Matches in SemOpenAlex for { <https://semopenalex.org/work/W3119383971> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3119383971 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 Dynamic Memory Generative Adversarial Network (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 such as DM-GAN and AttnGAN 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. Contribution-This paper improves the pipeline for text to image generation by incorporating perceptual understanding in the initial stage of image generation." @default.
- W3119383971 created "2021-01-18" @default.
- W3119383971 creator A5003374144 @default.
- W3119383971 creator A5066116024 @default.
- W3119383971 creator A5069548004 @default.
- W3119383971 creator A5071331674 @default.
- W3119383971 date "2020-08-26" @default.
- W3119383971 modified "2023-09-25" @default.
- W3119383971 title "PerceptionGAN: Real-world Image Construction from Provided Text through Perceptual Understanding" @default.
- W3119383971 cites W2194775991 @default.
- W3119383971 cites W2250539671 @default.
- W3119383971 cites W2298992465 @default.
- W3119383971 cites W2339652278 @default.
- W3119383971 cites W2398118205 @default.
- W3119383971 cites W2493916176 @default.
- W3119383971 cites W2557449848 @default.
- W3119383971 cites W2566832195 @default.
- W3119383971 cites W2963163163 @default.
- W3119383971 cites W2963966654 @default.
- W3119383971 cites W2964024144 @default.
- W3119383971 cites W2966792645 @default.
- W3119383971 doi "https://doi.org/10.1109/icievicivpr48672.2020.9306618" @default.
- W3119383971 hasPublicationYear "2020" @default.
- W3119383971 type Work @default.
- W3119383971 sameAs 3119383971 @default.
- W3119383971 citedByCount "1" @default.
- W3119383971 countsByYear W31193839712022 @default.
- W3119383971 crossrefType "proceedings-article" @default.
- W3119383971 hasAuthorship W3119383971A5003374144 @default.
- W3119383971 hasAuthorship W3119383971A5066116024 @default.
- W3119383971 hasAuthorship W3119383971A5069548004 @default.
- W3119383971 hasAuthorship W3119383971A5071331674 @default.
- W3119383971 hasBestOaLocation W31193839712 @default.
- W3119383971 hasConcept C111919701 @default.
- W3119383971 hasConcept C115961682 @default.
- W3119383971 hasConcept C153180895 @default.
- W3119383971 hasConcept C154945302 @default.
- W3119383971 hasConcept C169760540 @default.
- W3119383971 hasConcept C17744445 @default.
- W3119383971 hasConcept C199360897 @default.
- W3119383971 hasConcept C199539241 @default.
- W3119383971 hasConcept C26760741 @default.
- W3119383971 hasConcept C2776359362 @default.
- W3119383971 hasConcept C2779803651 @default.
- W3119383971 hasConcept C2781238097 @default.
- W3119383971 hasConcept C31972630 @default.
- W3119383971 hasConcept C41008148 @default.
- W3119383971 hasConcept C43521106 @default.
- W3119383971 hasConcept C76155785 @default.
- W3119383971 hasConcept C86803240 @default.
- W3119383971 hasConcept C94625758 @default.
- W3119383971 hasConcept C94915269 @default.
- W3119383971 hasConcept C98045186 @default.
- W3119383971 hasConceptScore W3119383971C111919701 @default.
- W3119383971 hasConceptScore W3119383971C115961682 @default.
- W3119383971 hasConceptScore W3119383971C153180895 @default.
- W3119383971 hasConceptScore W3119383971C154945302 @default.
- W3119383971 hasConceptScore W3119383971C169760540 @default.
- W3119383971 hasConceptScore W3119383971C17744445 @default.
- W3119383971 hasConceptScore W3119383971C199360897 @default.
- W3119383971 hasConceptScore W3119383971C199539241 @default.
- W3119383971 hasConceptScore W3119383971C26760741 @default.
- W3119383971 hasConceptScore W3119383971C2776359362 @default.
- W3119383971 hasConceptScore W3119383971C2779803651 @default.
- W3119383971 hasConceptScore W3119383971C2781238097 @default.
- W3119383971 hasConceptScore W3119383971C31972630 @default.
- W3119383971 hasConceptScore W3119383971C41008148 @default.
- W3119383971 hasConceptScore W3119383971C43521106 @default.
- W3119383971 hasConceptScore W3119383971C76155785 @default.
- W3119383971 hasConceptScore W3119383971C86803240 @default.
- W3119383971 hasConceptScore W3119383971C94625758 @default.
- W3119383971 hasConceptScore W3119383971C94915269 @default.
- W3119383971 hasConceptScore W3119383971C98045186 @default.
- W3119383971 hasLocation W31193839711 @default.
- W3119383971 hasLocation W31193839712 @default.
- W3119383971 hasOpenAccess W3119383971 @default.
- W3119383971 hasPrimaryLocation W31193839711 @default.
- W3119383971 hasRelatedWork W1533292911 @default.
- W3119383971 hasRelatedWork W2005185696 @default.
- W3119383971 hasRelatedWork W2132132164 @default.
- W3119383971 hasRelatedWork W2161229648 @default.
- W3119383971 hasRelatedWork W2166044122 @default.
- W3119383971 hasRelatedWork W2235753890 @default.
- W3119383971 hasRelatedWork W2359631359 @default.
- W3119383971 hasRelatedWork W2366116130 @default.
- W3119383971 hasRelatedWork W1966218515 @default.
- W3119383971 hasRelatedWork W2551465695 @default.
- W3119383971 isParatext "false" @default.
- W3119383971 isRetracted "false" @default.
- W3119383971 magId "3119383971" @default.
- W3119383971 workType "article" @default.