Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912107785> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2912107785 abstract "Environmental sound recognition (ESR) has extensive various civilian and military applications. Existing ESR methods generally tackle this problem by employing various signal processing and machine learning methods. Herein, an ESR paradigm based on feature extraction from pre-trained deep convolutional neural networks (CNN), the derivation of higher-order statistics by compact bilinear pooling and normalisation. In particular, we consider two deep ImageNet architectures for deep feature extraction, and the Random Maclaurin (RM) to produce the compact bilinear features. A support vector machine (SVM) with homogeneous mapping is used in the classification stage. Two publicly available environmental sound datasets are used to verify the efficacy of the approach namely, ESC-50 and ESC-10. We compare the proposed method with various previous state-of-the-art methods. Presented results indicate the suitability of the higher-order statistics of Deep Spectrum representations for ESR classification tasks." @default.
- W2912107785 created "2019-02-21" @default.
- W2912107785 creator A5010754413 @default.
- W2912107785 creator A5019651318 @default.
- W2912107785 creator A5045216943 @default.
- W2912107785 creator A5053441398 @default.
- W2912107785 creator A5077471358 @default.
- W2912107785 creator A5090485343 @default.
- W2912107785 date "2018-09-01" @default.
- W2912107785 modified "2023-10-03" @default.
- W2912107785 title "Compact Bilinear Deep Features For Environmental Sound Recognition" @default.
- W2912107785 cites W1998654670 @default.
- W2912107785 cites W2038484192 @default.
- W2912107785 cites W2052666245 @default.
- W2912107785 cites W2062118960 @default.
- W2912107785 cites W2104657103 @default.
- W2912107785 cites W2114806403 @default.
- W2912107785 cites W2137561966 @default.
- W2912107785 cites W2140647972 @default.
- W2912107785 cites W2168515119 @default.
- W2912107785 cites W2170653751 @default.
- W2912107785 cites W2654517624 @default.
- W2912107785 cites W2676925568 @default.
- W2912107785 cites W2765860599 @default.
- W2912107785 cites W2775794021 @default.
- W2912107785 cites W2897297418 @default.
- W2912107785 cites W2963066927 @default.
- W2912107785 cites W3098357269 @default.
- W2912107785 doi "https://doi.org/10.1109/idap.2018.8620779" @default.
- W2912107785 hasPublicationYear "2018" @default.
- W2912107785 type Work @default.
- W2912107785 sameAs 2912107785 @default.
- W2912107785 citedByCount "1" @default.
- W2912107785 countsByYear W29121077852022 @default.
- W2912107785 crossrefType "proceedings-article" @default.
- W2912107785 hasAuthorship W2912107785A5010754413 @default.
- W2912107785 hasAuthorship W2912107785A5019651318 @default.
- W2912107785 hasAuthorship W2912107785A5045216943 @default.
- W2912107785 hasAuthorship W2912107785A5053441398 @default.
- W2912107785 hasAuthorship W2912107785A5077471358 @default.
- W2912107785 hasAuthorship W2912107785A5090485343 @default.
- W2912107785 hasConcept C108583219 @default.
- W2912107785 hasConcept C119857082 @default.
- W2912107785 hasConcept C12267149 @default.
- W2912107785 hasConcept C138885662 @default.
- W2912107785 hasConcept C153180895 @default.
- W2912107785 hasConcept C154945302 @default.
- W2912107785 hasConcept C205203396 @default.
- W2912107785 hasConcept C2776401178 @default.
- W2912107785 hasConcept C28490314 @default.
- W2912107785 hasConcept C2984842247 @default.
- W2912107785 hasConcept C31972630 @default.
- W2912107785 hasConcept C41008148 @default.
- W2912107785 hasConcept C41895202 @default.
- W2912107785 hasConcept C52622490 @default.
- W2912107785 hasConcept C70437156 @default.
- W2912107785 hasConcept C81363708 @default.
- W2912107785 hasConceptScore W2912107785C108583219 @default.
- W2912107785 hasConceptScore W2912107785C119857082 @default.
- W2912107785 hasConceptScore W2912107785C12267149 @default.
- W2912107785 hasConceptScore W2912107785C138885662 @default.
- W2912107785 hasConceptScore W2912107785C153180895 @default.
- W2912107785 hasConceptScore W2912107785C154945302 @default.
- W2912107785 hasConceptScore W2912107785C205203396 @default.
- W2912107785 hasConceptScore W2912107785C2776401178 @default.
- W2912107785 hasConceptScore W2912107785C28490314 @default.
- W2912107785 hasConceptScore W2912107785C2984842247 @default.
- W2912107785 hasConceptScore W2912107785C31972630 @default.
- W2912107785 hasConceptScore W2912107785C41008148 @default.
- W2912107785 hasConceptScore W2912107785C41895202 @default.
- W2912107785 hasConceptScore W2912107785C52622490 @default.
- W2912107785 hasConceptScore W2912107785C70437156 @default.
- W2912107785 hasConceptScore W2912107785C81363708 @default.
- W2912107785 hasLocation W29121077851 @default.
- W2912107785 hasOpenAccess W2912107785 @default.
- W2912107785 hasPrimaryLocation W29121077851 @default.
- W2912107785 hasRelatedWork W2279398222 @default.
- W2912107785 hasRelatedWork W2336974148 @default.
- W2912107785 hasRelatedWork W2517027266 @default.
- W2912107785 hasRelatedWork W2546942002 @default.
- W2912107785 hasRelatedWork W2915754718 @default.
- W2912107785 hasRelatedWork W3156786002 @default.
- W2912107785 hasRelatedWork W4299822940 @default.
- W2912107785 hasRelatedWork W4366492315 @default.
- W2912107785 hasRelatedWork W4385681650 @default.
- W2912107785 hasRelatedWork W2345184372 @default.
- W2912107785 isParatext "false" @default.
- W2912107785 isRetracted "false" @default.
- W2912107785 magId "2912107785" @default.
- W2912107785 workType "article" @default.