VLP: A Survey on Vision-language Pre-training

TLDR

Pre‑training models have propelled computer vision and natural language processing forward, proving beneficial for downstream uni‑modal tasks and prompting investigation into their applicability for multi‑modal vision‑language problems. This survey examines recent advances and emerging frontiers in vision‑language pre‑training, covering image‑text and video‑text modalities across five key dimensions: feature extraction, model architecture, pre‑training objectives, datasets, and downstream tasks. It then details specific VLP models and discusses new frontiers in the field. This is the first survey focused on VLP, and it aims to illuminate future research directions.

Abstract

Abstract In the past few years, the emergence of pre-training models has brought uni-modal fields such as computer vision (CV) and natural language processing (NLP) to a new era. Substantial works have shown that they are beneficial for downstream uni-modal tasks and avoid training a new model from scratch. So can such pre-trained models be applied to multi-modal tasks? Researchers have explored this problem and made significant progress. This paper surveys recent advances and new frontiers in vision-language pre-training (VLP), including image-text and video-text pre-training. To give readers a better overall grasp of VLP, we first review its recent advances in five aspects: feature extraction, model architecture, pre-training objectives, pre-training datasets, and downstream tasks. Then, we summarize the specific VLP models in detail. Finally, we discuss the new frontiers in VLP. To the best of our knowledge, this is the first survey focused on VLP. We hope that this survey can shed light on future research in the VLP field.