Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386808218> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4386808218 endingPage "107093" @default.
- W4386808218 startingPage "107093" @default.
- W4386808218 abstract "Automatically counting fish in sonar images has been attracting increasing attention in recent years because extreme efforts are needed in manual counting. Density map regression provides a promising approach in the counting field, but two obstacles are placed in front of fish counting in low resolution sonar images: the difficulty in distinguishing fish from the similar background noise and the inconsistency between the strip-shaped fishes in input images and dot-shaped ground truth density map. To address these issues, we present GPNet, a novel encoder-decoder network with global attention and point supervision, to boost sonar image-based fish counting accuracy. To alleviate the impact of background noise, we incorporate a segmentation module (SM) with global self-attention to the neck of the network to identify the fish region and space out background noise. Furthermore, feature enhancement modules (FEM) with a global receptive field are introduced to the encoder to enhance the feature representation and discrimination. To break down the performance upper bound resulting from target shape inconsistency between input and ground truth, we leverage fish center coordinates instead of the Gaussian density map to supervise the network training directly. Extensive experiments on a challenging public sonar image-based fish counting dataset, the ARIS dataset, demonstrate that GPNet achieves state-of-the-art performance both in counting accuracy and noise removal." @default.
- W4386808218 created "2023-09-17" @default.
- W4386808218 creator A5000446896 @default.
- W4386808218 creator A5005105786 @default.
- W4386808218 creator A5011189615 @default.
- W4386808218 creator A5011665118 @default.
- W4386808218 creator A5018841457 @default.
- W4386808218 creator A5046826631 @default.
- W4386808218 date "2023-11-01" @default.
- W4386808218 modified "2023-09-27" @default.
- W4386808218 title "Boosting fish counting in sonar images with global attention and point supervision" @default.
- W4386808218 cites W2023965496 @default.
- W4386808218 cites W2060005852 @default.
- W4386808218 cites W2133665775 @default.
- W4386808218 cites W2602078164 @default.
- W4386808218 cites W2748700684 @default.
- W4386808218 cites W2947929494 @default.
- W4386808218 cites W2963420686 @default.
- W4386808218 cites W2966893608 @default.
- W4386808218 cites W2998193888 @default.
- W4386808218 cites W3041430445 @default.
- W4386808218 cites W3084883754 @default.
- W4386808218 cites W3102632104 @default.
- W4386808218 cites W3132588545 @default.
- W4386808218 cites W3155371711 @default.
- W4386808218 cites W3159207138 @default.
- W4386808218 cites W3209526300 @default.
- W4386808218 cites W4205396300 @default.
- W4386808218 cites W4207050521 @default.
- W4386808218 cites W4210655134 @default.
- W4386808218 cites W4281743493 @default.
- W4386808218 cites W4282939170 @default.
- W4386808218 cites W4283690791 @default.
- W4386808218 cites W4292859076 @default.
- W4386808218 cites W4293723966 @default.
- W4386808218 cites W4296739197 @default.
- W4386808218 cites W4306955321 @default.
- W4386808218 cites W4317566866 @default.
- W4386808218 doi "https://doi.org/10.1016/j.engappai.2023.107093" @default.
- W4386808218 hasPublicationYear "2023" @default.
- W4386808218 type Work @default.
- W4386808218 citedByCount "0" @default.
- W4386808218 crossrefType "journal-article" @default.
- W4386808218 hasAuthorship W4386808218A5000446896 @default.
- W4386808218 hasAuthorship W4386808218A5005105786 @default.
- W4386808218 hasAuthorship W4386808218A5011189615 @default.
- W4386808218 hasAuthorship W4386808218A5011665118 @default.
- W4386808218 hasAuthorship W4386808218A5018841457 @default.
- W4386808218 hasAuthorship W4386808218A5046826631 @default.
- W4386808218 hasConcept C115961682 @default.
- W4386808218 hasConcept C146849305 @default.
- W4386808218 hasConcept C153083717 @default.
- W4386808218 hasConcept C153180895 @default.
- W4386808218 hasConcept C154945302 @default.
- W4386808218 hasConcept C31972630 @default.
- W4386808218 hasConcept C41008148 @default.
- W4386808218 hasConcept C555745239 @default.
- W4386808218 hasConcept C89600930 @default.
- W4386808218 hasConcept C99498987 @default.
- W4386808218 hasConceptScore W4386808218C115961682 @default.
- W4386808218 hasConceptScore W4386808218C146849305 @default.
- W4386808218 hasConceptScore W4386808218C153083717 @default.
- W4386808218 hasConceptScore W4386808218C153180895 @default.
- W4386808218 hasConceptScore W4386808218C154945302 @default.
- W4386808218 hasConceptScore W4386808218C31972630 @default.
- W4386808218 hasConceptScore W4386808218C41008148 @default.
- W4386808218 hasConceptScore W4386808218C555745239 @default.
- W4386808218 hasConceptScore W4386808218C89600930 @default.
- W4386808218 hasConceptScore W4386808218C99498987 @default.
- W4386808218 hasFunder F4320335777 @default.
- W4386808218 hasLocation W43868082181 @default.
- W4386808218 hasOpenAccess W4386808218 @default.
- W4386808218 hasPrimaryLocation W43868082181 @default.
- W4386808218 hasRelatedWork W1669643531 @default.
- W4386808218 hasRelatedWork W1982826852 @default.
- W4386808218 hasRelatedWork W2005437358 @default.
- W4386808218 hasRelatedWork W2008656436 @default.
- W4386808218 hasRelatedWork W2023558673 @default.
- W4386808218 hasRelatedWork W2110230079 @default.
- W4386808218 hasRelatedWork W2134924024 @default.
- W4386808218 hasRelatedWork W2517104666 @default.
- W4386808218 hasRelatedWork W2613186388 @default.
- W4386808218 hasRelatedWork W1967061043 @default.
- W4386808218 hasVolume "126" @default.
- W4386808218 isParatext "false" @default.
- W4386808218 isRetracted "false" @default.
- W4386808218 workType "article" @default.