Matches in SemOpenAlex for { <https://semopenalex.org/work/W3203092022> ?p ?o ?g. }
- W3203092022 endingPage "272" @default.
- W3203092022 startingPage "261" @default.
- W3203092022 abstract "In the dark scene at night, the face images captured by ordinary visible light (VIS) are generally poor quality and very dim, while the near-infrared (NIR) can capture high definition and recognizable face images at night. The NIR-VIS Heterogeneous face recognition has become a hot research field, which helps to build an all-weather face recognition system. NIR-VIS HFR is sophisticated because of the large visual difference between NIR images and VIS images. In order to reduce the difficulty of such cross-modality invariant feature learning, this paper proposes a cross-modality data gap decomposed by auxiliary modality method (DGD) for NIR-VIS HFR. First, the brightness component (Y component) of VIS image YCbCr space is used as the auxiliary modality to decompose the cross-modality data gap. The lightness component retained the structural information of VIS image and was similar to the colour information of NIR modality; in this way, the huge gap between the NIR data and the VIS data is decomposed into two smaller gaps, thus reducing the difficulty of network learning. Second, the data of the three modalities are input into the weight sharing network and training under the combined guidance of cross-modality gap decomposition loss and intra-modality gap loss; in this way, the modality invariant features can be learned faster and better. Extensive experiments were conducted on two commonly used datasets CASIA NIR-VIS 2.0 and Oulu-CASIA NIR-VIS to evaluate DGD method. Experimental results indicate DGD method has competitive performance compared with the latest methods." @default.
- W3203092022 created "2021-10-11" @default.
- W3203092022 creator A5027242644 @default.
- W3203092022 creator A5050852420 @default.
- W3203092022 creator A5085183952 @default.
- W3203092022 creator A5086976460 @default.
- W3203092022 date "2021-09-27" @default.
- W3203092022 modified "2023-10-17" @default.
- W3203092022 title "Data gap decomposed by auxiliary modality for NIR‐VIS heterogeneous face recognition" @default.
- W3203092022 cites W1484953274 @default.
- W3203092022 cites W2030899956 @default.
- W3203092022 cites W2034136097 @default.
- W3203092022 cites W2038809248 @default.
- W3203092022 cites W2085810284 @default.
- W3203092022 cites W2100553728 @default.
- W3203092022 cites W2140556441 @default.
- W3203092022 cites W2152788298 @default.
- W3203092022 cites W2158096215 @default.
- W3203092022 cites W2183341477 @default.
- W3203092022 cites W2186500555 @default.
- W3203092022 cites W2325939864 @default.
- W3203092022 cites W2345232174 @default.
- W3203092022 cites W2485822847 @default.
- W3203092022 cites W2515770085 @default.
- W3203092022 cites W2519985940 @default.
- W3203092022 cites W2523746035 @default.
- W3203092022 cites W2551624499 @default.
- W3203092022 cites W2568415986 @default.
- W3203092022 cites W2743674619 @default.
- W3203092022 cites W2791375745 @default.
- W3203092022 cites W2897015430 @default.
- W3203092022 cites W2904791642 @default.
- W3203092022 cites W2913468054 @default.
- W3203092022 cites W2941841895 @default.
- W3203092022 cites W2963276927 @default.
- W3203092022 cites W2963460857 @default.
- W3203092022 cites W2963600167 @default.
- W3203092022 cites W2963809521 @default.
- W3203092022 cites W2964350391 @default.
- W3203092022 cites W2970943217 @default.
- W3203092022 cites W3008762881 @default.
- W3203092022 cites W97858523 @default.
- W3203092022 doi "https://doi.org/10.1049/ipr2.12350" @default.
- W3203092022 hasPublicationYear "2021" @default.
- W3203092022 type Work @default.
- W3203092022 sameAs 3203092022 @default.
- W3203092022 citedByCount "1" @default.
- W3203092022 countsByYear W32030920222023 @default.
- W3203092022 crossrefType "journal-article" @default.
- W3203092022 hasAuthorship W3203092022A5027242644 @default.
- W3203092022 hasAuthorship W3203092022A5050852420 @default.
- W3203092022 hasAuthorship W3203092022A5085183952 @default.
- W3203092022 hasAuthorship W3203092022A5086976460 @default.
- W3203092022 hasConcept C138885662 @default.
- W3203092022 hasConcept C144024400 @default.
- W3203092022 hasConcept C153180895 @default.
- W3203092022 hasConcept C154945302 @default.
- W3203092022 hasConcept C159078339 @default.
- W3203092022 hasConcept C2776401178 @default.
- W3203092022 hasConcept C2779304628 @default.
- W3203092022 hasConcept C2780226545 @default.
- W3203092022 hasConcept C31510193 @default.
- W3203092022 hasConcept C31972630 @default.
- W3203092022 hasConcept C36289849 @default.
- W3203092022 hasConcept C41008148 @default.
- W3203092022 hasConcept C41895202 @default.
- W3203092022 hasConceptScore W3203092022C138885662 @default.
- W3203092022 hasConceptScore W3203092022C144024400 @default.
- W3203092022 hasConceptScore W3203092022C153180895 @default.
- W3203092022 hasConceptScore W3203092022C154945302 @default.
- W3203092022 hasConceptScore W3203092022C159078339 @default.
- W3203092022 hasConceptScore W3203092022C2776401178 @default.
- W3203092022 hasConceptScore W3203092022C2779304628 @default.
- W3203092022 hasConceptScore W3203092022C2780226545 @default.
- W3203092022 hasConceptScore W3203092022C31510193 @default.
- W3203092022 hasConceptScore W3203092022C31972630 @default.
- W3203092022 hasConceptScore W3203092022C36289849 @default.
- W3203092022 hasConceptScore W3203092022C41008148 @default.
- W3203092022 hasConceptScore W3203092022C41895202 @default.
- W3203092022 hasFunder F4320321001 @default.
- W3203092022 hasIssue "1" @default.
- W3203092022 hasLocation W32030920221 @default.
- W3203092022 hasLocation W32030920222 @default.
- W3203092022 hasOpenAccess W3203092022 @default.
- W3203092022 hasPrimaryLocation W32030920221 @default.
- W3203092022 hasRelatedWork W1560697087 @default.
- W3203092022 hasRelatedWork W1869808405 @default.
- W3203092022 hasRelatedWork W1989039360 @default.
- W3203092022 hasRelatedWork W2009382932 @default.
- W3203092022 hasRelatedWork W2031007444 @default.
- W3203092022 hasRelatedWork W2031420897 @default.
- W3203092022 hasRelatedWork W2060029454 @default.
- W3203092022 hasRelatedWork W2136485282 @default.
- W3203092022 hasRelatedWork W2783789044 @default.
- W3203092022 hasRelatedWork W2908959303 @default.
- W3203092022 hasVolume "16" @default.
- W3203092022 isParatext "false" @default.
- W3203092022 isRetracted "false" @default.