Multimedia Applications and Processing
(MMAP)

Riga, Latvia, 23-26 August, 2026

Background and Goals

Multimedia data have become a fundamental component of modern information systems, encompassing visual, auditory, textual, and sensory modalities. The rapid growth of multimedia content has created new challenges in representation, understanding, indexing, retrieval, interaction, and generation of complex data streams. Addressing these challenges requires advanced methods that combine signal and image processing, computer vision, machine learning, and artificial intelligence.

Recent advances in large-scale pre-trained and foundation models, multimodal learning, and generative AI have profoundly transformed multimedia processing and analysis. Vision–language–audio models, diffusion-based generative techniques, and transformer architectures now enable unified understanding and synthesis of multimedia content, opening new opportunities for intelligent, interactive, and human-centered systems. These developments impact a wide range of domains, including healthcare, industry, education, creative media, autonomous systems, and public services.
At the same time, new research challenges have emerged, such as efficient and sustainable model design, learning with limited or noisy data, robustness and trustworthiness of AI systems, explainability, and deployment on edge and embedded platforms.

The MMAP Thematic Session provides a forum for researchers and practitioners to discuss recent advances, emerging trends, and future challenges in multimedia, vision, graphics, and multimodal AI. The session aims to foster interdisciplinary exchange and collaboration between communities working on theoretical foundations, algorithmic developments, system design, and real-world applications.
We invite original, previously unpublished contributions that are not under consideration elsewhere. Submissions may address conceptual, methodological, or application-oriented aspects of multimedia and multimodal intelligent systems, with particular emphasis on innovative, scalable, and impactful solutions.
Paper acceptance and publication will be based on relevance to the session theme, originality, technical quality, clarity of presentation, and significance of results.

Topics

We welcome contributions including, but not limited to, the following topics:

Multimedia Processing and Multimodal Systems

Multimodal data representation and joint processing of audio, image, video, and text
Multimodal foundation models and large-scale pre-trained models
Content understanding, retrieval, and semantic reasoning
Generative multimedia models and content synthesis
Self-supervised, weakly supervised, and data-centric learning approaches
Cloud, edge, and mobile multimedia systems
Human–computer interaction and intelligent multimedia interfaces
Trustworthy, explainable, and responsible multimedia AI

Machine Vision, Image Processing, and Analysis

Object detection, segmentation, tracking, and recognition
Scene understanding and visual reasoning
Vision foundation models and prompt-based vision systems
3D vision, neural representations, and neural rendering
Stereo, multispectral, and hyperspectral imaging
Embedded and robotic vision systems
Robustness, uncertainty estimation, and out-of-distribution detection
Modeling of human visual perception

Visualization and Computer Graphics

Data-driven and generative graphics
Neural rendering and image synthesis
Visualization for large-scale and complex data
Virtual, augmented, and mixed reality
AI-assisted content creation and creative media
Human-centered visualization and interaction design
Computer animation, games, and interactive entertainment

Machine Learning for Multimedia, Vision, and Graphics

Multimodal transformers and unified architectures
Diffusion models and generative learning
Foundation models and instruction-tuned systems
Continual, lifelong, and adaptive learning
Efficient learning: pruning, distillation, quantization
Deep reinforcement learning for perception and interaction
Graph-based and structured learning models

Applications

Multimedia systems in healthcare and medical imaging
Autonomous and intelligent transportation systems
Remote sensing and Earth observation
Digital microscopy and computational biology
Surveillance and security systems
Document analysis and OCR
Creative industries and media production
E-learning, e-commerce, and e-society applications
Authentication, watermarking, and multimedia security

Thematic Session organizers

Kwaśnicka, Halina, Wrocław University of Science and Technology, Poland
Stanescu, Liana, University of Craiova, Romania
Iwanowski, Marcin, Warsaw University of Technology, Poland
Śluzek, Andrzej, Warsaw University of Life Sciences, Poland

Contact: mmap@fedcsis.org

Submission rules

Authors should submit their papers as Postscript, PDF or MSWord files.
The total length of a paper should not exceed 12 pages IEEE style (including tables, figures and references). More pages can be added, for an additional fee. IEEE style templates are available here.
Papers will be refereed and accepted on the basis of their scientific merit and relevance to the Topical Area.
Preprints containing accepted papers will be published online.
Only papers presented at the conference will be published in Conference Proceedings and submitted for inclusion in the IEEE Xplore® database.
Conference proceedings will be published in a volume with ISBN, ISSN and DOI numbers and posted at the conference WWW site.
Conference proceedings will be submitted for indexation according to information here.
Organizers reserve right to move accepted papers between FedCSIS Sessions.