FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3000996870> ?p ?o ?g. }

• W3000996870 endingPage "3397" @default.
• W3000996870 startingPage "3387" @default.
• W3000996870 abstract "Face recognition has achieved advanced development by using convolutional neural network (CNN) based recognizers. Existing recognizers typically demonstrate powerful capacity in recognizing un-occluded faces, but often suffer from accuracy degradation when directly identifying occluded faces. This is mainly due to insufficient visual and identity cues caused by occlusions. On the other hand, generative adversarial network (GAN) is particularly suitable when it needs to reconstruct visually plausible occlusions by face inpainting. Motivated by these observations, this paper proposes identity-diversity inpainting to facilitate occluded face recognition. The core idea is integrating GAN with an optimized pre-trained CNN recognizer which serves as the third player to compete with the generator by distinguishing diversity within the same identity class. To this end, a collect of identity-centered features is applied in the recognizer as supervision to enable the inpainted faces clustering towards their identity centers. In this way, our approach can benefit from GAN for reconstruction and CNN for representation, and simultaneously addresses two challenging tasks, face inpainting and face recognition. Experimental results compared with 4 state-of-the-arts prove the efficacy of the proposed approach." @default.
• W3000996870 created "2020-01-30" @default.
• W3000996870 creator A5005407838 @default.
• W3000996870 creator A5022640003 @default.
• W3000996870 creator A5033254559 @default.
• W3000996870 creator A5084763603 @default.
• W3000996870 date "2020-10-01" @default.
• W3000996870 modified "2023-10-17" @default.
• W3000996870 title "Occluded Face Recognition in the Wild by Identity-Diversity Inpainting" @default.
• W3000996870 cites W1772300941 @default.
• W3000996870 cites W1834627138 @default.
• W3000996870 cites W1993120651 @default.
• W3000996870 cites W2024688311 @default.
• W3000996870 cites W2025530562 @default.
• W3000996870 cites W2041306058 @default.
• W3000996870 cites W2044632064 @default.
• W3000996870 cites W2054366734 @default.
• W3000996870 cites W2085400714 @default.
• W3000996870 cites W2129812935 @default.
• W3000996870 cites W2145287260 @default.
• W3000996870 cites W2152516042 @default.
• W3000996870 cites W2153169342 @default.
• W3000996870 cites W2155893237 @default.
• W3000996870 cites W2167905668 @default.
• W3000996870 cites W2220707429 @default.
• W3000996870 cites W2342578201 @default.
• W3000996870 cites W2396968374 @default.
• W3000996870 cites W2507989420 @default.
• W3000996870 cites W2511925907 @default.
• W3000996870 cites W2520774990 @default.
• W3000996870 cites W2530163446 @default.
• W3000996870 cites W2556783285 @default.
• W3000996870 cites W2565575913 @default.
• W3000996870 cites W2604305041 @default.
• W3000996870 cites W2611104282 @default.
• W3000996870 cites W2614580201 @default.
• W3000996870 cites W2619170298 @default.
• W3000996870 cites W2621210799 @default.
• W3000996870 cites W2731516742 @default.
• W3000996870 cites W2738588019 @default.
• W3000996870 cites W2739722733 @default.
• W3000996870 cites W2781292787 @default.
• W3000996870 cites W2799209711 @default.
• W3000996870 cites W2803418063 @default.
• W3000996870 cites W2884066303 @default.
• W3000996870 cites W2962898354 @default.
• W3000996870 cites W2962922273 @default.
• W3000996870 cites W2963403266 @default.
• W3000996870 cites W2963420272 @default.
• W3000996870 cites W2963466847 @default.
• W3000996870 cites W2963521568 @default.
• W3000996870 cites W2963839617 @default.
• W3000996870 cites W2964339532 @default.
• W3000996870 cites W2969985801 @default.
• W3000996870 cites W3043547428 @default.
• W3000996870 cites W3099206234 @default.
• W3000996870 cites W2963613219 @default.
• W3000996870 doi "https://doi.org/10.1109/tcsvt.2020.2967754" @default.
• W3000996870 hasPublicationYear "2020" @default.
• W3000996870 type Work @default.
• W3000996870 sameAs 3000996870 @default.
• W3000996870 citedByCount "62" @default.
• W3000996870 countsByYear W30009968702020 @default.
• W3000996870 countsByYear W30009968702021 @default.
• W3000996870 countsByYear W30009968702022 @default.
• W3000996870 countsByYear W30009968702023 @default.
• W3000996870 crossrefType "journal-article" @default.
• W3000996870 hasAuthorship W3000996870A5005407838 @default.
• W3000996870 hasAuthorship W3000996870A5022640003 @default.
• W3000996870 hasAuthorship W3000996870A5033254559 @default.
• W3000996870 hasAuthorship W3000996870A5084763603 @default.
• W3000996870 hasConcept C107038049 @default.
• W3000996870 hasConcept C115961682 @default.
• W3000996870 hasConcept C11727466 @default.
• W3000996870 hasConcept C138885662 @default.
• W3000996870 hasConcept C142362112 @default.
• W3000996870 hasConcept C144024400 @default.
• W3000996870 hasConcept C153180895 @default.
• W3000996870 hasConcept C154945302 @default.
• W3000996870 hasConcept C19165224 @default.
• W3000996870 hasConcept C2778355321 @default.
• W3000996870 hasConcept C2779304628 @default.
• W3000996870 hasConcept C2781316041 @default.
• W3000996870 hasConcept C31510193 @default.
• W3000996870 hasConcept C31972630 @default.
• W3000996870 hasConcept C41008148 @default.
• W3000996870 hasConcept C41895202 @default.
• W3000996870 hasConceptScore W3000996870C107038049 @default.
• W3000996870 hasConceptScore W3000996870C115961682 @default.
• W3000996870 hasConceptScore W3000996870C11727466 @default.
• W3000996870 hasConceptScore W3000996870C138885662 @default.
• W3000996870 hasConceptScore W3000996870C142362112 @default.
• W3000996870 hasConceptScore W3000996870C144024400 @default.
• W3000996870 hasConceptScore W3000996870C153180895 @default.
• W3000996870 hasConceptScore W3000996870C154945302 @default.
• W3000996870 hasConceptScore W3000996870C19165224 @default.
• W3000996870 hasConceptScore W3000996870C2778355321 @default.
• W3000996870 hasConceptScore W3000996870C2779304628 @default.

• next