Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312528217> ?p ?o ?g. }
- W4312528217 endingPage "426" @default.
- W4312528217 startingPage "409" @default.
- W4312528217 abstract "Text removal has attracted increasingly attention due to its various applications on privacy protection, document restoration, and text editing. It has shown significant progress with deep neural network. However, most of the existing methods often generate inconsistent results for complex background. To address this issue, we propose a Contextual-guided Text Removal Network, termed as CTRNet. CTRNet explores both low-level structure and high-level discriminative context feature as prior knowledge to guide the process of text erasure and background restoration. We further propose a Local-global Content Modeling (LGCM) block with CNNs and Transformer-Encoder to capture local features and establish the long-term relationship among pixels globally. Finally, we incorporate LGCM with context guidance for feature modeling and decoding. Experiments on benchmark datasets, SCUT-EnsText and SCUT-Syn show that CTRNet significantly outperforms the existing state-of-the-art methods. Furthermore, a qualitative experiment on examination papers also demonstrates the generalizability of our method. The code of CTRNet is available at https://github.com/lcy0604/CTRNet." @default.
- W4312528217 created "2023-01-05" @default.
- W4312528217 creator A5021919264 @default.
- W4312528217 creator A5031427009 @default.
- W4312528217 creator A5037101589 @default.
- W4312528217 creator A5045160787 @default.
- W4312528217 creator A5071461852 @default.
- W4312528217 creator A5080674767 @default.
- W4312528217 creator A5085010670 @default.
- W4312528217 date "2022-01-01" @default.
- W4312528217 modified "2023-10-16" @default.
- W4312528217 title "Don’t Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Context" @default.
- W4312528217 cites W1521064364 @default.
- W4312528217 cites W2008806374 @default.
- W4312528217 cites W2074849287 @default.
- W4312528217 cites W2108598243 @default.
- W4312528217 cites W2144554289 @default.
- W4312528217 cites W2163922914 @default.
- W4312528217 cites W2331128040 @default.
- W4312528217 cites W2343052201 @default.
- W4312528217 cites W2475287302 @default.
- W4312528217 cites W2612775908 @default.
- W4312528217 cites W2785383245 @default.
- W4312528217 cites W2798365772 @default.
- W4312528217 cites W2914492226 @default.
- W4312528217 cites W2962974533 @default.
- W4312528217 cites W2963005009 @default.
- W4312528217 cites W2963073614 @default.
- W4312528217 cites W2963255313 @default.
- W4312528217 cites W2963299604 @default.
- W4312528217 cites W2963647456 @default.
- W4312528217 cites W2963899311 @default.
- W4312528217 cites W2967615747 @default.
- W4312528217 cites W2981682056 @default.
- W4312528217 cites W2982148195 @default.
- W4312528217 cites W2991377405 @default.
- W4312528217 cites W2991626090 @default.
- W4312528217 cites W2995942257 @default.
- W4312528217 cites W3003433862 @default.
- W4312528217 cites W3003868038 @default.
- W4312528217 cites W3003921261 @default.
- W4312528217 cites W3010428518 @default.
- W4312528217 cites W3034446980 @default.
- W4312528217 cites W3082245115 @default.
- W4312528217 cites W3100936573 @default.
- W4312528217 cites W3108554146 @default.
- W4312528217 cites W3135462872 @default.
- W4312528217 cites W3168428721 @default.
- W4312528217 cites W3188999719 @default.
- W4312528217 cites W3192658445 @default.
- W4312528217 cites W3193700193 @default.
- W4312528217 cites W3197980622 @default.
- W4312528217 cites W3199738066 @default.
- W4312528217 cites W3203538104 @default.
- W4312528217 cites W3207918547 @default.
- W4312528217 cites W3213555225 @default.
- W4312528217 cites W4214673031 @default.
- W4312528217 cites W4214711516 @default.
- W4312528217 cites W4288083516 @default.
- W4312528217 doi "https://doi.org/10.1007/978-3-031-19815-1_24" @default.
- W4312528217 hasPublicationYear "2022" @default.
- W4312528217 type Work @default.
- W4312528217 citedByCount "2" @default.
- W4312528217 countsByYear W43125282172023 @default.
- W4312528217 crossrefType "book-chapter" @default.
- W4312528217 hasAuthorship W4312528217A5021919264 @default.
- W4312528217 hasAuthorship W4312528217A5031427009 @default.
- W4312528217 hasAuthorship W4312528217A5037101589 @default.
- W4312528217 hasAuthorship W4312528217A5045160787 @default.
- W4312528217 hasAuthorship W4312528217A5071461852 @default.
- W4312528217 hasAuthorship W4312528217A5080674767 @default.
- W4312528217 hasAuthorship W4312528217A5085010670 @default.
- W4312528217 hasBestOaLocation W43125282172 @default.
- W4312528217 hasConcept C105795698 @default.
- W4312528217 hasConcept C111919701 @default.
- W4312528217 hasConcept C11413529 @default.
- W4312528217 hasConcept C118505674 @default.
- W4312528217 hasConcept C119857082 @default.
- W4312528217 hasConcept C13280743 @default.
- W4312528217 hasConcept C138885662 @default.
- W4312528217 hasConcept C144133560 @default.
- W4312528217 hasConcept C151730666 @default.
- W4312528217 hasConcept C154945302 @default.
- W4312528217 hasConcept C162853370 @default.
- W4312528217 hasConcept C185798385 @default.
- W4312528217 hasConcept C204321447 @default.
- W4312528217 hasConcept C205649164 @default.
- W4312528217 hasConcept C27158222 @default.
- W4312528217 hasConcept C2776401178 @default.
- W4312528217 hasConcept C2779343474 @default.
- W4312528217 hasConcept C33923547 @default.
- W4312528217 hasConcept C41008148 @default.
- W4312528217 hasConcept C41895202 @default.
- W4312528217 hasConcept C57273362 @default.
- W4312528217 hasConcept C86251818 @default.
- W4312528217 hasConcept C86803240 @default.
- W4312528217 hasConcept C97931131 @default.
- W4312528217 hasConceptScore W4312528217C105795698 @default.