FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3182849571> ?p ?o ?g. }

• W3182849571 endingPage "2314" @default.
• W3182849571 startingPage "2303" @default.
• W3182849571 abstract "In recent years, marine animal study has gained increasing research attention, which raises significant demands for fine-grained marine animal segmentation (MAS) techniques. In addition, deep learning has been widely adopted for object segmentation and has achieved promising performance. However, deep-based MAS is still lack of investigation due to the shortage of a large-scale MAS dataset. To tackle this issue, we construct the first large-scale MAS dataset, called <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>MAS3K</i> , which consists of 3,103 images from different types, including camouflaged marine animal images, common marine animal images, and underwater images without marine animals. Furthermore, we consider different underwater conditions, such as low illumination, turbid water quality, photographic distortion, etc. Each image from <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>MAS3K</i> dataset has rich annotations, including an object-level mask, a category name, attributes, and a camouflage method (if applicable). Furthermore, we propose a novel MAS network, called Enhanced Cascade Decoder Network ( <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>ECD-Net</i> ), which consists of multiple Interactive Feature Enhancement Modules (IFEMs) and Cascade Decoder Modules (CDMs). In <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>ECD-Net</i> , the IFEMs are first utilized to extract rich multi-scale features. The resulting features are then fed to the CDMs for accurately segmenting marine animals from complex underwater environments. We perform extensive experiments to compare <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>ECD-Net</i> with 10 cutting-edge object segmentation models. The results demonstrate that <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>ECD-Net</i> is an effective MAS model and outperforms the cutting-edge models, both qualitatively and quantitatively." @default.
• W3182849571 created "2021-07-19" @default.
• W3182849571 creator A5029633264 @default.
• W3182849571 creator A5041974744 @default.
• W3182849571 creator A5047423420 @default.
• W3182849571 creator A5061274720 @default.
• W3182849571 creator A5062640176 @default.
• W3182849571 creator A5081513423 @default.
• W3182849571 date "2022-04-01" @default.
• W3182849571 modified "2023-10-11" @default.
• W3182849571 title "Marine Animal Segmentation" @default.
• W3182849571 cites W1903029394 @default.
• W3182849571 cites W1965718792 @default.
• W3182849571 cites W1976263166 @default.
• W3182849571 cites W1982075130 @default.
• W3182849571 cites W1982938587 @default.
• W3182849571 cites W1988671035 @default.
• W3182849571 cites W1994922096 @default.
• W3182849571 cites W1994968521 @default.
• W3182849571 cites W2001235318 @default.
• W3182849571 cites W2002781701 @default.
• W3182849571 cites W2012420567 @default.
• W3182849571 cites W2039313011 @default.
• W3182849571 cites W2055447163 @default.
• W3182849571 cites W2108598243 @default.
• W3182849571 cites W2124477965 @default.
• W3182849571 cites W2171378720 @default.
• W3182849571 cites W2194775991 @default.
• W3182849571 cites W2313538785 @default.
• W3182849571 cites W2317160870 @default.
• W3182849571 cites W2525286916 @default.
• W3182849571 cites W2561698828 @default.
• W3182849571 cites W2570343428 @default.
• W3182849571 cites W2596058005 @default.
• W3182849571 cites W2615981376 @default.
• W3182849571 cites W2728026583 @default.
• W3182849571 cites W2728766668 @default.
• W3182849571 cites W2740667773 @default.
• W3182849571 cites W2752646460 @default.
• W3182849571 cites W2768594928 @default.
• W3182849571 cites W2793668851 @default.
• W3182849571 cites W2884436604 @default.
• W3182849571 cites W2916798096 @default.
• W3182849571 cites W2939217524 @default.
• W3182849571 cites W2943545929 @default.
• W3182849571 cites W2948400274 @default.
• W3182849571 cites W2953029132 @default.
• W3182849571 cites W2961348656 @default.
• W3182849571 cites W2963112696 @default.
• W3182849571 cites W2963334022 @default.
• W3182849571 cites W2963529609 @default.
• W3182849571 cites W2963685207 @default.
• W3182849571 cites W2963868681 @default.
• W3182849571 cites W2987701848 @default.
• W3182849571 cites W2989161706 @default.
• W3182849571 cites W2990176100 @default.
• W3182849571 cites W2990984982 @default.
• W3182849571 cites W2997169099 @default.
• W3182849571 cites W2997408160 @default.
• W3182849571 cites W2998449272 @default.
• W3182849571 cites W3025800305 @default.
• W3182849571 cites W3027763298 @default.
• W3182849571 cites W3034684132 @default.
• W3182849571 cites W3035422681 @default.
• W3182849571 cites W3039108591 @default.
• W3182849571 cites W3092344722 @default.
• W3182849571 cites W3092933908 @default.
• W3182849571 cites W3095367607 @default.
• W3182849571 cites W3099562471 @default.
• W3182849571 cites W3104979525 @default.
• W3182849571 cites W3125478936 @default.
• W3182849571 cites W3132413796 @default.
• W3182849571 cites W3132455321 @default.
• W3182849571 cites W3190335749 @default.
• W3182849571 cites W4239147634 @default.
• W3182849571 doi "https://doi.org/10.1109/tcsvt.2021.3093890" @default.
• W3182849571 hasPublicationYear "2022" @default.
• W3182849571 type Work @default.
• W3182849571 sameAs 3182849571 @default.
• W3182849571 citedByCount "11" @default.
• W3182849571 countsByYear W31828495712022 @default.
• W3182849571 countsByYear W31828495712023 @default.
• W3182849571 crossrefType "journal-article" @default.
• W3182849571 hasAuthorship W3182849571A5029633264 @default.
• W3182849571 hasAuthorship W3182849571A5041974744 @default.
• W3182849571 hasAuthorship W3182849571A5047423420 @default.
• W3182849571 hasAuthorship W3182849571A5061274720 @default.
• W3182849571 hasAuthorship W3182849571A5062640176 @default.
• W3182849571 hasAuthorship W3182849571A5081513423 @default.
• W3182849571 hasConcept C153180895 @default.
• W3182849571 hasConcept C154945302 @default.
• W3182849571 hasConcept C205649164 @default.
• W3182849571 hasConcept C2778755073 @default.
• W3182849571 hasConcept C41008148 @default.
• W3182849571 hasConcept C58640448 @default.
• W3182849571 hasConcept C89600930 @default.
• W3182849571 hasConceptScore W3182849571C153180895 @default.
• W3182849571 hasConceptScore W3182849571C154945302 @default.

• next