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 …

Image captioning is a research area of immense importance, aiming to generate natural
language descriptions for visual content in the form of still images. The advent of deep …

Neural compression is the application of neural networks and other machine learning
methods to data compression. Recent advances in statistical machine learning have opened …

In this paper, we design and train a Generative Image-to-text Transformer, GIT, to unify
vision-language tasks such as image/video captioning and question answering. While …

Abstract Vision-language (VL) pre-training has recently received considerable attention.
However, most existing end-to-end pre-training approaches either only aim to tackle VL …

Recent advances on text-to-image generation have witnessed the rise of diffusion models
which act as powerful generative models. Nevertheless, it is not trivial to exploit such latent …

Zero-shot image captioning (IC) without well-paired image-text data can be categorized into
two main types: training-free and text-only-training methods. While both types integrate pre …

Controllable image captioning is an emerging multimodal topic that aims to describe the
image with natural language following human purpose, $\textit {eg} $, looking at the …

This paper presents Tag2Text, a vision language pre-training (VLP) framework, which
introduces image tagging into vision-language models to guide the learning of visual …

Zero-shot capability has been considered as a new revolution of deep learning, letting
machines work on tasks without curated training data. As a good start and the only existing …