Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964934051> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W2964934051 abstract "We investigate the viability of collecting annotations for face images while preserving privacy by using synthesized images as surrogates. We compare two approaches: a state-of-the-art 3-D face model based on deep neural networks (Extreme3D) to render a detailed 3-D reconstruction of the face from an input image; and a novel generative adversarial network architecture that we propose that extends BEGAN-CS to generate images conditioned on desired low-level facial attributes. Using these two alternative models, we conduct experiments on Mechanical Turk to annotate emotions (joy and anger) on raw and synthesized versions of face images. Across 60 workers each annotating 3 versions of 60 images in each experiment, we find that: (1) The labeling accuracy when viewing surrogate images can be very similar to the accuracy when viewing raw images, but depends significantly on the labeling task. (2) The proposed extension to BEGAN-CS is effective in generating realistic images that correspond to the input vector of low-level facial attributes. (3) Overall, the GAN-based approach to generating surrogate images gives comparable accuracy as the 3-D face model, but is easier to train." @default.
- W2964934051 created "2019-08-13" @default.
- W2964934051 creator A5027788582 @default.
- W2964934051 creator A5073655930 @default.
- W2964934051 date "2019-06-01" @default.
- W2964934051 modified "2023-10-18" @default.
- W2964934051 title "Privacy-Preserving Annotation of Face Images Through Attribute-Preserving Face Synthesis" @default.
- W2964934051 cites W2081112272 @default.
- W2964934051 cites W2103958416 @default.
- W2964934051 cites W2157653492 @default.
- W2964934051 cites W2158551678 @default.
- W2964934051 cites W2159024459 @default.
- W2964934051 cites W2237250383 @default.
- W2964934051 cites W2296433216 @default.
- W2964934051 cites W2761974878 @default.
- W2964934051 cites W2888531725 @default.
- W2964934051 cites W2920684706 @default.
- W2964934051 cites W2962712356 @default.
- W2964934051 cites W2963278610 @default.
- W2964934051 cites W2964171387 @default.
- W2964934051 cites W2964176417 @default.
- W2964934051 doi "https://doi.org/10.1109/cvprw.2019.00009" @default.
- W2964934051 hasPublicationYear "2019" @default.
- W2964934051 type Work @default.
- W2964934051 sameAs 2964934051 @default.
- W2964934051 citedByCount "6" @default.
- W2964934051 countsByYear W29649340512021 @default.
- W2964934051 countsByYear W29649340512022 @default.
- W2964934051 countsByYear W29649340512023 @default.
- W2964934051 crossrefType "proceedings-article" @default.
- W2964934051 hasAuthorship W2964934051A5027788582 @default.
- W2964934051 hasAuthorship W2964934051A5073655930 @default.
- W2964934051 hasConcept C144024400 @default.
- W2964934051 hasConcept C153180895 @default.
- W2964934051 hasConcept C154945302 @default.
- W2964934051 hasConcept C2776321320 @default.
- W2964934051 hasConcept C2779304628 @default.
- W2964934051 hasConcept C31510193 @default.
- W2964934051 hasConcept C31972630 @default.
- W2964934051 hasConcept C36289849 @default.
- W2964934051 hasConcept C41008148 @default.
- W2964934051 hasConcept C4641261 @default.
- W2964934051 hasConceptScore W2964934051C144024400 @default.
- W2964934051 hasConceptScore W2964934051C153180895 @default.
- W2964934051 hasConceptScore W2964934051C154945302 @default.
- W2964934051 hasConceptScore W2964934051C2776321320 @default.
- W2964934051 hasConceptScore W2964934051C2779304628 @default.
- W2964934051 hasConceptScore W2964934051C31510193 @default.
- W2964934051 hasConceptScore W2964934051C31972630 @default.
- W2964934051 hasConceptScore W2964934051C36289849 @default.
- W2964934051 hasConceptScore W2964934051C41008148 @default.
- W2964934051 hasConceptScore W2964934051C4641261 @default.
- W2964934051 hasLocation W29649340511 @default.
- W2964934051 hasOpenAccess W2964934051 @default.
- W2964934051 hasPrimaryLocation W29649340511 @default.
- W2964934051 hasRelatedWork W1548715306 @default.
- W2964934051 hasRelatedWork W1560697087 @default.
- W2964934051 hasRelatedWork W1589930024 @default.
- W2964934051 hasRelatedWork W1989039360 @default.
- W2964934051 hasRelatedWork W2003685048 @default.
- W2964934051 hasRelatedWork W2146295394 @default.
- W2964934051 hasRelatedWork W2532573070 @default.
- W2964934051 hasRelatedWork W2545171730 @default.
- W2964934051 hasRelatedWork W2607108626 @default.
- W2964934051 hasRelatedWork W269042006 @default.
- W2964934051 isParatext "false" @default.
- W2964934051 isRetracted "false" @default.
- W2964934051 magId "2964934051" @default.
- W2964934051 workType "article" @default.