Matches in SemOpenAlex for { <https://semopenalex.org/work/W2893202042> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2893202042 endingPage "57" @default.
- W2893202042 startingPage "47" @default.
- W2893202042 abstract "Weather Recognition plays an important role in our daily lives and many computer vision applications. However, recognizing the weather conditions from a single image remains challenging and has not been studied thoroughly. Generally, most previous works treat weather recognition as a single-label classification task, namely, determining whether an image belongs to a specific weather class or not. This treatment is not always appropriate, since more than one weather conditions may appear simultaneously in a single image. To address this problem, we make the first attempt to view weather recognition as a multi-label classification task, i.e., assigning an image more than one labels according to the displayed weather conditions. Specifically, a CNN–RNN based multi-label classification approach is proposed in this paper. The convolutional neural network (CNN) is extended with a channel-wise attention model to extract the most correlated visual features. The Recurrent Neural Network (RNN) further processes the features and excavates the dependencies among weather classes. Finally, the weather labels are predicted step by step. Besides, we construct two datasets for the weather recognition task and explore the relationships among different weather conditions. Experimental results demonstrate the superiority and effectiveness of the proposed approach. The new constructed datasets will be available at https://github.com/wzgwzg/Multi-Label-Weather-Recognition." @default.
- W2893202042 created "2018-10-05" @default.
- W2893202042 creator A5014425465 @default.
- W2893202042 creator A5018824735 @default.
- W2893202042 creator A5024812719 @default.
- W2893202042 creator A5068918243 @default.
- W2893202042 date "2018-12-01" @default.
- W2893202042 modified "2023-10-05" @default.
- W2893202042 title "A CNN–RNN architecture for multi-label weather recognition" @default.
- W2893202042 cites W1992345060 @default.
- W2893202042 cites W2020048531 @default.
- W2893202042 cites W2052684427 @default.
- W2893202042 cites W2064675550 @default.
- W2893202042 cites W2083366168 @default.
- W2893202042 cites W2221832395 @default.
- W2893202042 cites W2360445881 @default.
- W2893202042 cites W2531468424 @default.
- W2893202042 cites W2564885033 @default.
- W2893202042 cites W2601707599 @default.
- W2893202042 cites W2615981376 @default.
- W2893202042 cites W2773771410 @default.
- W2893202042 cites W2783165089 @default.
- W2893202042 cites W2783231089 @default.
- W2893202042 cites W3128913384 @default.
- W2893202042 doi "https://doi.org/10.1016/j.neucom.2018.09.048" @default.
- W2893202042 hasPublicationYear "2018" @default.
- W2893202042 type Work @default.
- W2893202042 sameAs 2893202042 @default.
- W2893202042 citedByCount "77" @default.
- W2893202042 countsByYear W28932020422019 @default.
- W2893202042 countsByYear W28932020422020 @default.
- W2893202042 countsByYear W28932020422021 @default.
- W2893202042 countsByYear W28932020422022 @default.
- W2893202042 countsByYear W28932020422023 @default.
- W2893202042 crossrefType "journal-article" @default.
- W2893202042 hasAuthorship W2893202042A5014425465 @default.
- W2893202042 hasAuthorship W2893202042A5018824735 @default.
- W2893202042 hasAuthorship W2893202042A5024812719 @default.
- W2893202042 hasAuthorship W2893202042A5068918243 @default.
- W2893202042 hasBestOaLocation W28932020422 @default.
- W2893202042 hasConcept C115961682 @default.
- W2893202042 hasConcept C119857082 @default.
- W2893202042 hasConcept C147168706 @default.
- W2893202042 hasConcept C153180895 @default.
- W2893202042 hasConcept C154945302 @default.
- W2893202042 hasConcept C162324750 @default.
- W2893202042 hasConcept C187736073 @default.
- W2893202042 hasConcept C199360897 @default.
- W2893202042 hasConcept C2780451532 @default.
- W2893202042 hasConcept C2780801425 @default.
- W2893202042 hasConcept C41008148 @default.
- W2893202042 hasConcept C50644808 @default.
- W2893202042 hasConcept C75294576 @default.
- W2893202042 hasConcept C81363708 @default.
- W2893202042 hasConceptScore W2893202042C115961682 @default.
- W2893202042 hasConceptScore W2893202042C119857082 @default.
- W2893202042 hasConceptScore W2893202042C147168706 @default.
- W2893202042 hasConceptScore W2893202042C153180895 @default.
- W2893202042 hasConceptScore W2893202042C154945302 @default.
- W2893202042 hasConceptScore W2893202042C162324750 @default.
- W2893202042 hasConceptScore W2893202042C187736073 @default.
- W2893202042 hasConceptScore W2893202042C199360897 @default.
- W2893202042 hasConceptScore W2893202042C2780451532 @default.
- W2893202042 hasConceptScore W2893202042C2780801425 @default.
- W2893202042 hasConceptScore W2893202042C41008148 @default.
- W2893202042 hasConceptScore W2893202042C50644808 @default.
- W2893202042 hasConceptScore W2893202042C75294576 @default.
- W2893202042 hasConceptScore W2893202042C81363708 @default.
- W2893202042 hasLocation W28932020421 @default.
- W2893202042 hasLocation W28932020422 @default.
- W2893202042 hasOpenAccess W2893202042 @default.
- W2893202042 hasPrimaryLocation W28932020421 @default.
- W2893202042 hasRelatedWork W2742991909 @default.
- W2893202042 hasRelatedWork W2766604260 @default.
- W2893202042 hasRelatedWork W2767651786 @default.
- W2893202042 hasRelatedWork W2912288872 @default.
- W2893202042 hasRelatedWork W2986507176 @default.
- W2893202042 hasRelatedWork W3012393889 @default.
- W2893202042 hasRelatedWork W3021430260 @default.
- W2893202042 hasRelatedWork W3027997911 @default.
- W2893202042 hasRelatedWork W4287776258 @default.
- W2893202042 hasRelatedWork W564581980 @default.
- W2893202042 hasVolume "322" @default.
- W2893202042 isParatext "false" @default.
- W2893202042 isRetracted "false" @default.
- W2893202042 magId "2893202042" @default.
- W2893202042 workType "article" @default.