Survey on Self-Supervised Multimodal Representation Learning and Foundation Models

Deep learning has been the subject of growing interest in recent years. Specifically, the field of multimodal machine learning, which leverages information across modalities such as vision, language, and audio, has seen rapid progress driven by self-supervised pretraining. This survey reviews self-supervised multimodal representation learning methods and the emerging landscape of multimodal foundation models.

Paper (arXiv)

BibTeX

@article{thapa2022survey,
  title   = {Survey on Self-Supervised Multimodal Representation Learning and Foundation Models},
  author  = {Thapa, Sushil},
  journal = {arXiv preprint arXiv:2211.15837},
  year    = {2022}
}