Matches in SemOpenAlex for { <https://semopenalex.org/work/W3215141862> ?p ?o ?g. }
- W3215141862 endingPage "116543" @default.
- W3215141862 startingPage "116543" @default.
- W3215141862 abstract "Kinship verification based on facial images in the wild is an interesting and challenging research topic in the fields of computer vision. It has many potential applications, e.g., missing children search, image annotation, etc. In practice, the biggest obstacle in kinship verification is that there usually exists large divergence between the images of parent and children. How to effectively tackle such challenge is important for improving kinship verification performance. To this end, we proposed a novel Deep Discriminant Generation-Shared Feature Learning for Image-Based Kinship Verification (D2GFL) method for kinship verification, which consists of a two-stream generation-specific feature learning module and a generation-shared discrepancy reducing module. The generation-specific feature learning module can learn parent-specific and child-specific features. The generation-shared module aims to reduce the divergence between facial images of parent and child. In order to further relieve the cross-generation difference and improve the discriminability of learned features, we also design a cross-generation difference loss term and an intra-generation discriminant loss term, which simultaneously make use of the local and holistic features, as well as the family identity information. Experimental results on several widely used kinship datasets are presented to validate the effectiveness of our proposed approach by comparing with the state-of-the-art kinship verification methods. Specially, our approach can improve the average verification accuracy at least by 3.5%, 1.5% and 0.8% on KinFaceW-I, Cornell, and TSKinFace datasets, respectively." @default.
- W3215141862 created "2021-12-06" @default.
- W3215141862 creator A5008315702 @default.
- W3215141862 creator A5012689262 @default.
- W3215141862 creator A5013074804 @default.
- W3215141862 creator A5051407732 @default.
- W3215141862 creator A5061971455 @default.
- W3215141862 creator A5062314052 @default.
- W3215141862 creator A5080119140 @default.
- W3215141862 date "2022-02-01" @default.
- W3215141862 modified "2023-10-16" @default.
- W3215141862 title "Deep discriminant generation-shared feature learning for image-based kinship verification" @default.
- W3215141862 cites W1241252238 @default.
- W3215141862 cites W1906145078 @default.
- W3215141862 cites W2012783213 @default.
- W3215141862 cites W2079742827 @default.
- W3215141862 cites W2106955482 @default.
- W3215141862 cites W2125911081 @default.
- W3215141862 cites W2132074694 @default.
- W3215141862 cites W2132886138 @default.
- W3215141862 cites W2145773134 @default.
- W3215141862 cites W2151103935 @default.
- W3215141862 cites W2163808566 @default.
- W3215141862 cites W2172260703 @default.
- W3215141862 cites W2323684557 @default.
- W3215141862 cites W2435048505 @default.
- W3215141862 cites W2512291285 @default.
- W3215141862 cites W2560852071 @default.
- W3215141862 cites W2567804583 @default.
- W3215141862 cites W2604305041 @default.
- W3215141862 cites W2617586438 @default.
- W3215141862 cites W2679426462 @default.
- W3215141862 cites W2751574673 @default.
- W3215141862 cites W2766119523 @default.
- W3215141862 cites W2769771355 @default.
- W3215141862 cites W2770681586 @default.
- W3215141862 cites W2778865088 @default.
- W3215141862 cites W2806332870 @default.
- W3215141862 cites W2897151190 @default.
- W3215141862 cites W2913071101 @default.
- W3215141862 cites W2943866869 @default.
- W3215141862 cites W2963809521 @default.
- W3215141862 cites W2969336025 @default.
- W3215141862 cites W2980597757 @default.
- W3215141862 cites W2998633236 @default.
- W3215141862 cites W3004990178 @default.
- W3215141862 cites W3033235266 @default.
- W3215141862 cites W3037574114 @default.
- W3215141862 cites W3039317552 @default.
- W3215141862 doi "https://doi.org/10.1016/j.image.2021.116543" @default.
- W3215141862 hasPublicationYear "2022" @default.
- W3215141862 type Work @default.
- W3215141862 sameAs 3215141862 @default.
- W3215141862 citedByCount "3" @default.
- W3215141862 countsByYear W32151418622022 @default.
- W3215141862 countsByYear W32151418622023 @default.
- W3215141862 crossrefType "journal-article" @default.
- W3215141862 hasAuthorship W3215141862A5008315702 @default.
- W3215141862 hasAuthorship W3215141862A5012689262 @default.
- W3215141862 hasAuthorship W3215141862A5013074804 @default.
- W3215141862 hasAuthorship W3215141862A5051407732 @default.
- W3215141862 hasAuthorship W3215141862A5061971455 @default.
- W3215141862 hasAuthorship W3215141862A5062314052 @default.
- W3215141862 hasAuthorship W3215141862A5080119140 @default.
- W3215141862 hasConcept C108583219 @default.
- W3215141862 hasConcept C119857082 @default.
- W3215141862 hasConcept C138885662 @default.
- W3215141862 hasConcept C144024400 @default.
- W3215141862 hasConcept C144348335 @default.
- W3215141862 hasConcept C153180895 @default.
- W3215141862 hasConcept C154945302 @default.
- W3215141862 hasConcept C17744445 @default.
- W3215141862 hasConcept C199539241 @default.
- W3215141862 hasConcept C207390915 @default.
- W3215141862 hasConcept C2776401178 @default.
- W3215141862 hasConcept C2779304628 @default.
- W3215141862 hasConcept C31510193 @default.
- W3215141862 hasConcept C36289849 @default.
- W3215141862 hasConcept C41008148 @default.
- W3215141862 hasConcept C41895202 @default.
- W3215141862 hasConcept C50644808 @default.
- W3215141862 hasConcept C52622490 @default.
- W3215141862 hasConcept C69738355 @default.
- W3215141862 hasConceptScore W3215141862C108583219 @default.
- W3215141862 hasConceptScore W3215141862C119857082 @default.
- W3215141862 hasConceptScore W3215141862C138885662 @default.
- W3215141862 hasConceptScore W3215141862C144024400 @default.
- W3215141862 hasConceptScore W3215141862C144348335 @default.
- W3215141862 hasConceptScore W3215141862C153180895 @default.
- W3215141862 hasConceptScore W3215141862C154945302 @default.
- W3215141862 hasConceptScore W3215141862C17744445 @default.
- W3215141862 hasConceptScore W3215141862C199539241 @default.
- W3215141862 hasConceptScore W3215141862C207390915 @default.
- W3215141862 hasConceptScore W3215141862C2776401178 @default.
- W3215141862 hasConceptScore W3215141862C2779304628 @default.
- W3215141862 hasConceptScore W3215141862C31510193 @default.
- W3215141862 hasConceptScore W3215141862C36289849 @default.
- W3215141862 hasConceptScore W3215141862C41008148 @default.