Despite the success of large vision and language models (VLMs) in many downstream
applications, it is unclear how well they encode compositional information. Here, we create …

Pre-trained vision-language models (VLMs) learn to align vision and language
representations on large-scale datasets, where each image-text pair usually contains a bag …

Multimodal contrastive pretraining has been used to train multimodal representation models,
such as CLIP, on large amounts of paired image-text data. However, previous studies have …

Abstract Multi-modal (vision-language) models, such as CLIP, are replacing traditional
supervised pre-training models (eg, ImageNet-based pre-training) as the new generation of …

The automatic identification of harmful content online is of major concern for social media
platforms, policymakers, and society. Researchers have studied textual, visual, and audio …

Recent advances in contrastive representation learning over paired image-text data have
led to models such as CLIP that achieve state-of-the-art performance for zero-shot …

Vision-language models (VLMs) are impactful in part because they can be applied to a
variety of visual understanding tasks in a zero-shot fashion, without any fine-tuning. We …

Pre-trained vision-language models (VLMs) have achieved high performance on various
downstream tasks which have been widely used for visual grounding tasks in a weakly …

Despite noise and caption quality having been acknowledged as important factors impacting
vision-language contrastive pre-training in this paper we show that the full potential of …

Vision-Language Pre-training (VLP) with large-scale image-text pairs has demonstrated
superior performance in various fields. However, the image-text pairs co-occurrent on the …