Matches in SemOpenAlex for { <https://semopenalex.org/work/W3043013312> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3043013312 endingPage "130781" @default.
- W3043013312 startingPage "130771" @default.
- W3043013312 abstract "Gender recognition has been among the most investigated problems in the last years; although several contributions have been proposed, gender recognition in unconstrained environments is still a challenging problem and a definitive solution has not been found yet. Furthermore, Deep Convolutional Neural Networks (DCNNs) achieve very interesting performance, but they typically require a huge amount of computational resources (CPU, GPU, RAM, storage), that are not always available in real systems, due to their cost or to specific application constraints (when the application needs to be installed directly on board of low-power smart cameras, e.g. for digital signage). In the latest years the Machine Learning community developed an interest towards optimizing the efficiency of Deep Learning solutions, in order to make them portable and widespread. In this work we propose a compact DCNN architecture for Gender Recognition from face images that achieves approximately state of the art accuracy at a highly reduced computational cost (almost five times). We also perform a sensitivity analysis in order to show how some changes in the architecture of the network can influence the tradeoff between accuracy and speed. In addition, we compare our optimized architecture with popular efficient CNNs on various common benchmark dataset, widely adopted in the scientific community, namely LFW, MIVIA-Gender, IMDB-WIKI and Adience, demonstrating the effectiveness of the proposed solution." @default.
- W3043013312 created "2020-07-23" @default.
- W3043013312 creator A5027593663 @default.
- W3043013312 creator A5064364003 @default.
- W3043013312 creator A5071216669 @default.
- W3043013312 date "2020-01-01" @default.
- W3043013312 modified "2023-10-14" @default.
- W3043013312 title "A Convolutional Neural Network for Gender Recognition Optimizing the Accuracy/Speed Tradeoff" @default.
- W3043013312 cites W1834627138 @default.
- W3043013312 cites W1849007038 @default.
- W3043013312 cites W1916406603 @default.
- W3043013312 cites W1965804146 @default.
- W3043013312 cites W2023161323 @default.
- W3043013312 cites W2101392314 @default.
- W3043013312 cites W2149494055 @default.
- W3043013312 cites W2164598857 @default.
- W3043013312 cites W2179234838 @default.
- W3043013312 cites W2194775991 @default.
- W3043013312 cites W2247274765 @default.
- W3043013312 cites W2325939864 @default.
- W3043013312 cites W2494453810 @default.
- W3043013312 cites W2510725918 @default.
- W3043013312 cites W2531409750 @default.
- W3043013312 cites W2550061716 @default.
- W3043013312 cites W2731793484 @default.
- W3043013312 cites W2765443779 @default.
- W3043013312 cites W2796310778 @default.
- W3043013312 cites W2797145190 @default.
- W3043013312 cites W2883780447 @default.
- W3043013312 cites W2893813411 @default.
- W3043013312 cites W2901282250 @default.
- W3043013312 cites W2921737442 @default.
- W3043013312 cites W2960230137 @default.
- W3043013312 cites W2963377935 @default.
- W3043013312 cites W2963839617 @default.
- W3043013312 cites W2995882507 @default.
- W3043013312 cites W3000638052 @default.
- W3043013312 doi "https://doi.org/10.1109/access.2020.3008793" @default.
- W3043013312 hasPublicationYear "2020" @default.
- W3043013312 type Work @default.
- W3043013312 sameAs 3043013312 @default.
- W3043013312 citedByCount "22" @default.
- W3043013312 countsByYear W30430133122020 @default.
- W3043013312 countsByYear W30430133122021 @default.
- W3043013312 countsByYear W30430133122022 @default.
- W3043013312 countsByYear W30430133122023 @default.
- W3043013312 crossrefType "journal-article" @default.
- W3043013312 hasAuthorship W3043013312A5027593663 @default.
- W3043013312 hasAuthorship W3043013312A5064364003 @default.
- W3043013312 hasAuthorship W3043013312A5071216669 @default.
- W3043013312 hasBestOaLocation W30430133121 @default.
- W3043013312 hasConcept C119857082 @default.
- W3043013312 hasConcept C153180895 @default.
- W3043013312 hasConcept C154945302 @default.
- W3043013312 hasConcept C173608175 @default.
- W3043013312 hasConcept C28490314 @default.
- W3043013312 hasConcept C41008148 @default.
- W3043013312 hasConcept C68339613 @default.
- W3043013312 hasConcept C81363708 @default.
- W3043013312 hasConceptScore W3043013312C119857082 @default.
- W3043013312 hasConceptScore W3043013312C153180895 @default.
- W3043013312 hasConceptScore W3043013312C154945302 @default.
- W3043013312 hasConceptScore W3043013312C173608175 @default.
- W3043013312 hasConceptScore W3043013312C28490314 @default.
- W3043013312 hasConceptScore W3043013312C41008148 @default.
- W3043013312 hasConceptScore W3043013312C68339613 @default.
- W3043013312 hasConceptScore W3043013312C81363708 @default.
- W3043013312 hasLocation W30430133121 @default.
- W3043013312 hasOpenAccess W3043013312 @default.
- W3043013312 hasPrimaryLocation W30430133121 @default.
- W3043013312 hasRelatedWork W2175746458 @default.
- W3043013312 hasRelatedWork W2613736958 @default.
- W3043013312 hasRelatedWork W2732542196 @default.
- W3043013312 hasRelatedWork W2738221750 @default.
- W3043013312 hasRelatedWork W2760085659 @default.
- W3043013312 hasRelatedWork W3012978760 @default.
- W3043013312 hasRelatedWork W3027997911 @default.
- W3043013312 hasRelatedWork W3081496756 @default.
- W3043013312 hasRelatedWork W3093612317 @default.
- W3043013312 hasRelatedWork W4287776258 @default.
- W3043013312 hasVolume "8" @default.
- W3043013312 isParatext "false" @default.
- W3043013312 isRetracted "false" @default.
- W3043013312 magId "3043013312" @default.
- W3043013312 workType "article" @default.