Guest Editor(s)
Dr. Xianxun Zhu
Email: xianxun.zhu@mq.edu.au
Affiliation: School of Computing, Macquarie University, Sydney, Australia
Homepage:
Research Interests: multimodal learning, affective computing
Prof. Imad Rida
Email: imad.rida@utc.fr
Affiliation: Laboratory Biomechanics and Bioengineering, Université de Technologie de Compiègne, Compiègne, France
Homepage:
Research Interests: multimodal learning, machine learning, pattern recognition and signal/image processing
Dr. Lucia Cascone
Email: lcascone@unisa.it
Affiliation: Department of Computer Science, University of Salerno, Fisciano, Italy
Homepage:
Research Interests: applied mathematics for machine learning, biometrics, human-robot interaction, and pattern recognition
Dr. Hui Chen
Email: h.chen@mq.edu.au
Affiliation: School of Computing, Macquarie University, Sydney, Australia
Homepage:
Research Interests: multimodal Learning, probabilistic machine learning
Summary
Recent advances in multimodal learning have enabled the integration of heterogeneous data sources such as vision, language, audio, and sensor signals, significantly improving the performance of intelligent systems. However, real-world multimodal applications often face challenges including missing modalities, noisy inputs, and distributional shifts, which can severely affect model reliability and robustness.
This Special Issue aims to explore recent progress in multimodal learning with a focus on uncertainty estimation, reliability modeling, and robust fusion strategies. It seeks to advance both theoretical and practical developments for building trustworthy multimodal systems capable of operating under imperfect and dynamic conditions. Contributions from both centralized and distributed settings, including emerging paradigms such as federated and edge-based multimodal learning, are encouraged.
Suggested themes include:
· Uncertainty-aware multimodal fusion and inference
· Reliability modeling and confidence estimation in multimodal systems
· Learning with missing, noisy, or corrupted modalities
· Robust and trustworthy multimodal learning frameworks
· Efficient and scalable multimodal models
· Multimodal learning in federated and distributed environments
· Real-world applications such as healthcare, sentiment analysis, and intelligent systems
Keywords
multimodal learning; uncertainty quantification; reliability modeling
Login
Register
Submit a Paper
Propose a Special lssue