FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3038514202> ?p ?o ?g. }

• W3038514202 abstract "Generating an image from a provided descriptive text is quite a challenging task because of the difficulty in incorporating perceptual information (object shapes, colors, and their interactions) along with providing high relevancy related to the provided text. Current methods first generate an initial low-resolution image, which typically has irregular object shapes, colors, and interaction between objects. This initial image is then improved by conditioning on the text. However, these methods mainly address the problem of using text representation efficiently in the refinement of the initially generated image, while the success of this refinement process depends heavily on the quality of the initially generated image, as pointed out in the DM-GAN paper. Hence, we propose a method to provide good initialized images by incorporating perceptual understanding in the discriminator module. We improve the perceptual information at the first stage itself, which results in significant improvement in the final generated image. In this paper, we have applied our approach to the novel StackGAN architecture. We then show that the perceptual information included in the initial image is improved while modeling image distribution at multiple stages. Finally, we generated realistic multi-colored images conditioned by text. These images have good quality along with containing improved basic perceptual information. More importantly, the proposed method can be integrated into the pipeline of other state-of-the-art text-based-image-generation models to generate initial low-resolution images. We also worked on improving the refinement process in StackGAN by augmenting the third stage of the generator-discriminator pair in the StackGAN architecture. Our experimental analysis and comparison with the state-of-the-art on a large but sparse dataset MS COCO further validate the usefulness of our proposed approach." @default.
• W3038514202 created "2020-07-10" @default.
• W3038514202 creator A5003374144 @default.
• W3038514202 creator A5066116024 @default.
• W3038514202 creator A5069548004 @default.
• W3038514202 creator A5071331674 @default.
• W3038514202 date "2020-07-02" @default.
• W3038514202 modified "2023-09-25" @default.
• W3038514202 title "PerceptionGAN: Real-world Image Construction from Provided Text through Perceptual Understanding" @default.
• W3038514202 cites W1614298861 @default.
• W3038514202 cites W1797268635 @default.
• W3038514202 cites W1861492603 @default.
• W3038514202 cites W2099471712 @default.
• W3038514202 cites W2194775991 @default.
• W3038514202 cites W2250539671 @default.
• W3038514202 cites W2298992465 @default.
• W3038514202 cites W2339652278 @default.
• W3038514202 cites W2398118205 @default.
• W3038514202 cites W2405756170 @default.
• W3038514202 cites W2493916176 @default.
• W3038514202 cites W2530372461 @default.
• W3038514202 cites W2557449848 @default.
• W3038514202 cites W2564591810 @default.
• W3038514202 cites W2566832195 @default.
• W3038514202 cites W2592101326 @default.
• W3038514202 cites W2751273146 @default.
• W3038514202 cites W2949399848 @default.
• W3038514202 cites W2962760235 @default.
• W3038514202 cites W2963143316 @default.
• W3038514202 cites W2963163163 @default.
• W3038514202 cites W2963373786 @default.
• W3038514202 cites W2963684088 @default.
• W3038514202 cites W2963966654 @default.
• W3038514202 cites W2964024144 @default.
• W3038514202 cites W2964201867 @default.
• W3038514202 cites W2966792645 @default.
• W3038514202 cites W648143168 @default.
• W3038514202 hasPublicationYear "2020" @default.
• W3038514202 type Work @default.
• W3038514202 sameAs 3038514202 @default.
• W3038514202 citedByCount "0" @default.
• W3038514202 crossrefType "posted-content" @default.
• W3038514202 hasAuthorship W3038514202A5003374144 @default.
• W3038514202 hasAuthorship W3038514202A5066116024 @default.
• W3038514202 hasAuthorship W3038514202A5069548004 @default.
• W3038514202 hasAuthorship W3038514202A5071331674 @default.
• W3038514202 hasConcept C111919701 @default.
• W3038514202 hasConcept C115961682 @default.
• W3038514202 hasConcept C121332964 @default.
• W3038514202 hasConcept C153180895 @default.
• W3038514202 hasConcept C154945302 @default.
• W3038514202 hasConcept C163258240 @default.
• W3038514202 hasConcept C169760540 @default.
• W3038514202 hasConcept C17744445 @default.
• W3038514202 hasConcept C199360897 @default.
• W3038514202 hasConcept C199539241 @default.
• W3038514202 hasConcept C26760741 @default.
• W3038514202 hasConcept C2776359362 @default.
• W3038514202 hasConcept C2779803651 @default.
• W3038514202 hasConcept C2780992000 @default.
• W3038514202 hasConcept C2781238097 @default.
• W3038514202 hasConcept C31972630 @default.
• W3038514202 hasConcept C41008148 @default.
• W3038514202 hasConcept C43521106 @default.
• W3038514202 hasConcept C62520636 @default.
• W3038514202 hasConcept C76155785 @default.
• W3038514202 hasConcept C86803240 @default.
• W3038514202 hasConcept C94625758 @default.
• W3038514202 hasConcept C94915269 @default.
• W3038514202 hasConcept C98045186 @default.
• W3038514202 hasConceptScore W3038514202C111919701 @default.
• W3038514202 hasConceptScore W3038514202C115961682 @default.
• W3038514202 hasConceptScore W3038514202C121332964 @default.
• W3038514202 hasConceptScore W3038514202C153180895 @default.
• W3038514202 hasConceptScore W3038514202C154945302 @default.
• W3038514202 hasConceptScore W3038514202C163258240 @default.
• W3038514202 hasConceptScore W3038514202C169760540 @default.
• W3038514202 hasConceptScore W3038514202C17744445 @default.
• W3038514202 hasConceptScore W3038514202C199360897 @default.
• W3038514202 hasConceptScore W3038514202C199539241 @default.
• W3038514202 hasConceptScore W3038514202C26760741 @default.
• W3038514202 hasConceptScore W3038514202C2776359362 @default.
• W3038514202 hasConceptScore W3038514202C2779803651 @default.
• W3038514202 hasConceptScore W3038514202C2780992000 @default.
• W3038514202 hasConceptScore W3038514202C2781238097 @default.
• W3038514202 hasConceptScore W3038514202C31972630 @default.
• W3038514202 hasConceptScore W3038514202C41008148 @default.
• W3038514202 hasConceptScore W3038514202C43521106 @default.
• W3038514202 hasConceptScore W3038514202C62520636 @default.
• W3038514202 hasConceptScore W3038514202C76155785 @default.
• W3038514202 hasConceptScore W3038514202C86803240 @default.
• W3038514202 hasConceptScore W3038514202C94625758 @default.
• W3038514202 hasConceptScore W3038514202C94915269 @default.
• W3038514202 hasConceptScore W3038514202C98045186 @default.
• W3038514202 hasLocation W30385142021 @default.
• W3038514202 hasOpenAccess W3038514202 @default.
• W3038514202 hasPrimaryLocation W30385142021 @default.
• W3038514202 hasRelatedWork W2015861798 @default.
• W3038514202 hasRelatedWork W2086465792 @default.
• W3038514202 hasRelatedWork W2184218725 @default.

• next