FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313139043> ?p ?o ?g. }

• W4313139043 endingPage "2905" @default.
• W4313139043 startingPage "2892" @default.
• W4313139043 abstract "Similar to other multi-modal pixel-level prediction tasks, existing RGB-T semantic segmentation methods usually employ a two-stream structure to extract RGB and thermal infrared (TIR) features, respectively, and adopt the same fusion strategies to integrate different levels of unimodal features. This will result in inadequate extraction of unimodal features and exploitation of cross-modal information from the paired RGB and TIR images. Alternatively, in this paper, we present a novel RGB-T semantic segmentation model, i.e., FDCNet, where a feature divide-and-conquer strategy performs unimodal feature extraction and cross-modal feature fusion in one go. Concretely, we first employ a two-stream structure to extract unimodal low-level features, followed by a Siamese structure to extract unimodal high-level features from the paired RGB and TIR images. This concise but efficient structure enables to take into account both the modality discrepancies of low-level features and the underlying semantic consistency of high-level features across the paired RGB and TIR images. Furthermore, considering the characteristics of different layers of features, a Cross-modal Spatial Activation (CSA) module and a Cross-modal Channel Activation (CCA) module are presented for the fusion of low-level RGB and TIR features and for the fusion of high-level RGB and TIR features, respectively, thus facilitating the capture of cross-modal information. On top of that, with an embedded Cross-scale Interaction Context (CIC) module for mining multi-scale contextual information, our proposed model (i.e., FDCNet) for RGB-T semantic segmentation achieves new state-of-the-art experimental results on MFNet dataset and PST900 dataset." @default.
• W4313139043 created "2023-01-06" @default.
• W4313139043 creator A5017213221 @default.
• W4313139043 creator A5087790071 @default.
• W4313139043 date "2023-06-01" @default.
• W4313139043 modified "2023-09-27" @default.
• W4313139043 title "A Feature Divide-and-Conquer Network for RGB-T Semantic Segmentation" @default.
• W4313139043 cites W1903029394 @default.
• W4313139043 cites W1994616650 @default.
• W4313139043 cites W2194775991 @default.
• W4313139043 cites W2340897893 @default.
• W4313139043 cites W2412782625 @default.
• W4313139043 cites W2485522583 @default.
• W4313139043 cites W2560023338 @default.
• W4313139043 cites W2563705555 @default.
• W4313139043 cites W2584009249 @default.
• W4313139043 cites W2774839435 @default.
• W4313139043 cites W2775906317 @default.
• W4313139043 cites W2799213142 @default.
• W4313139043 cites W2916798096 @default.
• W4313139043 cites W2921749009 @default.
• W4313139043 cites W2949579494 @default.
• W4313139043 cites W2955058313 @default.
• W4313139043 cites W2963091558 @default.
• W4313139043 cites W2963881378 @default.
• W4313139043 cites W2963896186 @default.
• W4313139043 cites W2971014764 @default.
• W4313139043 cites W2998449272 @default.
• W4313139043 cites W3010616503 @default.
• W4313139043 cites W3033020497 @default.
• W4313139043 cites W3035284915 @default.
• W4313139043 cites W3035807818 @default.
• W4313139043 cites W3045052737 @default.
• W4313139043 cites W3047800102 @default.
• W4313139043 cites W3048402753 @default.
• W4313139043 cites W3049194477 @default.
• W4313139043 cites W3091001089 @default.
• W4313139043 cites W3106587394 @default.
• W4313139043 cites W3135874576 @default.
• W4313139043 cites W3137799923 @default.
• W4313139043 cites W3138511503 @default.
• W4313139043 cites W3159018159 @default.
• W4313139043 cites W3166016280 @default.
• W4313139043 cites W3170841864 @default.
• W4313139043 cites W3185043317 @default.
• W4313139043 cites W3194841206 @default.
• W4313139043 cites W3195411577 @default.
• W4313139043 cites W3202407433 @default.
• W4313139043 cites W3203079214 @default.
• W4313139043 cites W3206439726 @default.
• W4313139043 cites W4200635035 @default.
• W4313139043 cites W4205262979 @default.
• W4313139043 cites W4212987071 @default.
• W4313139043 cites W4214893857 @default.
• W4313139043 doi "https://doi.org/10.1109/tcsvt.2022.3229359" @default.
• W4313139043 hasPublicationYear "2023" @default.
• W4313139043 type Work @default.
• W4313139043 citedByCount "0" @default.
• W4313139043 crossrefType "journal-article" @default.
• W4313139043 hasAuthorship W4313139043A5017213221 @default.
• W4313139043 hasAuthorship W4313139043A5087790071 @default.
• W4313139043 hasConcept C138885662 @default.
• W4313139043 hasConcept C153180895 @default.
• W4313139043 hasConcept C154945302 @default.
• W4313139043 hasConcept C185592680 @default.
• W4313139043 hasConcept C188027245 @default.
• W4313139043 hasConcept C2776401178 @default.
• W4313139043 hasConcept C31972630 @default.
• W4313139043 hasConcept C41008148 @default.
• W4313139043 hasConcept C41895202 @default.
• W4313139043 hasConcept C52622490 @default.
• W4313139043 hasConcept C71139939 @default.
• W4313139043 hasConcept C82990744 @default.
• W4313139043 hasConcept C89600930 @default.
• W4313139043 hasConceptScore W4313139043C138885662 @default.
• W4313139043 hasConceptScore W4313139043C153180895 @default.
• W4313139043 hasConceptScore W4313139043C154945302 @default.
• W4313139043 hasConceptScore W4313139043C185592680 @default.
• W4313139043 hasConceptScore W4313139043C188027245 @default.
• W4313139043 hasConceptScore W4313139043C2776401178 @default.
• W4313139043 hasConceptScore W4313139043C31972630 @default.
• W4313139043 hasConceptScore W4313139043C41008148 @default.
• W4313139043 hasConceptScore W4313139043C41895202 @default.
• W4313139043 hasConceptScore W4313139043C52622490 @default.
• W4313139043 hasConceptScore W4313139043C71139939 @default.
• W4313139043 hasConceptScore W4313139043C82990744 @default.
• W4313139043 hasConceptScore W4313139043C89600930 @default.
• W4313139043 hasFunder F4320321001 @default.
• W4313139043 hasIssue "6" @default.
• W4313139043 hasLocation W43131390431 @default.
• W4313139043 hasOpenAccess W4313139043 @default.
• W4313139043 hasPrimaryLocation W43131390431 @default.
• W4313139043 hasRelatedWork W2016461833 @default.
• W4313139043 hasRelatedWork W2134924024 @default.
• W4313139043 hasRelatedWork W2241457321 @default.
• W4313139043 hasRelatedWork W2534909612 @default.
• W4313139043 hasRelatedWork W2546942002 @default.
• W4313139043 hasRelatedWork W2558375057 @default.

• next