Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385605307> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4385605307 endingPage "63" @default.
- W4385605307 startingPage "57" @default.
- W4385605307 abstract "Text-to-image (T2I) generation, which involves synthesizing an image from a textual description, has emerged as a popular research topic in computer vision. Meanwhile, transformer-based models, such as BERT, GPT-2, and T5, have demonstrated promising results in various natural language processing tasks, including text generation and translation. However, their application to T2I generation remains largely unexplored. Therefore, a comparative study investigating the performance of BERT, GPT-2, and T5 in T2I generation is of significant importance. Such a study would shed light on the strengths and weaknesses of each model, facilitating the identification of the most suitable approach for this task. In this paper, we propose three architectures to conduct a comparative study of T5, GPT-2, and BERT in T2I generation tasks. We fine-tune these models to generate text vectors and then transform the textual information into images using the affine transformation into the DF-GAN generator. Subsequently, we evaluate the quality, diversity, and the models’ ability to recognize the words. Our experiments on the challenging CUB and Oxford-102 flower datasets demonstrate that T5 exhibits promising potential for T2I generation. It has the capability to generate visually appealing and semantically coherent images from textual descriptions." @default.
- W4385605307 created "2023-08-06" @default.
- W4385605307 creator A5021802342 @default.
- W4385605307 creator A5026593169 @default.
- W4385605307 creator A5046020393 @default.
- W4385605307 date "2023-09-01" @default.
- W4385605307 modified "2023-09-27" @default.
- W4385605307 title "The effectiveness of T5, GPT-2, and BERT on text-to-image generation task" @default.
- W4385605307 cites W1566289585 @default.
- W4385605307 cites W2108598243 @default.
- W4385605307 cites W2183341477 @default.
- W4385605307 cites W2962845008 @default.
- W4385605307 cites W2963748441 @default.
- W4385605307 cites W2963966654 @default.
- W4385605307 cites W3157525179 @default.
- W4385605307 cites W3191587092 @default.
- W4385605307 cites W3192242026 @default.
- W4385605307 cites W3211950664 @default.
- W4385605307 cites W4224026172 @default.
- W4385605307 cites W4296312410 @default.
- W4385605307 cites W4309204637 @default.
- W4385605307 doi "https://doi.org/10.1016/j.patrec.2023.08.001" @default.
- W4385605307 hasPublicationYear "2023" @default.
- W4385605307 type Work @default.
- W4385605307 citedByCount "0" @default.
- W4385605307 crossrefType "journal-article" @default.
- W4385605307 hasAuthorship W4385605307A5021802342 @default.
- W4385605307 hasAuthorship W4385605307A5026593169 @default.
- W4385605307 hasAuthorship W4385605307A5046020393 @default.
- W4385605307 hasConcept C104317684 @default.
- W4385605307 hasConcept C121332964 @default.
- W4385605307 hasConcept C153180895 @default.
- W4385605307 hasConcept C154945302 @default.
- W4385605307 hasConcept C162324750 @default.
- W4385605307 hasConcept C163258240 @default.
- W4385605307 hasConcept C165801399 @default.
- W4385605307 hasConcept C185592680 @default.
- W4385605307 hasConcept C187736073 @default.
- W4385605307 hasConcept C202444582 @default.
- W4385605307 hasConcept C204241405 @default.
- W4385605307 hasConcept C204321447 @default.
- W4385605307 hasConcept C23123220 @default.
- W4385605307 hasConcept C2780451532 @default.
- W4385605307 hasConcept C2780992000 @default.
- W4385605307 hasConcept C28490314 @default.
- W4385605307 hasConcept C2985684807 @default.
- W4385605307 hasConcept C33923547 @default.
- W4385605307 hasConcept C41008148 @default.
- W4385605307 hasConcept C55493867 @default.
- W4385605307 hasConcept C62520636 @default.
- W4385605307 hasConcept C66322947 @default.
- W4385605307 hasConcept C92757383 @default.
- W4385605307 hasConceptScore W4385605307C104317684 @default.
- W4385605307 hasConceptScore W4385605307C121332964 @default.
- W4385605307 hasConceptScore W4385605307C153180895 @default.
- W4385605307 hasConceptScore W4385605307C154945302 @default.
- W4385605307 hasConceptScore W4385605307C162324750 @default.
- W4385605307 hasConceptScore W4385605307C163258240 @default.
- W4385605307 hasConceptScore W4385605307C165801399 @default.
- W4385605307 hasConceptScore W4385605307C185592680 @default.
- W4385605307 hasConceptScore W4385605307C187736073 @default.
- W4385605307 hasConceptScore W4385605307C202444582 @default.
- W4385605307 hasConceptScore W4385605307C204241405 @default.
- W4385605307 hasConceptScore W4385605307C204321447 @default.
- W4385605307 hasConceptScore W4385605307C23123220 @default.
- W4385605307 hasConceptScore W4385605307C2780451532 @default.
- W4385605307 hasConceptScore W4385605307C2780992000 @default.
- W4385605307 hasConceptScore W4385605307C28490314 @default.
- W4385605307 hasConceptScore W4385605307C2985684807 @default.
- W4385605307 hasConceptScore W4385605307C33923547 @default.
- W4385605307 hasConceptScore W4385605307C41008148 @default.
- W4385605307 hasConceptScore W4385605307C55493867 @default.
- W4385605307 hasConceptScore W4385605307C62520636 @default.
- W4385605307 hasConceptScore W4385605307C66322947 @default.
- W4385605307 hasConceptScore W4385605307C92757383 @default.
- W4385605307 hasLocation W43856053071 @default.
- W4385605307 hasOpenAccess W4385605307 @default.
- W4385605307 hasPrimaryLocation W43856053071 @default.
- W4385605307 hasRelatedWork W2048228344 @default.
- W4385605307 hasRelatedWork W2081647779 @default.
- W4385605307 hasRelatedWork W2086064646 @default.
- W4385605307 hasRelatedWork W2119135658 @default.
- W4385605307 hasRelatedWork W2357241418 @default.
- W4385605307 hasRelatedWork W2364151838 @default.
- W4385605307 hasRelatedWork W2365767001 @default.
- W4385605307 hasRelatedWork W2390459957 @default.
- W4385605307 hasRelatedWork W2789919619 @default.
- W4385605307 hasRelatedWork W3033942572 @default.
- W4385605307 hasVolume "173" @default.
- W4385605307 isParatext "false" @default.
- W4385605307 isRetracted "false" @default.
- W4385605307 workType "article" @default.