Plenary Speakers

Sponsors

Regular papers presented at the conference will be included in the workshop proceedings. As for the previous EUVIP workshops, all accepted regular papers will be included in IEEE Xplore. Regular papers presented at the conference will be included in the workshop proceedings. As for the previous EUVIP workshops, all accepted regular papers will be included in IEEE Xplore. EUVIP 2025 will recognize outstanding contributions with the Best Paper Award, for the most distinguished regular paper, as well as the Best Student Paper Award and the Student poster/demo Award.

Quick Links

• Calls
• Information for Authors
• Important Dates

Sponsors

Plenary Speakers

Tutorials

Volumetric Video: How to capture authentic 3D representations of humans?

Tutorial

Abstract

Volumetric video is considered as one of the major technological break troughs for highly realistic representation of humans in eXtended Reality applications, future video communication services and collaboration tools. This technology becomes especially important in use cases, where convincing and natural representation of humans and their emotions is required. It significantly paves the way to overcome the uncanny valley for representation of digitized humans. This talk will focus on the state of the art of volumetric video as well as potential future directions. We present details on various volumetric capture systems with different complexities and give insights on overall volumetric video production and processing workflows. Participants will learn about practical challenges in designing a multi-view capture system. Novel rendering and 3D content generation concepts, such as neural rendering, Gaussian Splatting and AI-based dynamic surface reconstruction will be discussed. An overview on interactive volumetric video solutions, volumetric video encoding and streaming will be given. While keeping a strong technical focus, the authors will enrich the tutorial by their long years scientific and practical experience and give examples from most recent productions.

Biography

Oliver Schreer is head of “Immersive Media & Communication” research group at “Vision & Imaging Technologies” department at Fraunhofer Heinrich-Hertz-Institute and Associate Professor at Technical University Berlin. Since August 1998, he is working at Fraunhofer HHI. He started as scientific project manager and since January 2015, he is leading the Immersive Media & Communications Group at Vision & Imaging Technologies Department together with his colleague Ingo Feldmann. His main research fields are 3D video processing and immersive and interactive media services and applications exploiting Augmented and Virtual Reality technologies. He published more than 130 papers and he acted as main editor of several books. In May 2019, Oliver Schreer and his colleagues I. Feldmann and P. Kauff have been awarded with the Joseph-von-Fraunhofer Prize entitled by "Realistic people in virtual worlds - A movie as a true experience".Ingo Feldmann is head of the Immersive Media & Communication group at Vision & Imaging Technologies department. He received his Dipl.-Ing. degree in Electrical Engineering from the Technical University of Berlin in 2000 respectively. Since September 2000, he is with Fraunhofer HHI, where he was engaged in various research activities in the field of 2D image processing, 3D scene reconstruction and modelling, digital cinema, multi-view projector-camera systems, real-time 3D video conferencing and immersive TV applications. His current research focus is in the field of future Virtual Reality, Augmented Reality and Mixed Reality applications and Volumetric Video Acquisition. In May 2019, Ingo Feldmann and his colleagues O. Schreer and P. Kauff have been awarded with the Joseph-von-Fraunhofer Prize entitled by "Realistic people in virtual worlds - A movie as a true experience".

From Subjective Ratings to Objective Metrics: A Tutorial on Perceptual Visual Quality in Multimedia Communication

Tutorial

Abstract

As multimedia services like video streaming, video conferencing, virtual reality (VR), and online gaming continue to evolve, ensuring high perceptual visual quality is crucial for enhancing user experience and maintaining competitiveness. However, multimedia content inevitably undergoes various distortions during acquisition, compression, transmission, and storage, leading to quality degradation. Therefore, perceptual visual quality assessment, which evaluates multimedia quality from a human perception perspective, plays a vital role in optimizing user experience in modern communication systems. This tutorial provides a comprehensive overview of perceptual visual quality assessment, covering both subjective methods, where human observers directly rate their experience, and objective methods, where computational models predict perceptual quality based on measurable factors such as bitrate, frame rate, and compression levels. The session also explores quality assessment metrics tailored to different types of multimedia content, including images, videos, VR, point clouds, meshes, and AI-generated media. Furthermore, we discuss challenges posed by diverse multimedia characteristics, complex distortion scenarios, and varying viewing conditions. By the end of this tutorial, attendees will gain a deep understanding of the principles, methodologies, and latest advancements in perceptual visual quality assessment for multimedia communication.

