FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2792910644> ?p ?o ?g. }

• W2792910644 abstract "Representations generated by Fisher vector (FV) have shown decent performances on many facial image datasets. However, discriminative information could be masked by noise if the authors directly sum all local responses with respect to the learned dictionary. Further, the high dimension of FV prohibits its practical use. To mitigate these problems, the authors propose a new framework called joint compressed Fisher vector (JCFV), which generate task-specific data representation by jointly encoding multiscale deep convolutional activations. Firstly, they feed into the deep network facial images cropped with cascaded sub-windows and resized into various scales. Next, they select discriminative convolutional features to form a dictionary. Then, they aggregate multiscale features with respect to the dictionary by calculating a re-weighted first-order statistics. JCFV halves the dimension of FV, and they could further compress the dimension with several combinations of subspace methods. They prove the effectiveness of their JCFV descriptor with comprehensive experiments on FERET, AR, LFW and FRGC 2.0 Experiment 4." @default.
• W2792910644 created "2018-03-29" @default.
• W2792910644 creator A5024197883 @default.
• W2792910644 creator A5025452586 @default.
• W2792910644 date "2018-03-07" @default.
• W2792910644 modified "2023-09-27" @default.
• W2792910644 title "Face recognition with compressed Fisher vector on multiscale convolutional features" @default.
• W2792910644 cites W1548783750 @default.
• W2792910644 cites W1761337995 @default.
• W2792910644 cites W1783842908 @default.
• W2792910644 cites W1901075642 @default.
• W2792910644 cites W1925596459 @default.
• W2792910644 cites W1932481952 @default.
• W2792910644 cites W1950843348 @default.
• W2792910644 cites W1951319388 @default.
• W2792910644 cites W1964266152 @default.
• W2792910644 cites W1966385142 @default.
• W2792910644 cites W1975056068 @default.
• W2792910644 cites W1975780119 @default.
• W2792910644 cites W1976921161 @default.
• W2792910644 cites W1985425861 @default.
• W2792910644 cites W1997011019 @default.
• W2792910644 cites W2002273623 @default.
• W2792910644 cites W2005385547 @default.
• W2792910644 cites W2046649434 @default.
• W2792910644 cites W2047186200 @default.
• W2792910644 cites W2062118960 @default.
• W2792910644 cites W2071027807 @default.
• W2792910644 cites W2079315848 @default.
• W2792910644 cites W2110721032 @default.
• W2792910644 cites W2114588272 @default.
• W2792910644 cites W2145287260 @default.
• W2792910644 cites W2147238549 @default.
• W2792910644 cites W2167912153 @default.
• W2792910644 cites W2194775991 @default.
• W2792910644 cites W2296228058 @default.
• W2792910644 cites W2325939864 @default.
• W2792910644 cites W2480418144 @default.
• W2792910644 cites W2963173190 @default.
• W2792910644 cites W3099206234 @default.
• W2792910644 cites W4212863985 @default.
• W2792910644 cites W1596605326 @default.
• W2792910644 doi "https://doi.org/10.1049/iet-bmt.2017.0194" @default.
• W2792910644 hasPublicationYear "2018" @default.
• W2792910644 type Work @default.
• W2792910644 sameAs 2792910644 @default.
• W2792910644 citedByCount "1" @default.
• W2792910644 countsByYear W27929106442020 @default.
• W2792910644 crossrefType "journal-article" @default.
• W2792910644 hasAuthorship W2792910644A5024197883 @default.
• W2792910644 hasAuthorship W2792910644A5025452586 @default.
• W2792910644 hasConcept C144024400 @default.
• W2792910644 hasConcept C153180895 @default.
• W2792910644 hasConcept C154945302 @default.
• W2792910644 hasConcept C17744445 @default.
• W2792910644 hasConcept C199539241 @default.
• W2792910644 hasConcept C202444582 @default.
• W2792910644 hasConcept C2776359362 @default.
• W2792910644 hasConcept C2779304628 @default.
• W2792910644 hasConcept C28490314 @default.
• W2792910644 hasConcept C31510193 @default.
• W2792910644 hasConcept C32834561 @default.
• W2792910644 hasConcept C33676613 @default.
• W2792910644 hasConcept C33923547 @default.
• W2792910644 hasConcept C36289849 @default.
• W2792910644 hasConcept C41008148 @default.
• W2792910644 hasConcept C81363708 @default.
• W2792910644 hasConcept C94625758 @default.
• W2792910644 hasConcept C97931131 @default.
• W2792910644 hasConceptScore W2792910644C144024400 @default.
• W2792910644 hasConceptScore W2792910644C153180895 @default.
• W2792910644 hasConceptScore W2792910644C154945302 @default.
• W2792910644 hasConceptScore W2792910644C17744445 @default.
• W2792910644 hasConceptScore W2792910644C199539241 @default.
• W2792910644 hasConceptScore W2792910644C202444582 @default.
• W2792910644 hasConceptScore W2792910644C2776359362 @default.
• W2792910644 hasConceptScore W2792910644C2779304628 @default.
• W2792910644 hasConceptScore W2792910644C28490314 @default.
• W2792910644 hasConceptScore W2792910644C31510193 @default.
• W2792910644 hasConceptScore W2792910644C32834561 @default.
• W2792910644 hasConceptScore W2792910644C33676613 @default.
• W2792910644 hasConceptScore W2792910644C33923547 @default.
• W2792910644 hasConceptScore W2792910644C36289849 @default.
• W2792910644 hasConceptScore W2792910644C41008148 @default.
• W2792910644 hasConceptScore W2792910644C81363708 @default.
• W2792910644 hasConceptScore W2792910644C94625758 @default.
• W2792910644 hasConceptScore W2792910644C97931131 @default.
• W2792910644 hasLocation W27929106441 @default.
• W2792910644 hasOpenAccess W2792910644 @default.
• W2792910644 hasPrimaryLocation W27929106441 @default.
• W2792910644 hasRelatedWork W1500366037 @default.
• W2792910644 hasRelatedWork W1982285588 @default.
• W2792910644 hasRelatedWork W2000955465 @default.
• W2792910644 hasRelatedWork W2053673812 @default.
• W2792910644 hasRelatedWork W2146248736 @default.
• W2792910644 hasRelatedWork W2198976020 @default.
• W2792910644 hasRelatedWork W2334876076 @default.
• W2792910644 hasRelatedWork W2343008037 @default.
• W2792910644 hasRelatedWork W2605718464 @default.
• W2792910644 hasRelatedWork W2887356678 @default.

• next