Matches in SemOpenAlex for { <https://semopenalex.org/work/W3015597694> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3015597694 abstract "Multiple instance learning (MIL) with convolutional neural networks (CNNs) has been proposed recently for weakly labelled audio tagging. However, features from the various CNN filtering channels and spatial regions are often treated equally, which may limit its performance in event prediction. In this paper, we propose a novel attention mechanism, namely, spatial and channel-wise attention (SCA). For spatial attention, we divide it into global and local submodules with the former to capture the event-related spatial regions and the latter to estimate the onset and offset of the events. Considering the variations in CNN channels, channel-wise attention is also exploited to recognize different sound scenes. The proposed SCA can be employed into any CNNs seamlessly with affordable overheads and is end-to-end trainable fashion. Extensive experiments on weakly labelled dataset Audioset show that the proposed SCA with CNNs achieves a state-of-the-art mean average precision (mAP) of 0.390." @default.
- W3015597694 created "2020-04-17" @default.
- W3015597694 creator A5002795838 @default.
- W3015597694 creator A5037691180 @default.
- W3015597694 creator A5067002890 @default.
- W3015597694 creator A5083633440 @default.
- W3015597694 date "2020-05-01" @default.
- W3015597694 modified "2023-10-16" @default.
- W3015597694 title "Weakly Labelled Audio Tagging Via Convolutional Networks with Spatial and Channel-Wise Attention" @default.
- W3015597694 cites W2062388453 @default.
- W3015597694 cites W2354870669 @default.
- W3015597694 cites W2526050071 @default.
- W3015597694 cites W2593116425 @default.
- W3015597694 cites W2604490051 @default.
- W3015597694 cites W2752782242 @default.
- W3015597694 cites W2883651221 @default.
- W3015597694 cites W2889351461 @default.
- W3015597694 cites W2937077415 @default.
- W3015597694 cites W2963022469 @default.
- W3015597694 cites W2963610932 @default.
- W3015597694 cites W2963715927 @default.
- W3015597694 cites W2964891022 @default.
- W3015597694 doi "https://doi.org/10.1109/icassp40776.2020.9053427" @default.
- W3015597694 hasPublicationYear "2020" @default.
- W3015597694 type Work @default.
- W3015597694 sameAs 3015597694 @default.
- W3015597694 citedByCount "8" @default.
- W3015597694 countsByYear W30155976942019 @default.
- W3015597694 countsByYear W30155976942021 @default.
- W3015597694 countsByYear W30155976942022 @default.
- W3015597694 countsByYear W30155976942023 @default.
- W3015597694 crossrefType "proceedings-article" @default.
- W3015597694 hasAuthorship W3015597694A5002795838 @default.
- W3015597694 hasAuthorship W3015597694A5037691180 @default.
- W3015597694 hasAuthorship W3015597694A5067002890 @default.
- W3015597694 hasAuthorship W3015597694A5083633440 @default.
- W3015597694 hasBestOaLocation W30155976942 @default.
- W3015597694 hasConcept C105795698 @default.
- W3015597694 hasConcept C121332964 @default.
- W3015597694 hasConcept C127162648 @default.
- W3015597694 hasConcept C153180895 @default.
- W3015597694 hasConcept C154945302 @default.
- W3015597694 hasConcept C159620131 @default.
- W3015597694 hasConcept C175291020 @default.
- W3015597694 hasConcept C199360897 @default.
- W3015597694 hasConcept C2779662365 @default.
- W3015597694 hasConcept C28490314 @default.
- W3015597694 hasConcept C33923547 @default.
- W3015597694 hasConcept C41008148 @default.
- W3015597694 hasConcept C62520636 @default.
- W3015597694 hasConcept C76155785 @default.
- W3015597694 hasConcept C81363708 @default.
- W3015597694 hasConceptScore W3015597694C105795698 @default.
- W3015597694 hasConceptScore W3015597694C121332964 @default.
- W3015597694 hasConceptScore W3015597694C127162648 @default.
- W3015597694 hasConceptScore W3015597694C153180895 @default.
- W3015597694 hasConceptScore W3015597694C154945302 @default.
- W3015597694 hasConceptScore W3015597694C159620131 @default.
- W3015597694 hasConceptScore W3015597694C175291020 @default.
- W3015597694 hasConceptScore W3015597694C199360897 @default.
- W3015597694 hasConceptScore W3015597694C2779662365 @default.
- W3015597694 hasConceptScore W3015597694C28490314 @default.
- W3015597694 hasConceptScore W3015597694C33923547 @default.
- W3015597694 hasConceptScore W3015597694C41008148 @default.
- W3015597694 hasConceptScore W3015597694C62520636 @default.
- W3015597694 hasConceptScore W3015597694C76155785 @default.
- W3015597694 hasConceptScore W3015597694C81363708 @default.
- W3015597694 hasLocation W30155976941 @default.
- W3015597694 hasLocation W30155976942 @default.
- W3015597694 hasOpenAccess W3015597694 @default.
- W3015597694 hasPrimaryLocation W30155976941 @default.
- W3015597694 hasRelatedWork W2175746458 @default.
- W3015597694 hasRelatedWork W2732542196 @default.
- W3015597694 hasRelatedWork W2738221750 @default.
- W3015597694 hasRelatedWork W2758063741 @default.
- W3015597694 hasRelatedWork W2760085659 @default.
- W3015597694 hasRelatedWork W2883200793 @default.
- W3015597694 hasRelatedWork W2912288872 @default.
- W3015597694 hasRelatedWork W2940661641 @default.
- W3015597694 hasRelatedWork W3012978760 @default.
- W3015597694 hasRelatedWork W3093612317 @default.
- W3015597694 isParatext "false" @default.
- W3015597694 isRetracted "false" @default.
- W3015597694 magId "3015597694" @default.
- W3015597694 workType "article" @default.