Abstract: Pre-trained vision-language models (VLMs) and language models (LMs) have recently garnered significant attention due to their remarkable ability to represent textual concepts, opening up new ...

Abstract: Recently, the accuracy of image-text matching has been greatly improved by multimodal pretrained models, all of which use millions or billions of paired images and texts for supervised model ...

Note: This project was put together for fun and to kick the tires on Sveltekit 5 and Skeleton UI Next. Things may be broken or not work as expected.

Please Don't Scroll Past This Can you chip in? The Internet Archive partners with libraries, archives, and institutions across the globe to preserve cultural heritage that would otherwise be lost ...

* Equal contribution. † Co-corresponding author. Each image is paired with one or more text instances with polygon-level annotations. The dataset follows a consistent annotation format, detailed in ...