Matches in SemOpenAlex for { <https://semopenalex.org/work/W2975641008> ?p ?o ?g. }
- W2975641008 endingPage "140689" @default.
- W2975641008 startingPage "140680" @default.
- W2975641008 abstract "Remarkable success has been made by deep convolutional neural network (CNN) models in semantic image segmentation. However, most segmentation models are based on classification networks which tend to learn image-level features and lost abundant spatial information due to repeated pooling and downsampling operations, and the CNN-based methods are not robust to inputs, hence directly applying existing segmentation methods to semantic video segmentation will result in spatially inconsecutive and temporally inconsistent segmentation predictions within one instance and of the same objects across adjacent frames, respectively. To tackle this challenge, we propose an Attention-Guided Network (AGNet) to adaptively strengthen inter-frame and intra-frame features for more precise segmentation predictions. Specifically, we append an adjacent attention module (AAM) and a spatial attention module (SAM) on the top of dilated fully convolutional network (FCN), which model the feature correlations in temporal and spatial dimensions, respectively. The AAM selectively enhances the inter-frame features of the same objects across adjacent frames for temporally consistent predictions. Meanwhile, the SAM selectively aggregates the intra-frame features within one instance for spatially consecutive predictions. Finally, we sum the outputs of the two attention modules to further improve feature representations which contribute to more precise segmentation predictions across temporal and spatial dimensions simultaneously. Extensive experiments demonstrate the effectiveness of the proposed method, obtaining state-of-the-art mean intersection of union (mIoU) of 75.22% on CamVid dataset." @default.
- W2975641008 created "2019-10-03" @default.
- W2975641008 creator A5030441449 @default.
- W2975641008 creator A5035282947 @default.
- W2975641008 creator A5048093695 @default.
- W2975641008 creator A5052614612 @default.
- W2975641008 creator A5074215202 @default.
- W2975641008 date "2019-01-01" @default.
- W2975641008 modified "2023-10-02" @default.
- W2975641008 title "Attention-Guided Network for Semantic Video Segmentation" @default.
- W2975641008 cites W1536680647 @default.
- W2975641008 cites W1903029394 @default.
- W2975641008 cites W1913356549 @default.
- W2975641008 cites W2080142539 @default.
- W2975641008 cites W2085625911 @default.
- W2975641008 cites W2097117768 @default.
- W2975641008 cites W2109255472 @default.
- W2975641008 cites W2194775991 @default.
- W2975641008 cites W2342491128 @default.
- W2975641008 cites W2358876993 @default.
- W2975641008 cites W2412782625 @default.
- W2975641008 cites W2552900565 @default.
- W2975641008 cites W2560023338 @default.
- W2975641008 cites W2561585794 @default.
- W2975641008 cites W2798791840 @default.
- W2975641008 cites W2799217622 @default.
- W2975641008 cites W2884490794 @default.
- W2975641008 cites W2886934227 @default.
- W2975641008 cites W2890455694 @default.
- W2975641008 cites W2901710089 @default.
- W2975641008 cites W2962815021 @default.
- W2975641008 cites W2963019093 @default.
- W2975641008 cites W2963445119 @default.
- W2975641008 cites W2963727650 @default.
- W2975641008 cites W2963881378 @default.
- W2975641008 cites W2963917006 @default.
- W2975641008 cites W2964309882 @default.
- W2975641008 cites W764651262 @default.
- W2975641008 doi "https://doi.org/10.1109/access.2019.2943365" @default.
- W2975641008 hasPublicationYear "2019" @default.
- W2975641008 type Work @default.
- W2975641008 sameAs 2975641008 @default.
- W2975641008 citedByCount "14" @default.
- W2975641008 countsByYear W29756410082020 @default.
- W2975641008 countsByYear W29756410082021 @default.
- W2975641008 countsByYear W29756410082022 @default.
- W2975641008 countsByYear W29756410082023 @default.
- W2975641008 crossrefType "journal-article" @default.
- W2975641008 hasAuthorship W2975641008A5030441449 @default.
- W2975641008 hasAuthorship W2975641008A5035282947 @default.
- W2975641008 hasAuthorship W2975641008A5048093695 @default.
- W2975641008 hasAuthorship W2975641008A5052614612 @default.
- W2975641008 hasAuthorship W2975641008A5074215202 @default.
- W2975641008 hasBestOaLocation W29756410081 @default.
- W2975641008 hasConcept C110384440 @default.
- W2975641008 hasConcept C115961682 @default.
- W2975641008 hasConcept C124504099 @default.
- W2975641008 hasConcept C126042441 @default.
- W2975641008 hasConcept C138885662 @default.
- W2975641008 hasConcept C153180895 @default.
- W2975641008 hasConcept C154945302 @default.
- W2975641008 hasConcept C205649164 @default.
- W2975641008 hasConcept C2776401178 @default.
- W2975641008 hasConcept C31972630 @default.
- W2975641008 hasConcept C41008148 @default.
- W2975641008 hasConcept C41895202 @default.
- W2975641008 hasConcept C58640448 @default.
- W2975641008 hasConcept C64543145 @default.
- W2975641008 hasConcept C65885262 @default.
- W2975641008 hasConcept C70437156 @default.
- W2975641008 hasConcept C76155785 @default.
- W2975641008 hasConcept C81363708 @default.
- W2975641008 hasConcept C89600930 @default.
- W2975641008 hasConceptScore W2975641008C110384440 @default.
- W2975641008 hasConceptScore W2975641008C115961682 @default.
- W2975641008 hasConceptScore W2975641008C124504099 @default.
- W2975641008 hasConceptScore W2975641008C126042441 @default.
- W2975641008 hasConceptScore W2975641008C138885662 @default.
- W2975641008 hasConceptScore W2975641008C153180895 @default.
- W2975641008 hasConceptScore W2975641008C154945302 @default.
- W2975641008 hasConceptScore W2975641008C205649164 @default.
- W2975641008 hasConceptScore W2975641008C2776401178 @default.
- W2975641008 hasConceptScore W2975641008C31972630 @default.
- W2975641008 hasConceptScore W2975641008C41008148 @default.
- W2975641008 hasConceptScore W2975641008C41895202 @default.
- W2975641008 hasConceptScore W2975641008C58640448 @default.
- W2975641008 hasConceptScore W2975641008C64543145 @default.
- W2975641008 hasConceptScore W2975641008C65885262 @default.
- W2975641008 hasConceptScore W2975641008C70437156 @default.
- W2975641008 hasConceptScore W2975641008C76155785 @default.
- W2975641008 hasConceptScore W2975641008C81363708 @default.
- W2975641008 hasConceptScore W2975641008C89600930 @default.
- W2975641008 hasFunder F4320321001 @default.
- W2975641008 hasFunder F4320322919 @default.
- W2975641008 hasLocation W29756410081 @default.
- W2975641008 hasLocation W29756410082 @default.
- W2975641008 hasOpenAccess W2975641008 @default.
- W2975641008 hasPrimaryLocation W29756410081 @default.