With the advent of the big data era, the size of data far exceeds the limits of storage capacity in our processing devices. This has led to a shift in our learning methodologies, moving away from traditional batch processing to embrace streaming learning approaches. In streaming learning, data is processed sequentially and discarded after learning, without the need for repetitive use, instead, incremental learning is used. However, streaming data in many real-world scenarios were collected from different type of sensors. So, these data are multimodal, such as video, sound, temperature, humidity, and other types of data, making data alignment and correlation more challenging. In addition, these multimodal streaming data were learned in uncertain decision situations, i.e., these data involve missing values, errors, and concept drift. This uncertainty often forces multimodal streaming learning to operate in less-than-ideal conditions. Therefore, researching how to enhance the effectiveness, generalization, and robustness of multimodal streaming learning under uncertain conditions becomes imperative.

The expected topics include, but are not limited to: 

• Transfer learning, model reuse, or continual learning for concept drifts adaption
• Graph based model, pre-trained model, meta learning, and reinforcement learning for concept drifts detection
• Concept drift detection, understanding and adaption in multiple data streams
• Deep learning for streaming data classification
• Semi-supervised classification of multimodal data streams with concept drifts
• Distribution-free one-pass Learning
• Drift Detection for Multi-label Data Streams
• Continuous learning for multimodal streaming data
• Audio/speech/music streams processing
• Multimodal stream learning benchmark datasets
• Multi-drift and multi-stream learning
• Multimodal stream processing platforms
• Large models of multimodal streaming learning
• Real-world applications of multimodal stream learning

SUBMISSION GUIDELINES

Papers submitted to this journal for possible publication must be original and must not be under consideration for publication in any other journals. Prospective authors should submit an electronic copy of their completed manuscript to https://mc03.manuscriptcentral.com/tst with manuscript type as “Special Issue on Multimodal Streaming Learning in Uncertain Decision Situations”. Further information on the journal is available at: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=5971803.

IMPORTANT DATES

Submission deadline: August 31, 2024

Expected publication schedule: March 1, 2025

GUEST EDITORS

Prof. Hang Yu, School of Computer Engineering and Science, Shanghai University, China. Email: yuhang@shu.edu.cn.

Prof. Yimin Wen, School of Computer Science and Information Security, Guilin University of Electronic Technology, China. Email: ymwen@guet.edu.cn.

Prof. Shiping Wen, Australian AI Institute, University of Technology Sydney, Australia. Email: Shipping.wen@uts.edu.au.

Prof. Zhong Li, Faculty of Mathematics and Computer Science, Fern Universität in Hagen, Germany. Email: zhong.li@fernuni-hagen.de.