FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3083885798> ?p ?o ?g. }

• W3083885798 endingPage "2159" @default.
• W3083885798 startingPage "2147" @default.
• W3083885798 abstract "This work presents a gated non-local deep residual learning framework for image deraining. It can avoid the over-deraining or under-deraining caused by the global residual learning in existing deraining networks, since the learned soft gate in our method adaptively adjusts the amount of global residual to be passed for generating the final derained result. To generate feature maps for global residual prediction, we develop a non-local guided attention module (NLAM), which first obtains non-local features by exploiting spatial inter-dependencies among all the feature positions of local features produced by convolutional neural network (CNN), and then leverages the attention mechanism to merge the local and non-local features based on their complementary relation. Moreover, we develop a channel-wise gated prediction module to learn a soft gate on the global residual by explicitly modelling channel inter-dependencies of the feature maps obtained from NLAM. Experiments on four deraining benchmark datasets and real-world rainy images show that our network has a quantitative and qualitative improvement over state-of-the-arts." @default.
• W3083885798 created "2020-09-14" @default.
• W3083885798 creator A5013151488 @default.
• W3083885798 creator A5016081925 @default.
• W3083885798 creator A5027851405 @default.
• W3083885798 creator A5027872024 @default.
• W3083885798 creator A5031202827 @default.
• W3083885798 creator A5032708386 @default.
• W3083885798 creator A5077627006 @default.
• W3083885798 date "2021-06-01" @default.
• W3083885798 modified "2023-09-29" @default.
• W3083885798 title "Learning Gated Non-Local Residual for Single-Image Rain Streak Removal" @default.
• W3083885798 cites W1965572510 @default.
• W3083885798 cites W1992687477 @default.
• W3083885798 cites W2084053957 @default.
• W3083885798 cites W2097073572 @default.
• W3083885798 cites W2113968972 @default.
• W3083885798 cites W2119535410 @default.
• W3083885798 cites W2121396509 @default.
• W3083885798 cites W2133665775 @default.
• W3083885798 cites W2144701150 @default.
• W3083885798 cites W2154621477 @default.
• W3083885798 cites W2154815154 @default.
• W3083885798 cites W2163398148 @default.
• W3083885798 cites W2177195834 @default.
• W3083885798 cites W2194775991 @default.
• W3083885798 cites W2209874411 @default.
• W3083885798 cites W2412782625 @default.
• W3083885798 cites W2466666260 @default.
• W3083885798 cites W2509784253 @default.
• W3083885798 cites W2559264300 @default.
• W3083885798 cites W2740982616 @default.
• W3083885798 cites W2752782242 @default.
• W3083885798 cites W2777170053 @default.
• W3083885798 cites W2798600195 @default.
• W3083885798 cites W2887181327 @default.
• W3083885798 cites W2896911342 @default.
• W3083885798 cites W2912435603 @default.
• W3083885798 cites W2913360047 @default.
• W3083885798 cites W2930755307 @default.
• W3083885798 cites W2954171777 @default.
• W3083885798 cites W2962850830 @default.
• W3083885798 cites W2963017889 @default.
• W3083885798 cites W2963091558 @default.
• W3083885798 cites W2963372104 @default.
• W3083885798 cites W2963800716 @default.
• W3083885798 cites W2963861381 @default.
• W3083885798 cites W2963866045 @default.
• W3083885798 cites W2963878020 @default.
• W3083885798 cites W2964212750 @default.
• W3083885798 cites W2967584026 @default.
• W3083885798 cites W3026432413 @default.
• W3083885798 doi "https://doi.org/10.1109/tcsvt.2020.3022707" @default.
• W3083885798 hasPublicationYear "2021" @default.
• W3083885798 type Work @default.
• W3083885798 sameAs 3083885798 @default.
• W3083885798 citedByCount "29" @default.
• W3083885798 countsByYear W30838857982021 @default.
• W3083885798 countsByYear W30838857982022 @default.
• W3083885798 countsByYear W30838857982023 @default.
• W3083885798 crossrefType "journal-article" @default.
• W3083885798 hasAuthorship W3083885798A5013151488 @default.
• W3083885798 hasAuthorship W3083885798A5016081925 @default.
• W3083885798 hasAuthorship W3083885798A5027851405 @default.
• W3083885798 hasAuthorship W3083885798A5027872024 @default.
• W3083885798 hasAuthorship W3083885798A5031202827 @default.
• W3083885798 hasAuthorship W3083885798A5032708386 @default.
• W3083885798 hasAuthorship W3083885798A5077627006 @default.
• W3083885798 hasConcept C11413529 @default.
• W3083885798 hasConcept C120665830 @default.
• W3083885798 hasConcept C121332964 @default.
• W3083885798 hasConcept C13280743 @default.
• W3083885798 hasConcept C138885662 @default.
• W3083885798 hasConcept C153180895 @default.
• W3083885798 hasConcept C154945302 @default.
• W3083885798 hasConcept C155512373 @default.
• W3083885798 hasConcept C185798385 @default.
• W3083885798 hasConcept C197129107 @default.
• W3083885798 hasConcept C205649164 @default.
• W3083885798 hasConcept C23123220 @default.
• W3083885798 hasConcept C2776401178 @default.
• W3083885798 hasConcept C41008148 @default.
• W3083885798 hasConcept C41895202 @default.
• W3083885798 hasConcept C52622490 @default.
• W3083885798 hasConcept C65185188 @default.
• W3083885798 hasConcept C81363708 @default.
• W3083885798 hasConceptScore W3083885798C11413529 @default.
• W3083885798 hasConceptScore W3083885798C120665830 @default.
• W3083885798 hasConceptScore W3083885798C121332964 @default.
• W3083885798 hasConceptScore W3083885798C13280743 @default.
• W3083885798 hasConceptScore W3083885798C138885662 @default.
• W3083885798 hasConceptScore W3083885798C153180895 @default.
• W3083885798 hasConceptScore W3083885798C154945302 @default.
• W3083885798 hasConceptScore W3083885798C155512373 @default.
• W3083885798 hasConceptScore W3083885798C185798385 @default.
• W3083885798 hasConceptScore W3083885798C197129107 @default.
• W3083885798 hasConceptScore W3083885798C205649164 @default.
• W3083885798 hasConceptScore W3083885798C23123220 @default.

• next