FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3184934237> ?p ?o ?g. }

• W3184934237 abstract "Generating photo-realistic images from a text description is a challenging problem in computer vision. Previous works have shown promising performance to generate synthetic images conditional on text by Generative Adversarial Networks (GANs). In this paper, we focus on the category-consistent and relativistic diverse constraints to optimize the diversity of synthetic images. Based on those constraints, a category-consistent and relativistic diverse conditional GAN (CRD-CGAN) is proposed to synthesize $K$ photo-realistic images simultaneously. We use the attention loss and diversity loss to improve the sensitivity of the GAN to word attention and noises. Then, we employ the relativistic conditional loss to estimate the probability of relatively real or fake for synthetic images, which can improve the performance of basic conditional loss. Finally, we introduce a category-consistent loss to alleviate the over-category issues between K synthetic images. We evaluate our approach using the Birds-200-2011, Oxford-102 flower and MSCOCO 2014 datasets, and the extensive experiments demonstrate superiority of the proposed method in comparison with state-of-the-art methods in terms of photorealistic and diversity of the generated synthetic images." @default.
• W3184934237 created "2021-08-02" @default.
• W3184934237 creator A5027540915 @default.
• W3184934237 creator A5076741351 @default.
• W3184934237 creator A5082844948 @default.
• W3184934237 date "2023-09-06" @default.
• W3184934237 modified "2023-10-16" @default.
• W3184934237 title "CRD-CGAN: category-consistent and relativistic constraints for diverse text-to-image generation" @default.
• W3184934237 cites W1861492603 @default.
• W3184934237 cites W2029327121 @default.
• W3184934237 cites W2160448933 @default.
• W3184934237 cites W2201054263 @default.
• W3184934237 cites W2237301560 @default.
• W3184934237 cites W2533598788 @default.
• W3184934237 cites W2557449848 @default.
• W3184934237 cites W2566832195 @default.
• W3184934237 cites W2585635281 @default.
• W3184934237 cites W2593414223 @default.
• W3184934237 cites W2595390676 @default.
• W3184934237 cites W2618530766 @default.
• W3184934237 cites W2746125456 @default.
• W3184934237 cites W2905434858 @default.
• W3184934237 cites W2962785568 @default.
• W3184934237 cites W2962974533 @default.
• W3184934237 cites W2963047368 @default.
• W3184934237 cites W2963049565 @default.
• W3184934237 cites W2963163163 @default.
• W3184934237 cites W2963306805 @default.
• W3184934237 cites W2963413689 @default.
• W3184934237 cites W2963470893 @default.
• W3184934237 cites W2963612019 @default.
• W3184934237 cites W2963709863 @default.
• W3184934237 cites W2963966654 @default.
• W3184934237 cites W2964024144 @default.
• W3184934237 cites W2964338647 @default.
• W3184934237 cites W2965289598 @default.
• W3184934237 cites W2965989168 @default.
• W3184934237 cites W2979672901 @default.
• W3184934237 cites W2985245517 @default.
• W3184934237 cites W2991524597 @default.
• W3184934237 cites W2997085666 @default.
• W3184934237 cites W2998123743 @default.
• W3184934237 cites W2998251088 @default.
• W3184934237 cites W3006635140 @default.
• W3184934237 cites W3008062244 @default.
• W3184934237 cites W3023781467 @default.
• W3184934237 cites W3029442767 @default.
• W3184934237 cites W3034779438 @default.
• W3184934237 cites W3034855701 @default.
• W3184934237 cites W3035244041 @default.
• W3184934237 cites W3035500781 @default.
• W3184934237 cites W3036656500 @default.
• W3184934237 cites W3090238363 @default.
• W3184934237 cites W3096601784 @default.
• W3184934237 cites W3096831136 @default.
• W3184934237 cites W3108948338 @default.
• W3184934237 cites W3118580076 @default.
• W3184934237 cites W3127393268 @default.
• W3184934237 cites W3134812768 @default.
• W3184934237 cites W3149210910 @default.
• W3184934237 cites W3167280680 @default.
• W3184934237 cites W3173212682 @default.
• W3184934237 cites W3174525637 @default.
• W3184934237 cites W3201890160 @default.
• W3184934237 cites W4293518006 @default.
• W3184934237 cites W4293519465 @default.
• W3184934237 cites W4294691145 @default.
• W3184934237 doi "https://doi.org/10.1007/s11704-022-2385-x" @default.
• W3184934237 hasPublicationYear "2023" @default.
• W3184934237 type Work @default.
• W3184934237 sameAs 3184934237 @default.
• W3184934237 citedByCount "6" @default.
• W3184934237 countsByYear W31849342372021 @default.
• W3184934237 crossrefType "journal-article" @default.
• W3184934237 hasAuthorship W3184934237A5027540915 @default.
• W3184934237 hasAuthorship W3184934237A5076741351 @default.
• W3184934237 hasAuthorship W3184934237A5082844948 @default.
• W3184934237 hasBestOaLocation W31849342372 @default.
• W3184934237 hasConcept C115961682 @default.
• W3184934237 hasConcept C120665830 @default.
• W3184934237 hasConcept C121332964 @default.
• W3184934237 hasConcept C144024400 @default.
• W3184934237 hasConcept C153180895 @default.
• W3184934237 hasConcept C154945302 @default.
• W3184934237 hasConcept C19165224 @default.
• W3184934237 hasConcept C192209626 @default.
• W3184934237 hasConcept C2781316041 @default.
• W3184934237 hasConcept C2988773926 @default.
• W3184934237 hasConcept C39890363 @default.
• W3184934237 hasConcept C41008148 @default.
• W3184934237 hasConceptScore W3184934237C115961682 @default.
• W3184934237 hasConceptScore W3184934237C120665830 @default.
• W3184934237 hasConceptScore W3184934237C121332964 @default.
• W3184934237 hasConceptScore W3184934237C144024400 @default.
• W3184934237 hasConceptScore W3184934237C153180895 @default.
• W3184934237 hasConceptScore W3184934237C154945302 @default.
• W3184934237 hasConceptScore W3184934237C19165224 @default.
• W3184934237 hasConceptScore W3184934237C192209626 @default.
• W3184934237 hasConceptScore W3184934237C2781316041 @default.
• W3184934237 hasConceptScore W3184934237C2988773926 @default.

• next