Matches in SemOpenAlex for { <https://semopenalex.org/work/W3205994442> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3205994442 abstract "Utilizing an arbitrary speech clip to edit the mouth of the portrait in the target video is a novel yet challenging task. Despite impressive results have been achieved, there are still three limitations in the existing methods: 1) since the acoustic features are not completely decoupled from person identity, there is no global speech to facial features (i.e., landmarks, expression blendshape) mapping method. 2) the audio-driven talking face sequences generated by simple cascade structure usually lack of temporal consistency and spatial correlation, which leads to defects in the consistency of changes in details. 3) the operation of forgery is always at the video level, without considering the forgery of the voice, especially the synchronization of the converted voice and the mouth. To address these distortion problems, we propose a novel deep learning framework, named Temporal-Refinement Autoregressive-Cascade Rendering Network (TACR-Net) for audio-driven dynamic talking face editing. The proposed TACR-Net encodes facial expression blendshape based on the given acoustic features without separately training for special video. Then TACR-Net also involves a novel autoregressive cascade structure generator for video re-rendering. Finally, we transform the in-the-wild speech to the target portrait and obtain a photo-realistic and audio-realistic video." @default.
- W3205994442 created "2021-10-25" @default.
- W3205994442 creator A5002781909 @default.
- W3205994442 creator A5004119465 @default.
- W3205994442 creator A5024413169 @default.
- W3205994442 creator A5033440540 @default.
- W3205994442 creator A5048826252 @default.
- W3205994442 creator A5055238399 @default.
- W3205994442 date "2021-10-17" @default.
- W3205994442 modified "2023-09-27" @default.
- W3205994442 title "TACR-Net: Editing on Deep Video and Voice Portraits" @default.
- W3205994442 cites W1901129140 @default.
- W3205994442 cites W1975848997 @default.
- W3205994442 cites W2015143272 @default.
- W3205994442 cites W2087147962 @default.
- W3205994442 cites W2127141656 @default.
- W3205994442 cites W2146991130 @default.
- W3205994442 cites W2237250383 @default.
- W3205994442 cites W2402146185 @default.
- W3205994442 cites W2486034530 @default.
- W3205994442 cites W2526425061 @default.
- W3205994442 cites W2560474170 @default.
- W3205994442 cites W2562637781 @default.
- W3205994442 cites W2565639579 @default.
- W3205994442 cites W2726515241 @default.
- W3205994442 cites W2738406145 @default.
- W3205994442 cites W2806833697 @default.
- W3205994442 cites W2808631503 @default.
- W3205994442 cites W2942074357 @default.
- W3205994442 cites W2944294033 @default.
- W3205994442 cites W2960274051 @default.
- W3205994442 cites W2963073614 @default.
- W3205994442 cites W2963211739 @default.
- W3205994442 cites W2964449965 @default.
- W3205994442 cites W2979894294 @default.
- W3205994442 cites W3013529009 @default.
- W3205994442 cites W3015338123 @default.
- W3205994442 cites W3019952993 @default.
- W3205994442 cites W3081492798 @default.
- W3205994442 cites W3097792222 @default.
- W3205994442 cites W3107666850 @default.
- W3205994442 cites W3112809496 @default.
- W3205994442 doi "https://doi.org/10.1145/3474085.3475196" @default.
- W3205994442 hasPublicationYear "2021" @default.
- W3205994442 type Work @default.
- W3205994442 sameAs 3205994442 @default.
- W3205994442 citedByCount "5" @default.
- W3205994442 countsByYear W32059944422022 @default.
- W3205994442 countsByYear W32059944422023 @default.
- W3205994442 crossrefType "proceedings-article" @default.
- W3205994442 hasAuthorship W3205994442A5002781909 @default.
- W3205994442 hasAuthorship W3205994442A5004119465 @default.
- W3205994442 hasAuthorship W3205994442A5024413169 @default.
- W3205994442 hasAuthorship W3205994442A5033440540 @default.
- W3205994442 hasAuthorship W3205994442A5048826252 @default.
- W3205994442 hasAuthorship W3205994442A5055238399 @default.
- W3205994442 hasConcept C149782125 @default.
- W3205994442 hasConcept C154945302 @default.
- W3205994442 hasConcept C159877910 @default.
- W3205994442 hasConcept C162324750 @default.
- W3205994442 hasConcept C185592680 @default.
- W3205994442 hasConcept C205711294 @default.
- W3205994442 hasConcept C28490314 @default.
- W3205994442 hasConcept C31972630 @default.
- W3205994442 hasConcept C34146451 @default.
- W3205994442 hasConcept C41008148 @default.
- W3205994442 hasConcept C43617362 @default.
- W3205994442 hasConceptScore W3205994442C149782125 @default.
- W3205994442 hasConceptScore W3205994442C154945302 @default.
- W3205994442 hasConceptScore W3205994442C159877910 @default.
- W3205994442 hasConceptScore W3205994442C162324750 @default.
- W3205994442 hasConceptScore W3205994442C185592680 @default.
- W3205994442 hasConceptScore W3205994442C205711294 @default.
- W3205994442 hasConceptScore W3205994442C28490314 @default.
- W3205994442 hasConceptScore W3205994442C31972630 @default.
- W3205994442 hasConceptScore W3205994442C34146451 @default.
- W3205994442 hasConceptScore W3205994442C41008148 @default.
- W3205994442 hasConceptScore W3205994442C43617362 @default.
- W3205994442 hasLocation W32059944421 @default.
- W3205994442 hasOpenAccess W3205994442 @default.
- W3205994442 hasPrimaryLocation W32059944421 @default.
- W3205994442 hasRelatedWork W1503414886 @default.
- W3205994442 hasRelatedWork W1863533157 @default.
- W3205994442 hasRelatedWork W2048402902 @default.
- W3205994442 hasRelatedWork W2087353037 @default.
- W3205994442 hasRelatedWork W2095660797 @default.
- W3205994442 hasRelatedWork W2143214896 @default.
- W3205994442 hasRelatedWork W2166044122 @default.
- W3205994442 hasRelatedWork W2740010476 @default.
- W3205994442 hasRelatedWork W2797881514 @default.
- W3205994442 hasRelatedWork W3182299699 @default.
- W3205994442 isParatext "false" @default.
- W3205994442 isRetracted "false" @default.
- W3205994442 magId "3205994442" @default.
- W3205994442 workType "article" @default.