Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386800343> ?p ?o ?g. }
- W4386800343 endingPage "109961" @default.
- W4386800343 startingPage "109961" @default.
- W4386800343 abstract "Text-guided image inpainting aims to generate corrupted image patches and obtain a plausible image based on textual descriptions, considering the relationship between textual and visual semantics. Existing works focus on predicting missing patches from the residual pixels of corrupted images, ignoring the visual semantics of the objects of interest in the images corresponding to the textual descriptions. In this paper, we propose a text-guided image inpainting method with multi-grained image-text semantic learning (MISL), consisting of global-local generators and discriminators. More specifically, we devise hierarchical learning (HL) with global-coarse-grained, object-fine-grained, and global-fine-grained learning stages in the global-local generators to refine the corrupted images from the global to local. In particular, the object-fine-grained learning stage focuses on the visual semantics of objects of interest in corrupted images by using an encoder–decoder network with self-attention blocks. Not only that, we design a mask reconstruction (MR) module to further act on the restoration of the objects of interest corresponding to the given textual descriptions. To inject the textual semantics into the global-local generators, we implement a multi-attention (MA) module that incorporates the word-level and sentence-level textual features to generate three different-grained images. For training, we exploit a global discriminator and a flexible discriminator to penalize the whole image and the corrupted region, respectively. Extensive experiments conducted on four datasets show the outperformance of the proposed MISL." @default.
- W4386800343 created "2023-09-17" @default.
- W4386800343 creator A5008748675 @default.
- W4386800343 creator A5012177442 @default.
- W4386800343 creator A5013302961 @default.
- W4386800343 creator A5015195367 @default.
- W4386800343 creator A5021412272 @default.
- W4386800343 creator A5060428189 @default.
- W4386800343 date "2024-01-01" @default.
- W4386800343 modified "2023-10-18" @default.
- W4386800343 title "MISL: Multi-grained image-text semantic learning for text-guided image inpainting" @default.
- W4386800343 cites W1536680647 @default.
- W4386800343 cites W1861492603 @default.
- W4386800343 cites W1993120651 @default.
- W4386800343 cites W1999360130 @default.
- W4386800343 cites W2562637781 @default.
- W4386800343 cites W2963270367 @default.
- W4386800343 cites W2963966654 @default.
- W4386800343 cites W2964024144 @default.
- W4386800343 cites W2966792645 @default.
- W4386800343 cites W2989207674 @default.
- W4386800343 cites W3034667500 @default.
- W4386800343 cites W3035512475 @default.
- W4386800343 cites W3040248848 @default.
- W4386800343 cites W3055227258 @default.
- W4386800343 cites W3083963475 @default.
- W4386800343 cites W3092906216 @default.
- W4386800343 cites W3094715874 @default.
- W4386800343 cites W3095707326 @default.
- W4386800343 cites W3145291360 @default.
- W4386800343 cites W3206335650 @default.
- W4386800343 cites W3209482227 @default.
- W4386800343 cites W3214312641 @default.
- W4386800343 cites W4304098301 @default.
- W4386800343 cites W4311049322 @default.
- W4386800343 cites W4311901928 @default.
- W4386800343 cites W4312238440 @default.
- W4386800343 cites W4312383858 @default.
- W4386800343 cites W4313051036 @default.
- W4386800343 cites W4323922772 @default.
- W4386800343 cites W4328101918 @default.
- W4386800343 cites W4366722599 @default.
- W4386800343 doi "https://doi.org/10.1016/j.patcog.2023.109961" @default.
- W4386800343 hasPublicationYear "2024" @default.
- W4386800343 type Work @default.
- W4386800343 citedByCount "0" @default.
- W4386800343 crossrefType "journal-article" @default.
- W4386800343 hasAuthorship W4386800343A5008748675 @default.
- W4386800343 hasAuthorship W4386800343A5012177442 @default.
- W4386800343 hasAuthorship W4386800343A5013302961 @default.
- W4386800343 hasAuthorship W4386800343A5015195367 @default.
- W4386800343 hasAuthorship W4386800343A5021412272 @default.
- W4386800343 hasAuthorship W4386800343A5060428189 @default.
- W4386800343 hasConcept C111919701 @default.
- W4386800343 hasConcept C115961682 @default.
- W4386800343 hasConcept C11727466 @default.
- W4386800343 hasConcept C118505674 @default.
- W4386800343 hasConcept C120665830 @default.
- W4386800343 hasConcept C121332964 @default.
- W4386800343 hasConcept C153180895 @default.
- W4386800343 hasConcept C154945302 @default.
- W4386800343 hasConcept C160633673 @default.
- W4386800343 hasConcept C163258240 @default.
- W4386800343 hasConcept C184337299 @default.
- W4386800343 hasConcept C192209626 @default.
- W4386800343 hasConcept C199360897 @default.
- W4386800343 hasConcept C204321447 @default.
- W4386800343 hasConcept C2524010 @default.
- W4386800343 hasConcept C2777530160 @default.
- W4386800343 hasConcept C2779803651 @default.
- W4386800343 hasConcept C2780992000 @default.
- W4386800343 hasConcept C2781238097 @default.
- W4386800343 hasConcept C31972630 @default.
- W4386800343 hasConcept C33923547 @default.
- W4386800343 hasConcept C41008148 @default.
- W4386800343 hasConcept C62520636 @default.
- W4386800343 hasConcept C76155785 @default.
- W4386800343 hasConcept C90805587 @default.
- W4386800343 hasConcept C94915269 @default.
- W4386800343 hasConceptScore W4386800343C111919701 @default.
- W4386800343 hasConceptScore W4386800343C115961682 @default.
- W4386800343 hasConceptScore W4386800343C11727466 @default.
- W4386800343 hasConceptScore W4386800343C118505674 @default.
- W4386800343 hasConceptScore W4386800343C120665830 @default.
- W4386800343 hasConceptScore W4386800343C121332964 @default.
- W4386800343 hasConceptScore W4386800343C153180895 @default.
- W4386800343 hasConceptScore W4386800343C154945302 @default.
- W4386800343 hasConceptScore W4386800343C160633673 @default.
- W4386800343 hasConceptScore W4386800343C163258240 @default.
- W4386800343 hasConceptScore W4386800343C184337299 @default.
- W4386800343 hasConceptScore W4386800343C192209626 @default.
- W4386800343 hasConceptScore W4386800343C199360897 @default.
- W4386800343 hasConceptScore W4386800343C204321447 @default.
- W4386800343 hasConceptScore W4386800343C2524010 @default.
- W4386800343 hasConceptScore W4386800343C2777530160 @default.
- W4386800343 hasConceptScore W4386800343C2779803651 @default.
- W4386800343 hasConceptScore W4386800343C2780992000 @default.
- W4386800343 hasConceptScore W4386800343C2781238097 @default.