Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035753399> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3035753399 abstract "We propose a novel method to use both audio and a low-resolution image to perform extreme face super-resolution (a 16x increase of the input size). When the resolution of the input image is very low (e.g., 8x8 pixels), the loss of information is so dire that important details of the original identity have been lost and audio can aid the recovery of a plausible high-resolution image. In fact, audio carries information about facial attributes, such as gender and age. To combine the aural and visual modalities, we propose a method to first build the latent representations of a face from the lone audio track and then from the lone low-resolution image. We then train a network to fuse these two representations. We show experimentally that audio can assist in recovering attributes such as the gender, the age and the identity, and thus improve the correctness of the high-resolution image reconstruction process. Our procedure does not make use of human annotation and thus can be easily trained with existing video datasets. Moreover, we show that our model builds a factorized representation of images and audio as it allows one to mix low-resolution images and audio from different videos and to generate realistic faces with semantically meaningful combinations." @default.
- W3035753399 created "2020-06-19" @default.
- W3035753399 creator A5044455266 @default.
- W3035753399 creator A5070714354 @default.
- W3035753399 creator A5070940574 @default.
- W3035753399 date "2020-06-01" @default.
- W3035753399 modified "2023-10-16" @default.
- W3035753399 title "Learning to Have an Ear for Face Super-Resolution" @default.
- W3035753399 cites W2510725918 @default.
- W3035753399 cites W2607041014 @default.
- W3035753399 cites W2741976748 @default.
- W3035753399 cites W2747898905 @default.
- W3035753399 cites W2776107444 @default.
- W3035753399 cites W2780624730 @default.
- W3035753399 cites W2795024892 @default.
- W3035753399 cites W2798691622 @default.
- W3035753399 cites W2799120945 @default.
- W3035753399 cites W2808631503 @default.
- W3035753399 cites W2895085622 @default.
- W3035753399 cites W2895240252 @default.
- W3035753399 cites W2895598217 @default.
- W3035753399 cites W2919046835 @default.
- W3035753399 cites W2922435819 @default.
- W3035753399 cites W2923834406 @default.
- W3035753399 cites W2932253358 @default.
- W3035753399 cites W2938555542 @default.
- W3035753399 cites W2943960148 @default.
- W3035753399 cites W2947156405 @default.
- W3035753399 cites W2947376905 @default.
- W3035753399 cites W2949695917 @default.
- W3035753399 cites W2954930822 @default.
- W3035753399 cites W2962814024 @default.
- W3035753399 cites W2963031226 @default.
- W3035753399 cites W2963470893 @default.
- W3035753399 cites W2963583792 @default.
- W3035753399 cites W2963676087 @default.
- W3035753399 cites W2963729050 @default.
- W3035753399 cites W2963814095 @default.
- W3035753399 cites W2964101377 @default.
- W3035753399 cites W2964277374 @default.
- W3035753399 cites W2971292464 @default.
- W3035753399 cites W2979157532 @default.
- W3035753399 cites W2981722656 @default.
- W3035753399 cites W2983118621 @default.
- W3035753399 cites W2983339877 @default.
- W3035753399 cites W2983873691 @default.
- W3035753399 cites W2985060393 @default.
- W3035753399 cites W2985368596 @default.
- W3035753399 cites W2986556233 @default.
- W3035753399 cites W2986556279 @default.
- W3035753399 cites W2986833982 @default.
- W3035753399 cites W2987150909 @default.
- W3035753399 cites W3099380613 @default.
- W3035753399 cites W3102619627 @default.
- W3035753399 doi "https://doi.org/10.1109/cvpr42600.2020.00144" @default.
- W3035753399 hasPublicationYear "2020" @default.
- W3035753399 type Work @default.
- W3035753399 sameAs 3035753399 @default.
- W3035753399 citedByCount "18" @default.
- W3035753399 countsByYear W30357533992020 @default.
- W3035753399 countsByYear W30357533992021 @default.
- W3035753399 countsByYear W30357533992022 @default.
- W3035753399 countsByYear W30357533992023 @default.
- W3035753399 crossrefType "proceedings-article" @default.
- W3035753399 hasAuthorship W3035753399A5044455266 @default.
- W3035753399 hasAuthorship W3035753399A5070714354 @default.
- W3035753399 hasAuthorship W3035753399A5070940574 @default.
- W3035753399 hasBestOaLocation W30357533992 @default.
- W3035753399 hasConcept C138268822 @default.
- W3035753399 hasConcept C144024400 @default.
- W3035753399 hasConcept C154945302 @default.
- W3035753399 hasConcept C2779304628 @default.
- W3035753399 hasConcept C31972630 @default.
- W3035753399 hasConcept C36289849 @default.
- W3035753399 hasConcept C41008148 @default.
- W3035753399 hasConceptScore W3035753399C138268822 @default.
- W3035753399 hasConceptScore W3035753399C144024400 @default.
- W3035753399 hasConceptScore W3035753399C154945302 @default.
- W3035753399 hasConceptScore W3035753399C2779304628 @default.
- W3035753399 hasConceptScore W3035753399C31972630 @default.
- W3035753399 hasConceptScore W3035753399C36289849 @default.
- W3035753399 hasConceptScore W3035753399C41008148 @default.
- W3035753399 hasLocation W30357533991 @default.
- W3035753399 hasLocation W30357533992 @default.
- W3035753399 hasOpenAccess W3035753399 @default.
- W3035753399 hasPrimaryLocation W30357533991 @default.
- W3035753399 hasRelatedWork W1899364738 @default.
- W3035753399 hasRelatedWork W1955116508 @default.
- W3035753399 hasRelatedWork W2103413230 @default.
- W3035753399 hasRelatedWork W2136321227 @default.
- W3035753399 hasRelatedWork W2170790090 @default.
- W3035753399 hasRelatedWork W2355490025 @default.
- W3035753399 hasRelatedWork W2663901905 @default.
- W3035753399 hasRelatedWork W2908959303 @default.
- W3035753399 hasRelatedWork W43171467 @default.
- W3035753399 hasRelatedWork W2126942212 @default.
- W3035753399 isParatext "false" @default.
- W3035753399 isRetracted "false" @default.
- W3035753399 magId "3035753399" @default.
- W3035753399 workType "article" @default.