In this paper, we introduce a new vision-language pre-trained model--ImageBERT--for
image-text joint embedding. Our model is a Transformer-based model, which takes different …

Joint image-text embedding is the bedrock for most Vision-and-Language (V+ L) tasks,
where multimodality inputs are simultaneously processed for joint visual and textual …

Joint image-text embedding is the bedrock for most Vision-and-Language (V+ L) tasks,
where multimodality inputs are jointly processed for visual and textual understanding. In this …

As a bridge between language and vision domains, cross-modal retrieval between images
and texts is a hot research topic in recent years. It remains challenging because the current …

Matching images and sentences demands a fine understanding of both modalities. In this
article, we propose a new system to discriminatively embed the image and text to a shared …

A big convergence of language, vision, and multimodal pretraining is emerging. In this work,
we introduce a general-purpose multimodal foundation model BEiT-3, which achieves state …

A big convergence of language, vision, and multimodal pretraining is emerging. In this work,
we introduce a general-purpose multimodal foundation model BEiT-3, which achieves …

We propose Unicoder-VL, a universal encoder that aims to learn joint representations of
vision and language in a pre-training manner. Borrow ideas from cross-lingual pre-trained …

Multimodal pre-training has propelled great advancement in vision-and-language research.
These large-scale pre-trained models, although successful, fatefully suffer from slow …

Abstract Contrastive Language-Image Pre-training (CLIP) has significantly boosted the
performance of various vision-language tasks by scaling up the dataset with image-text pairs …