Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289491009> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W4289491009 abstract "Recently, generative adversarial networks have gained a lot of popularity for image generation tasks. However, such models are associated with complex learning mechanisms and demand very large relevant datasets. This work borrows concepts from image and video captioning models to form an image generative framework. The model is trained in a similar fashion as recurrent captioning model and uses the learned weights for image generation. This is done in an inverse direction, where the input is a caption and the output is an image. The vector representation of the sentence and frames are extracted from an encoder-decoder model which is initially trained on similar sentence and image pairs. Our model conditions image generation on a natural language caption. We leverage a sequence-to-sequence model to generate synthetic captions that have the same meaning for having a robust image generation. One key advantage of our method is that the traditional image captioning datasets can be used for synthetic sentence paraphrases. Results indicate that images generated through multiple captions are better at capturing the semantic meaning of the family of captions." @default.
- W4289491009 created "2022-08-02" @default.
- W4289491009 creator A5002928269 @default.
- W4289491009 creator A5021107723 @default.
- W4289491009 creator A5032475867 @default.
- W4289491009 creator A5062578844 @default.
- W4289491009 creator A5081619697 @default.
- W4289491009 creator A5088141052 @default.
- W4289491009 date "2018-09-26" @default.
- W4289491009 modified "2023-09-27" @default.
- W4289491009 title "Vector Learning for Cross Domain Representations" @default.
- W4289491009 doi "https://doi.org/10.48550/arxiv.1809.10312" @default.
- W4289491009 hasPublicationYear "2018" @default.
- W4289491009 type Work @default.
- W4289491009 citedByCount "0" @default.
- W4289491009 crossrefType "posted-content" @default.
- W4289491009 hasAuthorship W4289491009A5002928269 @default.
- W4289491009 hasAuthorship W4289491009A5021107723 @default.
- W4289491009 hasAuthorship W4289491009A5032475867 @default.
- W4289491009 hasAuthorship W4289491009A5062578844 @default.
- W4289491009 hasAuthorship W4289491009A5081619697 @default.
- W4289491009 hasAuthorship W4289491009A5088141052 @default.
- W4289491009 hasBestOaLocation W42894910091 @default.
- W4289491009 hasConcept C111919701 @default.
- W4289491009 hasConcept C115961682 @default.
- W4289491009 hasConcept C118505674 @default.
- W4289491009 hasConcept C153083717 @default.
- W4289491009 hasConcept C154945302 @default.
- W4289491009 hasConcept C157657479 @default.
- W4289491009 hasConcept C167966045 @default.
- W4289491009 hasConcept C195324797 @default.
- W4289491009 hasConcept C204321447 @default.
- W4289491009 hasConcept C2777530160 @default.
- W4289491009 hasConcept C39890363 @default.
- W4289491009 hasConcept C41008148 @default.
- W4289491009 hasConceptScore W4289491009C111919701 @default.
- W4289491009 hasConceptScore W4289491009C115961682 @default.
- W4289491009 hasConceptScore W4289491009C118505674 @default.
- W4289491009 hasConceptScore W4289491009C153083717 @default.
- W4289491009 hasConceptScore W4289491009C154945302 @default.
- W4289491009 hasConceptScore W4289491009C157657479 @default.
- W4289491009 hasConceptScore W4289491009C167966045 @default.
- W4289491009 hasConceptScore W4289491009C195324797 @default.
- W4289491009 hasConceptScore W4289491009C204321447 @default.
- W4289491009 hasConceptScore W4289491009C2777530160 @default.
- W4289491009 hasConceptScore W4289491009C39890363 @default.
- W4289491009 hasConceptScore W4289491009C41008148 @default.
- W4289491009 hasLocation W42894910091 @default.
- W4289491009 hasLocation W42894910092 @default.
- W4289491009 hasOpenAccess W4289491009 @default.
- W4289491009 hasPrimaryLocation W42894910091 @default.
- W4289491009 hasRelatedWork W159132833 @default.
- W4289491009 hasRelatedWork W2547835662 @default.
- W4289491009 hasRelatedWork W2903179935 @default.
- W4289491009 hasRelatedWork W3093329502 @default.
- W4289491009 hasRelatedWork W3209355071 @default.
- W4289491009 hasRelatedWork W3216250699 @default.
- W4289491009 hasRelatedWork W4281560470 @default.
- W4289491009 hasRelatedWork W4312206189 @default.
- W4289491009 hasRelatedWork W4366341475 @default.
- W4289491009 hasRelatedWork W4375870165 @default.
- W4289491009 isParatext "false" @default.
- W4289491009 isRetracted "false" @default.
- W4289491009 workType "article" @default.