This monograph surveys vision-language pre-training (VLP) methods for multimodal
intelligence that have been developed in the last few years. We group these approaches …

Astounding results from Transformer models on natural language tasks have intrigued the
vision community to study their application to computer vision problems. Among their salient …

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 present VISPROG, a neuro-symbolic approach to solving complex and compositional
visual tasks given natural language instructions. VISPROG avoids the need for any task …

Exploring large-scale pretrained foundation models is of significant interest in computer
vision because these models can be quickly transferred to many downstream tasks. This …

Most visual recognition studies rely heavily on crowd-labelled data in deep neural networks
(DNNs) training, and they usually train a DNN for each single visual recognition task …

Abstract Vision-Language Pre-training (VLP) has advanced the performance for many vision-
language tasks. However, most existing pre-trained models only excel in either …

Despite the success of large vision and language models (VLMs) in many downstream
applications, it is unclear how well they encode the compositional relationships between …

Fine-tuning large pre-trained models on downstream tasks has been adopted in a variety of
domains recently. However, it is costly to update the entire parameter set of large pre-trained …

Vision-language representation learning largely benefits from image-text alignment through
contrastive losses (eg, InfoNCE loss). The success of this alignment strategy is attributed to …