Article Source

• Transformers for Multimodal Self Supervised Learning from Raw Video, Audio and Text

Transformers for Multimodal Self Supervised Learning

Abstract

Multimodal self-supervised learning is a powerful technique that allows for learning representations from multiple sources of data, such as raw video, audio, and text. In this video, we will explore how transformers can be used for multimodal self-supervised learning and their advantages over other methods.