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 …

As information exists in various modalities in real world, effective interaction and fusion
among multimodal information plays a key role for the creation and perception of multimodal …

Large text-to-image models achieved a remarkable leap in the evolution of AI, enabling high-
quality and diverse synthesis of images from a given text prompt. However, these models …

Recent text-to-video generation approaches rely on computationally heavy training and
require large-scale video datasets. In this paper, we introduce a new task, zero-shot text-to …

Recent large-scale text-driven synthesis models have attracted much attention thanks to
their remarkable capabilities of generating highly diverse images that follow given text …

Recent CLIP-guided 3D optimization methods, such as DreamFields and PureCLIPNeRF,
have achieved impressive results in zero-shot text-to-3D synthesis. However, due to scratch …

Natural language offers a highly intuitive interface for image editing. In this paper, we
introduce the first solution for performing local (region-based) edits in generic natural …

We present the vector quantized diffusion (VQ-Diffusion) model for text-to-image generation.
This method is based on a vector quantized variational autoencoder (VQ-VAE) whose latent …

Synthesizing high-fidelity complex images from text is challenging. Based on large
pretraining, the autoregressive and diffusion models can synthesize photo-realistic images …

In the Internet-of-Things (IoT) era, billions of sensors and devices collect and process data
from the environment, transmit them to cloud centers, and receive feedback via the Internet …