Large-Scale Multimodal Learning:
Universality, Robustness, Efficiency, and Beyond

Guest Editors

Peng Xu
Tsinghua University

Song Bai
ByteDance AI Lab

Bowen Zhou
Tsinghua University

David Clifton
University of Oxford

Andrea Vedaldi
University of Oxford

Mihaela van der Schaar
University of Cambridge

Luc Van Gool
ETH Zurich

Overview

Thanks to the development of the internet and a wide variety of intelligent devices in recent years, increasing amounts of multimodal data are being transmitted over the internet, thus an increasing number of multimodal application scenarios are emerging. In modern life, we can see various multimodal applications, including commercial services (e.g., e-commerce/commodity retrieval, vision-and-language navigation), communication (e.g., lip reading, sign language translation), human-computer interaction, Healthcare AI, surveillance AI, etc. Specifically, in the era of Deep Learning, deep neural networks greatly promote the development of multimodal learning.

The goal of this special issue is to bring together perspectives from multiple disciplines (e.g., Computer Vision, Natural Language Processing, Machine Learning, Deep Learning, Healthcare AI, Medical Image ML, Bioinformatics, Cognitive Science, Sociology) to highlight major open questions and to identify research opportunities to address outstanding challenges in the domain of multimodal learning in the Deep Learning and Big Data Era.

Call for Papers

(CFP poster can be downloaded via this link)

Topics of Interests

Important Dates

Submission and Review