Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287759306> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4287759306 abstract "While deep learning technologies are now capable of generating realistic images confusing humans, the research efforts are turning to the synthesis of images for more concrete and application-specific purposes. Facial image generation based on vocal characteristics from speech is one of such important yet challenging tasks. It is the key enabler to influential use cases of image generation, especially for business in public security and entertainment. Existing solutions to the problem of speech2face renders limited image quality and fails to preserve facial similarity due to the lack of quality dataset for training and appropriate integration of vocal features. In this paper, we investigate these key technical challenges and propose Speech Fusion to Face, or SF2F in short, attempting to address the issue of facial image quality and the poor connection between vocal feature domain and modern image generation models. By adopting new strategies on data model and training, we demonstrate dramatic performance boost over state-of-the-art solution, by doubling the recall of individual identity, and lifting the quality score from 15 to 19 based on the mutual information score with VGGFace classifier." @default.
- W4287759306 created "2022-07-26" @default.
- W4287759306 creator A5016673919 @default.
- W4287759306 creator A5059210458 @default.
- W4287759306 creator A5074740653 @default.
- W4287759306 creator A5086764741 @default.
- W4287759306 date "2022-10-10" @default.
- W4287759306 modified "2023-09-30" @default.
- W4287759306 title "Speech Fusion to Face: Bridging the Gap Between Human's Vocal Characteristics and Facial Imaging" @default.
- W4287759306 cites W2097117768 @default.
- W4287759306 cites W2250436945 @default.
- W4287759306 cites W2325939864 @default.
- W4287759306 cites W2331128040 @default.
- W4287759306 cites W2737658251 @default.
- W4287759306 cites W2738406145 @default.
- W4287759306 cites W2739192055 @default.
- W4287759306 cites W2808631503 @default.
- W4287759306 cites W2884460600 @default.
- W4287759306 cites W2886300652 @default.
- W4287759306 cites W2897663715 @default.
- W4287759306 cites W2902299888 @default.
- W4287759306 cites W2952746495 @default.
- W4287759306 cites W2962770929 @default.
- W4287759306 cites W2962788625 @default.
- W4287759306 cites W2963184176 @default.
- W4287759306 cites W2963801643 @default.
- W4287759306 cites W2963887950 @default.
- W4287759306 cites W2963966654 @default.
- W4287759306 cites W2964024144 @default.
- W4287759306 cites W2979157532 @default.
- W4287759306 cites W3099206234 @default.
- W4287759306 doi "https://doi.org/10.1145/3503161.3547850" @default.
- W4287759306 hasPublicationYear "2022" @default.
- W4287759306 type Work @default.
- W4287759306 citedByCount "0" @default.
- W4287759306 crossrefType "proceedings-article" @default.
- W4287759306 hasAuthorship W4287759306A5016673919 @default.
- W4287759306 hasAuthorship W4287759306A5059210458 @default.
- W4287759306 hasAuthorship W4287759306A5074740653 @default.
- W4287759306 hasAuthorship W4287759306A5086764741 @default.
- W4287759306 hasBestOaLocation W42877593062 @default.
- W4287759306 hasConcept C138885662 @default.
- W4287759306 hasConcept C154945302 @default.
- W4287759306 hasConcept C158525013 @default.
- W4287759306 hasConcept C174348530 @default.
- W4287759306 hasConcept C2779304628 @default.
- W4287759306 hasConcept C28490314 @default.
- W4287759306 hasConcept C31258907 @default.
- W4287759306 hasConcept C31972630 @default.
- W4287759306 hasConcept C41008148 @default.
- W4287759306 hasConcept C41895202 @default.
- W4287759306 hasConceptScore W4287759306C138885662 @default.
- W4287759306 hasConceptScore W4287759306C154945302 @default.
- W4287759306 hasConceptScore W4287759306C158525013 @default.
- W4287759306 hasConceptScore W4287759306C174348530 @default.
- W4287759306 hasConceptScore W4287759306C2779304628 @default.
- W4287759306 hasConceptScore W4287759306C28490314 @default.
- W4287759306 hasConceptScore W4287759306C31258907 @default.
- W4287759306 hasConceptScore W4287759306C31972630 @default.
- W4287759306 hasConceptScore W4287759306C41008148 @default.
- W4287759306 hasConceptScore W4287759306C41895202 @default.
- W4287759306 hasLocation W42877593061 @default.
- W4287759306 hasLocation W42877593062 @default.
- W4287759306 hasOpenAccess W4287759306 @default.
- W4287759306 hasPrimaryLocation W42877593061 @default.
- W4287759306 hasRelatedWork W1899364738 @default.
- W4287759306 hasRelatedWork W2018638282 @default.
- W4287759306 hasRelatedWork W2103413230 @default.
- W4287759306 hasRelatedWork W2116300362 @default.
- W4287759306 hasRelatedWork W2138569648 @default.
- W4287759306 hasRelatedWork W2143020626 @default.
- W4287759306 hasRelatedWork W2663901905 @default.
- W4287759306 hasRelatedWork W2908959303 @default.
- W4287759306 hasRelatedWork W43171467 @default.
- W4287759306 hasRelatedWork W2126942212 @default.
- W4287759306 isParatext "false" @default.
- W4287759306 isRetracted "false" @default.
- W4287759306 workType "article" @default.