FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4221144911> ?p ?o ?g. }

• W4221144911 abstract "This work digs into a root question in human perception: can face geometry be gleaned from one's voices? Previous works that study this question only adopt developments in image synthesis and convert voices into face images to show correlations, but working on the image domain unavoidably involves predicting attributes that voices cannot hint, including facial textures, hairstyles, and backgrounds. We instead investigate the ability to reconstruct 3D faces to concentrate on only geometry, which is much more physiologically grounded. We propose our analysis framework, Cross-Modal Perceptionist, under both supervised and unsupervised learning. First, we construct a dataset, Voxceleb-3D, which extends Voxceleb and includes paired voices and face meshes, making supervised learning possible. Second, we use a knowledge distillation mechanism to study whether face geometry can still be gleaned from voices without paired voices and 3D face data under limited availability of 3D face scans. We break down the core question into four parts and perform visual and numerical analyses as responses to the core question. Our findings echo those in physiology and neuroscience about the correlation between voices and facial structures. The work provides future human-centric cross-modal learning with explainable foundations. See our project page." @default.
• W4221144911 created "2022-04-03" @default.
• W4221144911 creator A5024267838 @default.
• W4221144911 creator A5028115568 @default.
• W4221144911 creator A5082235583 @default.
• W4221144911 date "2022-06-01" @default.
• W4221144911 modified "2023-09-30" @default.
• W4221144911 title "Cross-Modal Perceptionist: Can Face Geometry be Gleaned from Voices?" @default.
• W4221144911 cites W1605417594 @default.
• W4221144911 cites W2011040757 @default.
• W4221144911 cites W2076591386 @default.
• W4221144911 cites W2080277992 @default.
• W4221144911 cites W2085999891 @default.
• W4221144911 cites W2107037917 @default.
• W4221144911 cites W2108696343 @default.
• W4221144911 cites W2156473462 @default.
• W4221144911 cites W2166563626 @default.
• W4221144911 cites W2325939864 @default.
• W4221144911 cites W2398381847 @default.
• W4221144911 cites W2403957496 @default.
• W4221144911 cites W2486034530 @default.
• W4221144911 cites W2509287279 @default.
• W4221144911 cites W2593898237 @default.
• W4221144911 cites W2599621350 @default.
• W4221144911 cites W2794922094 @default.
• W4221144911 cites W2796822548 @default.
• W4221144911 cites W2884460600 @default.
• W4221144911 cites W2914217321 @default.
• W4221144911 cites W2937977583 @default.
• W4221144911 cites W2962770929 @default.
• W4221144911 cites W2962918445 @default.
• W4221144911 cites W2963081548 @default.
• W4221144911 cites W2963290645 @default.
• W4221144911 cites W2963887950 @default.
• W4221144911 cites W2964014798 @default.
• W4221144911 cites W2964052309 @default.
• W4221144911 cites W2972778435 @default.
• W4221144911 cites W2979157532 @default.
• W4221144911 cites W2981263323 @default.
• W4221144911 cites W2984700035 @default.
• W4221144911 cites W2985068832 @default.
• W4221144911 cites W3007833402 @default.
• W4221144911 cites W3034192160 @default.
• W4221144911 cites W3035574324 @default.
• W4221144911 cites W3096831136 @default.
• W4221144911 cites W3097741049 @default.
• W4221144911 cites W3104300620 @default.
• W4221144911 cites W3104792420 @default.
• W4221144911 cites W3108710777 @default.
• W4221144911 cites W3127573699 @default.
• W4221144911 cites W3176913662 @default.
• W4221144911 cites W3177326298 @default.
• W4221144911 cites W3184648662 @default.
• W4221144911 cites W3211147706 @default.
• W4221144911 cites W4226087396 @default.
• W4221144911 cites W4253794606 @default.
• W4221144911 doi "https://doi.org/10.1109/cvpr52688.2022.01020" @default.
• W4221144911 hasPublicationYear "2022" @default.
• W4221144911 type Work @default.
• W4221144911 citedByCount "1" @default.
• W4221144911 countsByYear W42211449112023 @default.
• W4221144911 crossrefType "proceedings-article" @default.
• W4221144911 hasAuthorship W4221144911A5024267838 @default.
• W4221144911 hasAuthorship W4221144911A5028115568 @default.
• W4221144911 hasAuthorship W4221144911A5082235583 @default.
• W4221144911 hasBestOaLocation W42211449112 @default.
• W4221144911 hasConcept C107457646 @default.
• W4221144911 hasConcept C121684516 @default.
• W4221144911 hasConcept C138885662 @default.
• W4221144911 hasConcept C154945302 @default.
• W4221144911 hasConcept C15744967 @default.
• W4221144911 hasConcept C169760540 @default.
• W4221144911 hasConcept C185592680 @default.
• W4221144911 hasConcept C188027245 @default.
• W4221144911 hasConcept C199360897 @default.
• W4221144911 hasConcept C26760741 @default.
• W4221144911 hasConcept C2779304628 @default.
• W4221144911 hasConcept C2780801425 @default.
• W4221144911 hasConcept C31487907 @default.
• W4221144911 hasConcept C41008148 @default.
• W4221144911 hasConcept C41895202 @default.
• W4221144911 hasConcept C71139939 @default.
• W4221144911 hasConceptScore W4221144911C107457646 @default.
• W4221144911 hasConceptScore W4221144911C121684516 @default.
• W4221144911 hasConceptScore W4221144911C138885662 @default.
• W4221144911 hasConceptScore W4221144911C154945302 @default.
• W4221144911 hasConceptScore W4221144911C15744967 @default.
• W4221144911 hasConceptScore W4221144911C169760540 @default.
• W4221144911 hasConceptScore W4221144911C185592680 @default.
• W4221144911 hasConceptScore W4221144911C188027245 @default.
• W4221144911 hasConceptScore W4221144911C199360897 @default.
• W4221144911 hasConceptScore W4221144911C26760741 @default.
• W4221144911 hasConceptScore W4221144911C2779304628 @default.
• W4221144911 hasConceptScore W4221144911C2780801425 @default.
• W4221144911 hasConceptScore W4221144911C31487907 @default.
• W4221144911 hasConceptScore W4221144911C41008148 @default.
• W4221144911 hasConceptScore W4221144911C41895202 @default.
• W4221144911 hasConceptScore W4221144911C71139939 @default.
• W4221144911 hasLocation W42211449111 @default.
• W4221144911 hasLocation W42211449112 @default.

• next