FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313229418> ?p ?o ?g. }

• W4313229418 endingPage "862" @default.
• W4313229418 startingPage "849" @default.
• W4313229418 abstract "Environmental Sound Classification (ESC) is an important field in a broad range of applications, such as smart cities, audio surveillance, and health care. Recently, Convolutional Neural Networks (CNNs) have taken the lead from traditional approaches and have produced promising results. However, the achieved improvements are often accompanied by increasing depth, complexity, and size of the network, which prevents their usage in many practical applications. In this work, our goal is to empower a small-size low-complexity CNN model to achieve superior performance. To this end, we concentrate on the importance of global pooling technique, which is less investigated in ESC. In most previous works, models utilize global average pooling layer which does not consider regional saliency, and thus weakens the salient time-frequency regions contributions to the classification, and also to the training of convolutional kernels. We propose a novel global pooling method, called Sparse Salient Region Pooling (SSRP), which computes the channel descriptors using a sparse subset of features, and guides the model to effectively learn from the more salient time-frequency regions. Experimental results demonstrate that the proposed model with only 700K parameters yields accuracies of 86.7% on ESC-50 and 94.8% on ESC-10, which are comparable to that of the state-of-the-art methods. Compared to the baseline model, our model achieves absolute improvement of 21.8% in accuracy on ESC-50, with 98% smaller model size. Our visual analyses show that SSRP intensifies the responses of low-energy regions such that they contribute even more than high-energy regions to the classification of specific sound classes." @default.
• W4313229418 created "2023-01-06" @default.
• W4313229418 creator A5042880223 @default.
• W4313229418 creator A5043802641 @default.
• W4313229418 date "2023-01-01" @default.
• W4313229418 modified "2023-10-10" @default.
• W4313229418 title "Environmental Sound Classification With Low-Complexity Convolutional Neural Network Empowered by Sparse Salient Region Pooling" @default.
• W4313229418 cites W1496704041 @default.
• W4313229418 cites W1600744878 @default.
• W4313229418 cites W1840106123 @default.
• W4313229418 cites W1972567154 @default.
• W4313229418 cites W1995562189 @default.
• W4313229418 cites W1996528178 @default.
• W4313229418 cites W2052666245 @default.
• W4313229418 cites W2059652044 @default.
• W4313229418 cites W2082183045 @default.
• W4313229418 cites W2135342008 @default.
• W4313229418 cites W2191779130 @default.
• W4313229418 cites W2194775991 @default.
• W4313229418 cites W2306289963 @default.
• W4313229418 cites W2484273982 @default.
• W4313229418 cites W2526050071 @default.
• W4313229418 cites W2529337537 @default.
• W4313229418 cites W2556003166 @default.
• W4313229418 cites W2559156603 @default.
• W4313229418 cites W2563031223 @default.
• W4313229418 cites W2593451766 @default.
• W4313229418 cites W2745969942 @default.
• W4313229418 cites W2746255131 @default.
• W4313229418 cites W2751841560 @default.
• W4313229418 cites W2883588054 @default.
• W4313229418 cites W2888469011 @default.
• W4313229418 cites W2891365890 @default.
• W4313229418 cites W2962793908 @default.
• W4313229418 cites W2962858109 @default.
• W4313229418 cites W2963838685 @default.
• W4313229418 cites W2964012402 @default.
• W4313229418 cites W2972247414 @default.
• W4313229418 cites W2972425456 @default.
• W4313229418 cites W2976146944 @default.
• W4313229418 cites W2985407551 @default.
• W4313229418 cites W3020588108 @default.
• W4313229418 cites W3022215617 @default.
• W4313229418 cites W3032636897 @default.
• W4313229418 cites W3032888638 @default.
• W4313229418 cites W3040775664 @default.
• W4313229418 cites W3083566224 @default.
• W4313229418 cites W3094550259 @default.
• W4313229418 cites W3095348033 @default.
• W4313229418 cites W3173678936 @default.
• W4313229418 cites W3175400544 @default.
• W4313229418 cites W3195409179 @default.
• W4313229418 cites W3195567822 @default.
• W4313229418 cites W3209152703 @default.
• W4313229418 cites W4289521424 @default.
• W4313229418 cites W3032566731 @default.
• W4313229418 doi "https://doi.org/10.1109/access.2022.3232807" @default.
• W4313229418 hasPublicationYear "2023" @default.
• W4313229418 type Work @default.
• W4313229418 citedByCount "3" @default.
• W4313229418 countsByYear W43132294182023 @default.
• W4313229418 crossrefType "journal-article" @default.
• W4313229418 hasAuthorship W4313229418A5042880223 @default.
• W4313229418 hasAuthorship W4313229418A5043802641 @default.
• W4313229418 hasBestOaLocation W43132294181 @default.
• W4313229418 hasConcept C111368507 @default.
• W4313229418 hasConcept C119857082 @default.
• W4313229418 hasConcept C12725497 @default.
• W4313229418 hasConcept C127313418 @default.
• W4313229418 hasConcept C153180895 @default.
• W4313229418 hasConcept C154945302 @default.
• W4313229418 hasConcept C2780719617 @default.
• W4313229418 hasConcept C41008148 @default.
• W4313229418 hasConcept C70437156 @default.
• W4313229418 hasConcept C81363708 @default.
• W4313229418 hasConceptScore W4313229418C111368507 @default.
• W4313229418 hasConceptScore W4313229418C119857082 @default.
• W4313229418 hasConceptScore W4313229418C12725497 @default.
• W4313229418 hasConceptScore W4313229418C127313418 @default.
• W4313229418 hasConceptScore W4313229418C153180895 @default.
• W4313229418 hasConceptScore W4313229418C154945302 @default.
• W4313229418 hasConceptScore W4313229418C2780719617 @default.
• W4313229418 hasConceptScore W4313229418C41008148 @default.
• W4313229418 hasConceptScore W4313229418C70437156 @default.
• W4313229418 hasConceptScore W4313229418C81363708 @default.
• W4313229418 hasLocation W43132294181 @default.
• W4313229418 hasOpenAccess W4313229418 @default.
• W4313229418 hasPrimaryLocation W43132294181 @default.
• W4313229418 hasRelatedWork W2291847203 @default.
• W4313229418 hasRelatedWork W2424871898 @default.
• W4313229418 hasRelatedWork W2517027266 @default.
• W4313229418 hasRelatedWork W2756241593 @default.
• W4313229418 hasRelatedWork W2767651786 @default.
• W4313229418 hasRelatedWork W2944724518 @default.
• W4313229418 hasRelatedWork W3004532561 @default.
• W4313229418 hasRelatedWork W3027997911 @default.
• W4313229418 hasRelatedWork W4287776258 @default.
• W4313229418 hasRelatedWork W4313229418 @default.

• next