Text is ubiquitous in our visual world, conveying crucial information, such as in documents,
websites, and everyday photographs. In this work, we propose UReader, a first exploration …

Abstract Vision-Language Pre-training (VLP) models have shown promising capabilities in
grounding natural language in image data, facilitating a broad range of cross-modal tasks …

The recent large-scale vision-language pre-training (VLP) of dual-stream architectures (eg,
CLIP) with a tremendous amount of image-text pair data, has shown its superiority on …

Recent text-to-image matching models apply contrastive learning to large corpora of
uncurated pairs of images and sentences. While such models can provide a powerful score …

CLIP showcases exceptional cross-modal matching capabilities due to its training on image-
text contrastive learning tasks. However without specific optimization for unimodal scenarios …

Abstract Contrastive Language-Image Pre-training (CLIP) plays an essential role in
extracting valuable content information from images across diverse tasks. It aligns textual …

CLIP (Contrastive Language-Image Pre-training) is a very recent multi-modal model that
jointly learns representations of images and texts. The model is trained on a massive …

The surge of Multimodal Large Language Models (MLLMs), given their prominent emergent
capabilities in instruction following and reasoning, has greatly advanced the field of visual …

This paper presents contrastive-tuning, a simple method employing contrastive training to
align image and text models while still taking advantage of their pre-training. In our empirical …

Recently, large-scale Contrastive Language-Image Pre-training (CLIP) has attracted
unprecedented attention for its impressive zero-shot recognition ability and excellent …