Matches in SemOpenAlex for { <https://semopenalex.org/work/W3154170247> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3154170247 endingPage "24" @default.
- W3154170247 startingPage "12" @default.
- W3154170247 abstract "• A novel framework is proposed to deal with crowd counting in dense scenarios. • We adopt a multi-scale fusion strategy, which is built upon dilated convolution. • An attention mechanism is introduced to concentrate on crowd regions. In this paper, we propose an attention-guided multi-scale fusion network (named as AMS-Net) for crowd counting in dense scenarios. The overall model is mainly comprised by the density and the attention networks. The density network is able to provide a coarse prediction of the crowd distribution (density map), while the attention network helps to distinguish crowded regions from backgrounds. The output of the attention network serves as a mask of the coarse density map. The number of persons in the scene is finally estimated by applying integration on the refined density map. In order to deal with persons of varied resolutions, we introduce a multi-scale fusion strategy which is built upon dilated convolution. Experiments are carried out on the standard benchmark datasets, covering varied over-crowded scenarios. Experimental results demonstrate the effectiveness of the proposed approach." @default.
- W3154170247 created "2021-04-26" @default.
- W3154170247 creator A5000273221 @default.
- W3154170247 creator A5039907870 @default.
- W3154170247 creator A5043018796 @default.
- W3154170247 creator A5082773210 @default.
- W3154170247 creator A5087542455 @default.
- W3154170247 date "2021-09-01" @default.
- W3154170247 modified "2023-10-02" @default.
- W3154170247 title "Crowd counting based on attention-guided multi-scale fusion networks" @default.
- W3154170247 cites W2036536917 @default.
- W3154170247 cites W2325880033 @default.
- W3154170247 cites W2435426355 @default.
- W3154170247 cites W2729018917 @default.
- W3154170247 cites W2897819140 @default.
- W3154170247 cites W2899438351 @default.
- W3154170247 cites W2962832028 @default.
- W3154170247 cites W2963460857 @default.
- W3154170247 cites W2987468779 @default.
- W3154170247 cites W2994401994 @default.
- W3154170247 cites W3002638829 @default.
- W3154170247 cites W3097305524 @default.
- W3154170247 doi "https://doi.org/10.1016/j.neucom.2021.04.045" @default.
- W3154170247 hasPublicationYear "2021" @default.
- W3154170247 type Work @default.
- W3154170247 sameAs 3154170247 @default.
- W3154170247 citedByCount "11" @default.
- W3154170247 countsByYear W31541702472022 @default.
- W3154170247 countsByYear W31541702472023 @default.
- W3154170247 crossrefType "journal-article" @default.
- W3154170247 hasAuthorship W3154170247A5000273221 @default.
- W3154170247 hasAuthorship W3154170247A5039907870 @default.
- W3154170247 hasAuthorship W3154170247A5043018796 @default.
- W3154170247 hasAuthorship W3154170247A5082773210 @default.
- W3154170247 hasAuthorship W3154170247A5087542455 @default.
- W3154170247 hasConcept C105795698 @default.
- W3154170247 hasConcept C119857082 @default.
- W3154170247 hasConcept C121332964 @default.
- W3154170247 hasConcept C124101348 @default.
- W3154170247 hasConcept C13280743 @default.
- W3154170247 hasConcept C138885662 @default.
- W3154170247 hasConcept C153180895 @default.
- W3154170247 hasConcept C154945302 @default.
- W3154170247 hasConcept C158525013 @default.
- W3154170247 hasConcept C185429906 @default.
- W3154170247 hasConcept C185798385 @default.
- W3154170247 hasConcept C189508267 @default.
- W3154170247 hasConcept C205649164 @default.
- W3154170247 hasConcept C2778755073 @default.
- W3154170247 hasConcept C33923547 @default.
- W3154170247 hasConcept C41008148 @default.
- W3154170247 hasConcept C41895202 @default.
- W3154170247 hasConcept C45347329 @default.
- W3154170247 hasConcept C50644808 @default.
- W3154170247 hasConcept C62520636 @default.
- W3154170247 hasConceptScore W3154170247C105795698 @default.
- W3154170247 hasConceptScore W3154170247C119857082 @default.
- W3154170247 hasConceptScore W3154170247C121332964 @default.
- W3154170247 hasConceptScore W3154170247C124101348 @default.
- W3154170247 hasConceptScore W3154170247C13280743 @default.
- W3154170247 hasConceptScore W3154170247C138885662 @default.
- W3154170247 hasConceptScore W3154170247C153180895 @default.
- W3154170247 hasConceptScore W3154170247C154945302 @default.
- W3154170247 hasConceptScore W3154170247C158525013 @default.
- W3154170247 hasConceptScore W3154170247C185429906 @default.
- W3154170247 hasConceptScore W3154170247C185798385 @default.
- W3154170247 hasConceptScore W3154170247C189508267 @default.
- W3154170247 hasConceptScore W3154170247C205649164 @default.
- W3154170247 hasConceptScore W3154170247C2778755073 @default.
- W3154170247 hasConceptScore W3154170247C33923547 @default.
- W3154170247 hasConceptScore W3154170247C41008148 @default.
- W3154170247 hasConceptScore W3154170247C41895202 @default.
- W3154170247 hasConceptScore W3154170247C45347329 @default.
- W3154170247 hasConceptScore W3154170247C50644808 @default.
- W3154170247 hasConceptScore W3154170247C62520636 @default.
- W3154170247 hasFunder F4320321001 @default.
- W3154170247 hasLocation W31541702471 @default.
- W3154170247 hasOpenAccess W3154170247 @default.
- W3154170247 hasPrimaryLocation W31541702471 @default.
- W3154170247 hasRelatedWork W112744582 @default.
- W3154170247 hasRelatedWork W1485630101 @default.
- W3154170247 hasRelatedWork W172869079 @default.
- W3154170247 hasRelatedWork W1728708896 @default.
- W3154170247 hasRelatedWork W2183228276 @default.
- W3154170247 hasRelatedWork W2498017833 @default.
- W3154170247 hasRelatedWork W2554078916 @default.
- W3154170247 hasRelatedWork W2961085424 @default.
- W3154170247 hasRelatedWork W4293731510 @default.
- W3154170247 hasRelatedWork W4306674287 @default.
- W3154170247 hasVolume "451" @default.
- W3154170247 isParatext "false" @default.
- W3154170247 isRetracted "false" @default.
- W3154170247 magId "3154170247" @default.
- W3154170247 workType "article" @default.