32nd International Conference on Multimedia Modeling

In total four special sessions has been accepted for MMM 2026.

Extended Reality and Multimedia Modelling (XR-MM)

The Extended Reality and Multimedia Modelling (XR-MM) special session at the Multimedia Modelling 2026 conference invites researchers, industry experts, and enthusiasts to explore the latest advancements in extended reality (XR) and multimedia technologies. This session will focus on the development and integration of XR solutions with multimedia analysis, retrieval, and processing methods, emphasizing seamless and interactive experiences that transform the way we live, work, and interact with our surroundings.
Details and Call for papers

Human-Centric Multimodal Behavior Analysis

This special session delves into cutting-edge methods and applications in human-centric multimodal behavior analysis. By integrating vocal intonations, facial expressions, gestures, physiological signals, human actions, body poses, and person re-identification techniques, the session aims to advance understanding in areas such as affective state recognition, real-time behavior tracking, robust learning methods, human action recognition, and person re-identification. Synthesizing insights from computer vision, speech processing, wearable sensing, and machine learning, the session seeks to drive innovation in healthcare, human-computer interaction, social robotics, and security applications.
Details and Call for papers

Modelling Robustness and Security for Multimedia AI (MARS-26)

The MARS (Modelling Robustness and Security for Multimedia AI) Special Session investigates the critical intersection of Multimedia Modelling, Artificial Intelligence, and Security. As AI/ML models become integral to multimedia analysis, processing, and generation, understanding and mitigating their vulnerabilities is paramount. This session focuses on challenges posed by adversarial attacks, data poisoning, model theft, and other security threats targeting multimedia AI systems. Through keynote speeches, paper presentations, and expert discussions, MARS-26 aims to foster research into novel modelling techniques for attack characterization, robust model development, defense strategies, and security verification in multimedia AI applications.
Details and Call for papers

Multi Object Multi Sensor Tracking (MOMST)

This session aims to bring together researchers, practitioners, and industry experts working on the challenges of tracking multiple objects using data from multiple (visual) sensors in various use cases such as traffic management, etc.
Details and Call for papers

The Extended Reality and Multimedia Modelling (XR-MM) special session at the Multimedia Modelling 2026 conference invites researchers, industry experts, and enthusiasts to explore the latest advancements in extended reality (XR) and multimedia technologies. This session will focus on the development and integration of XR solutions with multimedia analysis, retrieval, and processing methods, emphasizing seamless and interactive experiences that transform the way we live, work, and interact with our surroundings.

Topics of Interests

The XR-MM 2026 special session will address the following key topics:

• Technologies for next-generation XR applications across all domains: Exploring cutting-edge solutions in virtual reality (VR), augmented reality (AR), and mixed reality (MR) that push the boundaries of XR experiences.
  • Human factors in design of XR interfaces and interactions.
• Real-time 3D Modeling and Rendering: Investigating innovative techniques for creating realistic and dynamic 3D models and environments, enabling high-quality visuals and interactions in XR applications.
  • 3D modeling and asset management for immersive XR experiences
  • Synthetic Dataset Generation and Benchmarking for XR Calibration and Reconstruction
  • Learning-Based Calibration and Pose Estimation for Multi-View XR Systems with Low Overlap and Sparse Data
• AI for XR Content Creation: Utilizing artificial intelligence and machine learning for content analysis, understanding and retrieval to facilitate XR content generation.
  • Generative AI and foundation models for XR content creation and synthetic data generation
  • Multimedia analysis and AI-based approaches for media mining and adaptation in XR experiences
• AI-Driven Multimedia and XR Integration: Utilizing artificial intelligence and machine learning to enhance recognition and manipulation in XR environments, leading to more intuitive and engaging experiences.
  • Active object detection and real-time scene understanding from first- and third-person perspectives
  • Processing of egocentric multimedia datasets and streams for immersive XR environments
• Multisensory & multimodal Interfaces and Wearable Technologies: Investigating the latest advancements in haptic feedback, gesture recognition, and sensory input/output devices that facilitate natural and immersive interactions with XR and multimedia content.
• Adaptive and Interactive Content Delivery: Developing methods for optimizing and personalizing multimedia content based on user preferences, context, and device capabilities, ensuring a seamless XR experience.
• Security, privacy aspects, and mitigations for XR multimedia content

Organizers

• Claudio Vairo, CNR-ISTI, IT
• Imad H. Elhajj, AUB, LB
• Leonel Toledo, i2CAT, ES
• Dimitrios Zarpalas, CERTH, EL
• Georg Thallinger (georg.thallinger@joanneum.at), JOANNEUM RESEARCH, AT

This special session delves into cutting-edge methods and applications in human-centric multimodal behavior analysis. By integrating vocal intonations, facial expressions, gestures, physiological signals, human actions, body poses, and person re-identification techniques, the session aims to advance understanding in areas such as affective state recognition, real-time behavior tracking, robust learning methods, human action recognition, and person re-identification. Synthesizing insights from computer vision, speech processing, wearable sensing, and machine learning, the session seeks to drive innovation in healthcare, human-computer interaction, social robotics, and security applications.

