FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3199474181> ?p ?o ?g. }

• W3199474181 endingPage "3773" @default.
• W3199474181 startingPage "3761" @default.
• W3199474181 abstract "Pose variation and occlusion are two key factors that affect the accuracy of face recognition. Most of the previous work alleviate the impacts of pose and occlusion by performing the tasks of face frontalization and face completion, respectively. Specially, generative adversarial networks (GANs) based methods have made a great progress on both of these two tasks. However, the two tasks are rarely paid attention simultaneously. Hence, the synthesis and recognition from the profile but occluded facial image is still an understudied and challenging problem in two aspects. 1) Occlusion mask, as a kind of noise, can be some very important prior information in the corrupted image. In particular, the occlusion mask is often used to fit this noise and help face restoration of the occluded region. However, a prior work, such as BoostGAN, failed to utilize the mask guided noise prior information. 2) The two tasks, de-occlusion and frontalization, are collaborative, so the identity discriminative information is easily lost if the two tasks are not organically unified in the training phase. In order to overcome these challenges, we propose a novel mask guided two-stage generative adversarial network ( <bold xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>TSGAN</b> ). There are two major contributions in this work: 1) In order to utilize the prior information of noise, an occluded mask based attention model is proposed, which is integrated into the two stages via U-connection. This mask works as a guidance to simultaneously repair and frontalize the profile but occluded faces. 2) An end-to-end paradigm with a two-stage architecture ( <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>i.e.,</i> face deocclusion network and face frontalization network) is proposed to complete the two tasks jointly. Furthermore, for preserving the discriminative identity information in both stages more effectively, we propose a novel dual triplet loss, consisting of a deocclusion triplet loss and a frontalization triplet loss. Qualitative and quantitative experiments on both constrained and unconstrained face datasets with regular and irregular (natural) occlusions demonstrate the superiority of our approach." @default.
• W3199474181 created "2021-09-27" @default.
• W3199474181 creator A5003381889 @default.
• W3199474181 creator A5033073191 @default.
• W3199474181 creator A5056569344 @default.
• W3199474181 date "2022-06-01" @default.
• W3199474181 modified "2023-10-14" @default.
• W3199474181 title "Simultaneous Face Completion and Frontalization via Mask Guided Two-Stage GAN" @default.
• W3199474181 cites W134498629 @default.
• W3199474181 cites W1991174941 @default.
• W3199474181 cites W1993120651 @default.
• W3199474181 cites W1994619529 @default.
• W3199474181 cites W2037231462 @default.
• W3199474181 cites W2071080980 @default.
• W3199474181 cites W2100495367 @default.
• W3199474181 cites W2217448953 @default.
• W3199474181 cites W2237250383 @default.
• W3199474181 cites W2404498690 @default.
• W3199474181 cites W2508385416 @default.
• W3199474181 cites W2519280274 @default.
• W3199474181 cites W2584229793 @default.
• W3199474181 cites W2606532215 @default.
• W3199474181 cites W2611104282 @default.
• W3199474181 cites W2614580201 @default.
• W3199474181 cites W2617561348 @default.
• W3199474181 cites W2621210799 @default.
• W3199474181 cites W2737047298 @default.
• W3199474181 cites W2738588019 @default.
• W3199474181 cites W2769176102 @default.
• W3199474181 cites W2792275277 @default.
• W3199474181 cites W2798575809 @default.
• W3199474181 cites W2902017744 @default.
• W3199474181 cites W2902412551 @default.
• W3199474181 cites W2912990735 @default.
• W3199474181 cites W2943314296 @default.
• W3199474181 cites W2962793481 @default.
• W3199474181 cites W2962898354 @default.
• W3199474181 cites W2962922273 @default.
• W3199474181 cites W2963100452 @default.
• W3199474181 cites W2963231084 @default.
• W3199474181 cites W2963460857 @default.
• W3199474181 cites W2963917315 @default.
• W3199474181 cites W2964337551 @default.
• W3199474181 cites W2997600418 @default.
• W3199474181 cites W3010003739 @default.
• W3199474181 cites W3012050083 @default.
• W3199474181 cites W3035678046 @default.
• W3199474181 cites W3043547428 @default.
• W3199474181 cites W3091476632 @default.
• W3199474181 cites W3095866053 @default.
• W3199474181 cites W3099206234 @default.
• W3199474181 cites W3101998545 @default.
• W3199474181 doi "https://doi.org/10.1109/tcsvt.2021.3111648" @default.
• W3199474181 hasPublicationYear "2022" @default.
• W3199474181 type Work @default.
• W3199474181 sameAs 3199474181 @default.
• W3199474181 citedByCount "7" @default.
• W3199474181 countsByYear W31994741812021 @default.
• W3199474181 countsByYear W31994741812022 @default.
• W3199474181 countsByYear W31994741812023 @default.
• W3199474181 crossrefType "journal-article" @default.
• W3199474181 hasAuthorship W3199474181A5003381889 @default.
• W3199474181 hasAuthorship W3199474181A5033073191 @default.
• W3199474181 hasAuthorship W3199474181A5056569344 @default.
• W3199474181 hasConcept C115961682 @default.
• W3199474181 hasConcept C144024400 @default.
• W3199474181 hasConcept C153180895 @default.
• W3199474181 hasConcept C154945302 @default.
• W3199474181 hasConcept C164705383 @default.
• W3199474181 hasConcept C2776268601 @default.
• W3199474181 hasConcept C2779304628 @default.
• W3199474181 hasConcept C2988773926 @default.
• W3199474181 hasConcept C31510193 @default.
• W3199474181 hasConcept C31972630 @default.
• W3199474181 hasConcept C36289849 @default.
• W3199474181 hasConcept C41008148 @default.
• W3199474181 hasConcept C71924100 @default.
• W3199474181 hasConcept C97931131 @default.
• W3199474181 hasConcept C99498987 @default.
• W3199474181 hasConceptScore W3199474181C115961682 @default.
• W3199474181 hasConceptScore W3199474181C144024400 @default.
• W3199474181 hasConceptScore W3199474181C153180895 @default.
• W3199474181 hasConceptScore W3199474181C154945302 @default.
• W3199474181 hasConceptScore W3199474181C164705383 @default.
• W3199474181 hasConceptScore W3199474181C2776268601 @default.
• W3199474181 hasConceptScore W3199474181C2779304628 @default.
• W3199474181 hasConceptScore W3199474181C2988773926 @default.
• W3199474181 hasConceptScore W3199474181C31510193 @default.
• W3199474181 hasConceptScore W3199474181C31972630 @default.
• W3199474181 hasConceptScore W3199474181C36289849 @default.
• W3199474181 hasConceptScore W3199474181C41008148 @default.
• W3199474181 hasConceptScore W3199474181C71924100 @default.
• W3199474181 hasConceptScore W3199474181C97931131 @default.
• W3199474181 hasConceptScore W3199474181C99498987 @default.
• W3199474181 hasFunder F4320321001 @default.
• W3199474181 hasFunder F4320335787 @default.
• W3199474181 hasIssue "6" @default.
• W3199474181 hasLocation W31994741811 @default.

• next