Call For Papers
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
MCMI Workshop 2026 - 2nd International Workshop on Multi- and Cross-Modal Information for Enhanced Pattern Recognition
In conjunction with the 28th International Conference on Pattern Recognition (ICPR 2026).

MCMI 2026 @ ICPR 2026
Website: https://mcmi-workshop.github.io/2026/
August 21, 2026, Lyon, France
IAPR-endorsed event
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

*** Important Dates ***
++ Electronic submission of full papers: April 20, 2026
++ Notification of paper acceptance: May 20, 2026
++ Camera-ready of accepted papers: June 6, 2026
++ Workshop: August 21, 2026

All deadlines: 23:59 AoE (Anywhere on Earth).

***********************************************************************
Goal
***********************************************************************

The MCMI workshop explores the convergence and fusion of information from multiple modalities, a central challenge in modern AI systems for robust pattern recognition and understanding. This interdisciplinary workshop encourages collaboration across fields such as audio processing, computer vision, and natural language processing. It serves as a venue to discuss recent findings, share innovative methodologies, and address future directions in multimodal and cross-modal pattern analysis. Special attention is given to applications in healthcare, human-machine interaction, and complex data analysis, where multimodal approaches are proving increasingly valuable.

***********************************************************************
Topics of Interest
***********************************************************************
We invite submissions of high-quality papers reporting original research and significant new work not under review or published elsewhere. Topics include, but are not limited to:

Multimodal Architectures and Learning:
- Multimodal Fusion Strategies
- Deep Learning Architectures for Multimodal Data
- Cross-Modal Feature Extraction and Representation Learning
- Self-Supervised and Contrastive Multimodal Learning
- Large Multimodal Models and Foundation Models
- Temporal Modeling in Multimodal Systems

Applications:
- Audio-Visual Speech Recognition
- Scene and Object Recognition from Audio-Visual Cues
- Emotion Recognition from Multimodal Signals
- Multimodal NLP and Vision-Language Models
- Multimodal Applications in Healthcare
- Interaction Paradigms for Multimodal Data Acquisition

Evaluation, Ethics, and Security:
- Multimodal Datasets and Benchmarks
- Robustness and Generalization across Modalities
- Adversarial Attacks and Defenses
- Privacy-Preserving Multimodal Learning
- Explainability in Multimodal Systems
- Ethical Considerations in Multimodal Data

************************************************************************
Submission Guidelines
*************************************************************************
Papers must be formatted according to Springer's LNCS template and submitted via Microsoft CMT. Submissions should present substantial new work and should not be under review elsewhere:

- Paper length: up to 15 pages in Springer LNCS format, including figures, tables, references, and appendices.
- Full papers (more than 6 pages) will be published in LNCS proceedings.
- Short papers (up to 6 pages) may be presented but will not appear in the proceedings.
- Submission link: https://cmt3.research.microsoft.com/MCMI2026/Track/1/Submission/Create
- Peer review: Double-blind (no author names or affiliations in the manuscript).
- LaTeX template: https://icpr2026.org/files/ICPR_2026_LaTeX_Templates.zip
- Word template: https://icpr2026.org/files/ICPR_2026_DOC_Templates.zip

Accepted full papers will be published in the Lecture Notes in Computer Science series by Springer. At least one author of each accepted paper must register for ICPR 2026 by the camera-ready deadline. Papers not presented at the workshop will not be included in the proceedings.

*************************************************************************
Workshop Organizers
*************************************************************************
- Moreno La Quatra, Kore University of Enna, Italy
- Nicole Dalia Cilia, Kore University of Enna, Italy
- Vincenzo Conti, Kore University of Enna, Italy
- Salvatore Sorce, Kore University of Enna, Italy
- Giuseppe Pappalardo, Kore University of Enna, Italy
- Valerio Mario Salerno, Kore University of Enna, Italy

For questions regarding the submission process, please contact the organizers at mcmi@unikore.it.