About this document
Self-Supervised Multimodal Learning - A Survey (Zong Et Al. - 07.2025) by Ali Hüsameddin ATEŞ is a document available to read on EtoBox.
This survey reviews self-supervised multimodal learning (SSML), which addresses the challenges of learning from unannotated multimodal data, including representation learning without labels, modality fusion, and handling unaligned data. It discusses state-of-the-art solutions, applications in various fields, and the potential for SSML to alleviate the reliance on expensive human annotations. The paper also outlines future research directions and provides a comprehensive taxonomy of SSML algorithms.
- Author
- Ali Hüsameddin ATEŞ
- Language
- EN