypoints and corresponding local transformations. However, these CNN based methods do not explicitly model the interactions between motions; as a result, the important underlying motion relationship may be neglected, which can potentially lead to noticeable artifacts being produced in the generated animation video. To this end, we propose a new method, the motion transformer, which is the first attempt to build a motion estimator based on a vision transformer. More specifically, we introduce two types of tokens in our proposed method: i) image tokens formed from patch features and corresponding position encoding; and ii) motion tokens encoded with motion information. Both types of tokens are sent into vision transformers to promote underlying interactions between them through multi-head self attention blocks. By adopting this process, the motion information can be better learned to boost the model performance. The final embedded motion tokens are then used to predict the corresponding motion keypoints and local transformations. Extensive experiments on benchmark datasets show that our proposed method achieves promising results to the state-of-the-art baselines. Our source code will be public available." @default.
- W4298054031 created "2022-10-01" @default.
- W4298054031 creator A5001969147 @default.
- W4298054031 creator A5027308029 @default.
- W4298054031 creator A5068394447 @default.
- W4298054031 creator A5074655314 @default.
- W4298054031 creator A5075523709 @default.
- W4298054031 creator A5080093489 @default.
- W4298054031 date "2022-09-28" @default.
- W4298054031 modified "2023-10-18" @default.
- W4298054031 title "Motion Transformer for Unsupervised Image Animation" @default.
- W4298054031 doi "https://doi.org/10.48550/arxiv.2209.14024" @default.
- W4298054031 hasPublicationYear "2022" @default.
- W4298054031 type Work @default.
- W4298054031 citedByCount "0" @default.
- W4298054031 crossrefType "posted-content" @default.
- W4298054031 hasAuthorship W4298054031A5001969147 @default.
- W4298054031 hasAuthorship W4298054031A5027308029 @default.
- W4298054031 hasAuthorship W4298054031A5068394447 @default.
- W4298054031 hasAuthorship W4298054031A5074655314 @default.
- W4298054031 hasAuthorship W4298054031A5075523709 @default.
- W4298054031 hasAuthorship W4298054031A5080093489 @default.
- W4298054031 hasBestOaLocation W42980540311 @default.
- W4298054031 hasConcept C10161872 @default.
- W4298054031 hasConcept C104114177 @default.
- W4298054031 hasConcept C121332964 @default.
- W4298054031 hasConcept C121684516 @default.
- W4298054031 hasConcept C154945302 @default.
- W4298054031 hasConcept C165801399 @default.
- W4298054031 hasConcept C31972630 @default.
- W4298054031 hasConcept C41008148 @default.
- W4298054031 hasConcept C502989409 @default.
- W4298054031 hasConcept C62520636 @default.
- W4298054031 hasConcept C66322947 @default.
- W4298054031 hasConcept C81363708 @default.
- W4298054031 hasConceptScore W4298054031C10161872 @default.
- W4298054031 hasConceptScore W4298054031C104114177 @default.
- W4298054031 hasConceptScore W4298054031C121332964 @default.
- W4298054031 hasConceptScore W4298054031C121684516 @default.
- W4298054031 hasConceptScore W4298054031C154945302 @default.
- W4298054031 hasConceptScore W4298054031C165801399 @default.
- W4298054031 hasConceptScore W4298054031C31972630 @default.
- W4298054031 hasConceptScore W4298054031C41008148 @default.
- W4298054031 hasConceptScore W4298054031C502989409 @default.
- W4298054031 hasConceptScore W4298054031C62520636 @default.
- W4298054031 hasConceptScore W4298054031C66322947 @default.
- W4298054031 hasConceptScore W4298054031C81363708 @default.
- W4298054031 hasLocation W42980540311 @default.
- W4298054031 hasOpenAccess W4298054031 @default.
- W4298054031 hasPrimaryLocation W42980540311 @default.
- W4298054031 hasRelatedWork W2029249305 @default.
- W4298054031 hasRelatedWork W2122456626 @default.
- W4298054031 hasRelatedWork W2140468889 @default.
- W4298054031 hasRelatedWork W2144043954 @default.
- W4298054031 hasRelatedWork W2153928989 @default.
- W4298054031 hasRelatedWork W2395873996 @default.
- W4298054031 hasRelatedWork W2511137960 @default.
- W4298054031 hasRelatedWork W2687972263 @default.
- W4298054031 hasRelatedWork W2902444409 @default.
- W4298054031 hasRelatedWork W4281553171 @default.
- W4298054031 isParatext "false" @default.
- W4298054031 isRetracted "false" @default.
- W4298054031 workType "article" @default.