Call for Papers

The MMM 2025 Special Session on Human-Centric Multimodal Behavior Analysis invites original research contributions that delve into the complexities of human behavior through the integration of multiple data modalities. This session aims to foster discussions on advanced methodologies and applications that enhance the understanding and interpretation of human behaviors in real-world contexts.

Topics of Interests

We welcome submissions on topics including, but not limited to:

• Multimodal Affective State Recognition
• Multimodal Human Action Recognition
• Multimodal Human Pose Estimation
• Real-Time Multimodal Behavior Tracking
• Multimodal Fusion Techniques for Behavior Analysis
• Privacy-Preserving Multimodal Learning
• Cross-Modality Person Re-Identification
• Explainable AI in Multimodal Behavior Analysis
• Multimodal Human-Computer Interaction
• Multimodal Behavior Analysis in Healthcare Applications
• Security Applications of Multimodal Behavior Analysis

Submission Types

• Full research papers
• Survey papers

Organizers

• Zhun Zhong, Hefei University of Technology, China, Email: zhunzhong007@gmail.com
• Nan Pu, University of Trento, Italy, Email: nan.pu@unitn.it
• Hong Liu, Xiamen University, China, Email: ynnliu.xmu@gmail.com
• Wenjing Li, Hefei University of Technology, China, Email: wenjingli@hfut.edu.cn

As AI and Machine Learning models revolutionize multimedia modelling, they introduce significant security vulnerabilities that must be addressed. The MARS-26 special session invites original, unpublished research focused on the robustness and security aspects of AI/ML models applied to multimedia data. We welcome submissions presenting novel modelling techniques, theoretical analyses, empirical studies, and application-focused perspectives.

Topics of Interests

• Modelling adversarial attacks specifically targeting multimedia models (e.g., image classifiers, object detectors, speech recognition, video analysis, generative models)
• Developing robust multimedia models and training strategies resistant to adversarial perturbations
• Techniques and models for detecting adversarial examples in multimedia data or streams
• Leveraging adversarial example techniques for generating counterfactual explanations of multimedia AI model decisions
• Model watermarking and fingerprinting techniques for tracing and protecting the intellectual property of multimedia AI models
• Security and robustness analysis of multimedia compression models or feature extraction pipelines against attacks
• Modelling, detecting, and defending against data poisoning and backdoor attacks in multimedia datasets and models
• Explainable AI (XAI) methods applied to understand and improve the security and robustness of multimedia models
• Certification and verification techniques for proving robustness properties of multimedia AI systems
• Security and privacy implications of federated learning for multimedia applications
• Modelling fairness and bias mitigation in the context of robust multimedia AI
• Benchmark datasets and evaluation protocols for assessing multimedia AI security and robustness

Submission Types

• Full research papers (12 pages)
• Short papers (6 pages)
• Demo papers (4 pages)

All submissions must follow the MMM 2026 formatting guidelines and be submitted through the conference submission system. Accepted papers will be published in the conference proceedings.

Special Session Format

• Keynote address (45 minutes)
• Technical paper presentations (20 minutes each)
• Interactive panel discussion (60 minutes)

Organizers

• Michael A. Riegler, Simula Research Laboratory (michael@simula.no)
• Nandor Knust, UiT

For any questions regarding the special session, please contact Michael A. Riegler at michael@simula.no.

Scope and Topics

We invite original contributions to the Special Session on Multi Object Multi Sensor Tracking (MOMST), held as part of the 28th International Conference on Multimedia Modeling (MMM 2026). This session aims to bring together researchers, practitioners, and industry experts working on the challenges of tracking multiple objects using data from multiple sensors.

Topics of interest include, but are not limited to:

• Multi-object multi-sensor tracking (MOMST) systems and architectures
• Sensor fusion techniques for robust tracking
• Data association and hypothesis tracking algorithms
• Deep learning-based tracking methods (CNNs, RNNs, Transformers)
• Multi-camera and multi-modal tracking
• Real-time object tracking in autonomous vehicles, robotics, or surveillance
• Evaluation frameworks and benchmarks (e.g., MOTChallenge, AI City Challenge)
• Datasets and simulation environments for MOMST research
• Applications in smart cities, security, transport, and Industry 4.0

Submission Guidelines

Submissions must follow the standard MMM 2026 guidelines and be submitted via the main MMM conference submission system. Please make sure to select the "Special Session: MOMST" track during submission. For paper templates and formatting instructions, visit: https://mmm2026.cz

Submitted papers are limited to 12 content pages, including all figures, tables, and appendices, in the Springer LNCS style. Additional 2 pages containing only cited references are allowed.

Organizers

• Mario Döller, (mario.doeller@fh-kufstein.ac.at)
• Ruben Tous, (ruben.tous@upc.edu)