English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Text-to-image synthesis aims to generate a photo-realistic and semanticconsistent image from a specific text description. The images synthesized byoff-the-shelf models usually contain limited components compared with thecorresponding image and text description, which decreases the image quality andthe textual-visual consistency. To address this issue, we propose a novelVision-Language Matching strategy for text-to-image synthesis, named VLMGAN*,which introduces a dual vision-language matching mechanism to strengthen theimage quality and semantic consistency. The dual vision-language matchingmechanism considers textual-visual matching between the generated image and thecorresponding text description, and visual-visual consistent constraintsbetween the synthesized image and the real image. Given a specific textdescription, VLMGAN* firstly encodes it into textual features and then feedsthem to a dual vision-language matching-based generative model to synthesize aphoto-realistic and textual semantic consistent image. Besides, the popularevaluation metrics for text-to-image synthesis are borrowed from simple imagegeneration, which mainly evaluates the reality and diversity of the synthesizedimages. Therefore, we introduce a metric named Vision-Language Matching Score(VLMS) to evaluate the performance of text-to-image synthesis which canconsider both the image quality and the semantic consistency betweensynthesized image and the description. The proposed dual multi-levelvision-language matching strategy can be applied to other text-to-imagesynthesis methods. We implement this strategy on two popular baselines, whichare marked with ${\text{VLMGAN}_{+\text{AttnGAN}}}$ and${\text{VLMGAN}_{+\text{DFGAN}}}$. The experimental results on two widely-useddatasets show that the model achieves significant improvements over otherstate-of-the-art methods.

Vision-Language Matching for Text-to-Image Synthesis via Generative Adversarial Networks