Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308952014> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4308952014 endingPage "283" @default.
- W4308952014 startingPage "276" @default.
- W4308952014 abstract "Occlusions, such as those due to wearing surgical masks, pose a significant challenge to the face recognition systems. Among possible remedies, ocular biometric has proven to be a popular choice. However, the upper ocular regions, especially the patterns presented by the eyebrows, have yet to gain the attention they deserve. In this work, we leverage Neural Architecture Search (NAS) to discover better-performing architectures for eyebrow recognition. To reduce the computational complexity, we apply a zero-shot NAS to assess the exploratory architectures’ performance prior to any training. We were able to discover three new architectures that achieved competitive accuracies in eyebrow recognition. In doing so, we explored depthwise separable convolution, hard-swish, and Arcface loss functions to further enhance the discovered models in terms of accuracy and number of parameters. Our best result provided 0.999 AUC, 0.6% EER, and 98.25% GMR at 10−3 FMR over FACES dataset, which is better than the results of state-of-the-art architecture, a 29-layer lightCNN which has 21× more parameters and 8× more FLOPS." @default.
- W4308952014 created "2022-11-20" @default.
- W4308952014 creator A5048986857 @default.
- W4308952014 creator A5067923262 @default.
- W4308952014 date "2022-12-01" @default.
- W4308952014 modified "2023-09-27" @default.
- W4308952014 title "NAS For efficient mobile eyebrow biometrics" @default.
- W4308952014 cites W1951319388 @default.
- W4308952014 cites W1964981411 @default.
- W4308952014 cites W2186574009 @default.
- W4308952014 cites W2888902882 @default.
- W4308952014 cites W2942211779 @default.
- W4308952014 cites W2944338288 @default.
- W4308952014 cites W2963460857 @default.
- W4308952014 cites W3025523728 @default.
- W4308952014 cites W3048254275 @default.
- W4308952014 cites W3157171624 @default.
- W4308952014 cites W3188354902 @default.
- W4308952014 cites W3206752670 @default.
- W4308952014 doi "https://doi.org/10.1016/j.patrec.2022.11.009" @default.
- W4308952014 hasPublicationYear "2022" @default.
- W4308952014 type Work @default.
- W4308952014 citedByCount "1" @default.
- W4308952014 countsByYear W43089520142023 @default.
- W4308952014 crossrefType "journal-article" @default.
- W4308952014 hasAuthorship W4308952014A5048986857 @default.
- W4308952014 hasAuthorship W4308952014A5067923262 @default.
- W4308952014 hasConcept C119857082 @default.
- W4308952014 hasConcept C141071460 @default.
- W4308952014 hasConcept C144024400 @default.
- W4308952014 hasConcept C153083717 @default.
- W4308952014 hasConcept C153180895 @default.
- W4308952014 hasConcept C154945302 @default.
- W4308952014 hasConcept C184297639 @default.
- W4308952014 hasConcept C2779022956 @default.
- W4308952014 hasConcept C2779304628 @default.
- W4308952014 hasConcept C31510193 @default.
- W4308952014 hasConcept C36289849 @default.
- W4308952014 hasConcept C41008148 @default.
- W4308952014 hasConcept C45347329 @default.
- W4308952014 hasConcept C50644808 @default.
- W4308952014 hasConcept C71924100 @default.
- W4308952014 hasConceptScore W4308952014C119857082 @default.
- W4308952014 hasConceptScore W4308952014C141071460 @default.
- W4308952014 hasConceptScore W4308952014C144024400 @default.
- W4308952014 hasConceptScore W4308952014C153083717 @default.
- W4308952014 hasConceptScore W4308952014C153180895 @default.
- W4308952014 hasConceptScore W4308952014C154945302 @default.
- W4308952014 hasConceptScore W4308952014C184297639 @default.
- W4308952014 hasConceptScore W4308952014C2779022956 @default.
- W4308952014 hasConceptScore W4308952014C2779304628 @default.
- W4308952014 hasConceptScore W4308952014C31510193 @default.
- W4308952014 hasConceptScore W4308952014C36289849 @default.
- W4308952014 hasConceptScore W4308952014C41008148 @default.
- W4308952014 hasConceptScore W4308952014C45347329 @default.
- W4308952014 hasConceptScore W4308952014C50644808 @default.
- W4308952014 hasConceptScore W4308952014C71924100 @default.
- W4308952014 hasFunder F4320318398 @default.
- W4308952014 hasLocation W43089520141 @default.
- W4308952014 hasOpenAccess W4308952014 @default.
- W4308952014 hasPrimaryLocation W43089520141 @default.
- W4308952014 hasRelatedWork W1775397219 @default.
- W4308952014 hasRelatedWork W1968332688 @default.
- W4308952014 hasRelatedWork W2001423728 @default.
- W4308952014 hasRelatedWork W2134472250 @default.
- W4308952014 hasRelatedWork W2159857630 @default.
- W4308952014 hasRelatedWork W2347601237 @default.
- W4308952014 hasRelatedWork W2536391335 @default.
- W4308952014 hasRelatedWork W2536516098 @default.
- W4308952014 hasRelatedWork W2897995864 @default.
- W4308952014 hasRelatedWork W3086983552 @default.
- W4308952014 hasVolume "164" @default.
- W4308952014 isParatext "false" @default.
- W4308952014 isRetracted "false" @default.
- W4308952014 workType "article" @default.