English

Multimodal Learning with Transformers: A Survey

Computer Vision and Pattern Recognition 2023-05-11 v2 Machine Learning

Abstract

Transformer is a promising neural network learner, and has achieved great success in various machine learning tasks. Thanks to the recent prevalence of multimodal applications and big data, Transformer-based multimodal learning has become a hot topic in AI research. This paper presents a comprehensive survey of Transformer techniques oriented at multimodal data. The main contents of this survey include: (1) a background of multimodal learning, Transformer ecosystem, and the multimodal big data era, (2) a theoretical review of Vanilla Transformer, Vision Transformer, and multimodal Transformers, from a geometrically topological perspective, (3) a review of multimodal Transformer applications, via two important paradigms, i.e., for multimodal pretraining and for specific multimodal tasks, (4) a summary of the common challenges and designs shared by the multimodal Transformer models and applications, and (5) a discussion of open problems and potential research directions for the community.

Keywords

Cite

@article{arxiv.2206.06488,
  title  = {Multimodal Learning with Transformers: A Survey},
  author = {Peng Xu and Xiatian Zhu and David A. Clifton},
  journal= {arXiv preprint arXiv:2206.06488},
  year   = {2023}
}

Comments

This paper is accepted by IEEE TPAMI

R2 v1 2026-06-24T11:49:58.450Z