Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384283544> ?p ?o ?g. }
- W4384283544 endingPage "126559" @default.
- W4384283544 startingPage "126559" @default.
- W4384283544 abstract "Shadows observed in practical scenes have complex shapes, and removing them is a very challenging task in computer vision. In particular, previous studies on complex shadow removal have limitations in that they can be learned only on paired datasets. Taking the issues into consideration, we present a new domain-adaptive shadow removal framework. The proposed approach includes domain adaptation, detection, and removal stages. The shadow-preserving domain translator in the first stage compensates for the lack of real data through domain transformation of the synthetic data. In the second stage, efficient shadow detection is performed through the domain adaptive mean teacher network. Last, a novel attention network removes complex shadows using detected shadows as a query, effectively removing complex shadows. The feasibility and effectiveness of the proposed framework are validated through the newly collected Grand Theft Auto-Road Shadow dataset. The proposed method outperforms existing methods for quantitative and qualitative metrics related to shadow detection and removal." @default.
- W4384283544 created "2023-07-15" @default.
- W4384283544 creator A5003130992 @default.
- W4384283544 creator A5015493373 @default.
- W4384283544 creator A5079659183 @default.
- W4384283544 creator A5081937055 @default.
- W4384283544 date "2023-10-01" @default.
- W4384283544 modified "2023-10-12" @default.
- W4384283544 title "Domain Adaptation for Complex Shadow Removal with Shadow Transformer Network" @default.
- W4384283544 cites W1432573875 @default.
- W4384283544 cites W1541667274 @default.
- W4384283544 cites W1816614560 @default.
- W4384283544 cites W1901129140 @default.
- W4384283544 cites W2003145026 @default.
- W4384283544 cites W2166502676 @default.
- W4384283544 cites W2252355370 @default.
- W4384283544 cites W2603203130 @default.
- W4384283544 cites W2963983207 @default.
- W4384283544 cites W2966588426 @default.
- W4384283544 cites W2999921958 @default.
- W4384283544 cites W3000647798 @default.
- W4384283544 cites W3012120793 @default.
- W4384283544 cites W3048323238 @default.
- W4384283544 cites W3106250896 @default.
- W4384283544 cites W3118389845 @default.
- W4384283544 cites W3153897875 @default.
- W4384283544 cites W4283815594 @default.
- W4384283544 cites W4312549046 @default.
- W4384283544 doi "https://doi.org/10.1016/j.neucom.2023.126559" @default.
- W4384283544 hasPublicationYear "2023" @default.
- W4384283544 type Work @default.
- W4384283544 citedByCount "0" @default.
- W4384283544 crossrefType "journal-article" @default.
- W4384283544 hasAuthorship W4384283544A5003130992 @default.
- W4384283544 hasAuthorship W4384283544A5015493373 @default.
- W4384283544 hasAuthorship W4384283544A5079659183 @default.
- W4384283544 hasAuthorship W4384283544A5081937055 @default.
- W4384283544 hasConcept C104317684 @default.
- W4384283544 hasConcept C117797892 @default.
- W4384283544 hasConcept C120665830 @default.
- W4384283544 hasConcept C121332964 @default.
- W4384283544 hasConcept C124101348 @default.
- W4384283544 hasConcept C134306372 @default.
- W4384283544 hasConcept C139807058 @default.
- W4384283544 hasConcept C153180895 @default.
- W4384283544 hasConcept C154945302 @default.
- W4384283544 hasConcept C15744967 @default.
- W4384283544 hasConcept C162324750 @default.
- W4384283544 hasConcept C185592680 @default.
- W4384283544 hasConcept C187736073 @default.
- W4384283544 hasConcept C204241405 @default.
- W4384283544 hasConcept C2776434776 @default.
- W4384283544 hasConcept C2780451532 @default.
- W4384283544 hasConcept C31972630 @default.
- W4384283544 hasConcept C33923547 @default.
- W4384283544 hasConcept C36503486 @default.
- W4384283544 hasConcept C41008148 @default.
- W4384283544 hasConcept C542102704 @default.
- W4384283544 hasConcept C55493867 @default.
- W4384283544 hasConcept C95623464 @default.
- W4384283544 hasConceptScore W4384283544C104317684 @default.
- W4384283544 hasConceptScore W4384283544C117797892 @default.
- W4384283544 hasConceptScore W4384283544C120665830 @default.
- W4384283544 hasConceptScore W4384283544C121332964 @default.
- W4384283544 hasConceptScore W4384283544C124101348 @default.
- W4384283544 hasConceptScore W4384283544C134306372 @default.
- W4384283544 hasConceptScore W4384283544C139807058 @default.
- W4384283544 hasConceptScore W4384283544C153180895 @default.
- W4384283544 hasConceptScore W4384283544C154945302 @default.
- W4384283544 hasConceptScore W4384283544C15744967 @default.
- W4384283544 hasConceptScore W4384283544C162324750 @default.
- W4384283544 hasConceptScore W4384283544C185592680 @default.
- W4384283544 hasConceptScore W4384283544C187736073 @default.
- W4384283544 hasConceptScore W4384283544C204241405 @default.
- W4384283544 hasConceptScore W4384283544C2776434776 @default.
- W4384283544 hasConceptScore W4384283544C2780451532 @default.
- W4384283544 hasConceptScore W4384283544C31972630 @default.
- W4384283544 hasConceptScore W4384283544C33923547 @default.
- W4384283544 hasConceptScore W4384283544C36503486 @default.
- W4384283544 hasConceptScore W4384283544C41008148 @default.
- W4384283544 hasConceptScore W4384283544C542102704 @default.
- W4384283544 hasConceptScore W4384283544C55493867 @default.
- W4384283544 hasConceptScore W4384283544C95623464 @default.
- W4384283544 hasFunder F4320321408 @default.
- W4384283544 hasFunder F4320322030 @default.
- W4384283544 hasFunder F4320322120 @default.
- W4384283544 hasFunder F4320335489 @default.
- W4384283544 hasFunder F4320337407 @default.
- W4384283544 hasLocation W43842835441 @default.
- W4384283544 hasOpenAccess W4384283544 @default.
- W4384283544 hasPrimaryLocation W43842835441 @default.
- W4384283544 hasRelatedWork W1969449762 @default.
- W4384283544 hasRelatedWork W1989438960 @default.
- W4384283544 hasRelatedWork W2052595151 @default.
- W4384283544 hasRelatedWork W2096823343 @default.
- W4384283544 hasRelatedWork W2098745069 @default.
- W4384283544 hasRelatedWork W2317337758 @default.
- W4384283544 hasRelatedWork W2750946167 @default.