Biography

Dr Wei Zhou is an Assistant Professor at Cardiff University, UK. Wei’s research interests mainly focus on perceptual image processing and multimodal computing. Dr Zhou has served as the Chair of the Elections Committee of IEEE UK and Ireland SPS Chapter, the Organization Committee of IEEE VCIP 2025 (Grand Challenge Chair), and the Founding Chair for the 1st Cardiff Image and Vision Computing Workshop. Dr Zhou is an Associate Editor for 8 journals, such as IEEE Transactions on Neural Networks and Learning Systems (TNNLS), ACM Transactions on Multimedia Computing Communications and Applications (TOMM), Pattern Recognition, etc. Dr Zhou has also served as the Guest Editor for many journals such as IEEE Journal of Biomedical and Health Informatics (JBHI) and Pattern Recognition; the Lead Competition Organizer for ICCV 2025; the Lead Workshop and Tutorial Organizer/Speaker for ACM MM 2025; the Workshop Organizer for IEEE BIBM 2025 and IEEE IROS 2025; the Area Chair for ACM MM 2024-2025, IEEE ICME 2025, ICIP 2025, and IJCNN 2025; the Special Session Organizer for IEEE ICME 2025, QoMEX 2025, MMSP 2023, and ICIP 2024-2025. Dr Zhou received the Grand Challenge Winner Award in CVPR CLIC Perceptual Metric Track in 2021 (1st place), the ACM SIGMM China Outstanding Doctoral Dissertation Award in 2022 (1st place in Multimedia research), the IEEE CASS VSPC Rising Star Honorable Mention Award in 2024 (the first recipient in image quality assessment field worldwide) and is listed in the Top 2% Scientists by Stanford University in 2024.Dr Hadi Amirpour is an Assistant Professor at the Institute of Information Technology (ITEC), University of Klagenfurt. Previously, he was a postdoctoral research fellow at the Christian Doppler (CD) Laboratory ATHENA. He earned his Ph.D. in Computer Science from the University of Klagenfurt in 2022. He was involved in EmergIMG, a Portuguese consortium on emerging imaging technologies, funded by the Portuguese funding agency and H2020. His research interests include video streaming, image and video compression, quality of experience (QoE), emerging 3D imaging technologies, and medical image analysis. He has contributed to standardization committees such as JPEG Pleno and MPEG and has been co-chairing Qualinet TF7 since 2021. Additionally, he serves as an Associate Editor of IEEE TCSVT. He has published in top-tier venues such as IEEE TIP, IEEE TMM, IEEE TCSVT, ACM TOMM, ACM MM, IEEE ICME, etc., and holds granted patents in his areas of expertise. He has also received the Best Paper Awards from PCS 2024 and NAB 2025. Furthermore, he has played an active role in organizing conferences, special sessions, workshops, and tutorials at leading international events, including IEEE ICME 2025, IEEE QoMEX 2025, ACM MM 2025, VQEG 2024, IEEE ICME 2023, ACM MM 2022, IEEE EUVIP 2022, and ACM MobiSys 2022.Imaging Brain Diseases through Connectivity: Advanced Diffusion MRI and Deep Learning for Biomarkers DiscoveryImaging Brain Diseases through Connectivity: Advanced Diffusion MRI and Deep Learning for Biomarkers Discovery

Imaging Brain Diseases through Connectivity: Advanced Diffusion MRI and Deep Learning for Biomarkers Discovery

Tutorial

Abstract

This tutorial centers on how advanced diffusion MRI (dMRI) and AI methods can uncover novel biomarkers of brain disorders by analyzing both tissue microstructure and white matter connectivity. We begin with the clinical challenges posed by neurodegenerative and neuropsychiatric conditions—Alzheimer’s disease, Alcohol Use Disorder (AUD), stroke, and cerebral palsy—and show how changes in brain microstructure and tract-level connectivity can serve as sensitive and specific imaging markers for diagnosis and monitoring. Participants will explore how diffusion MRI, uniquely suited to probe brain tissue architecture, enables these discoveries. We'll contrast traditional models like Diffusion Tensor Imaging (DTI) with advanced multi-shell and multi-fixel approaches—such as NODDI, DIAMOND, and Microstructure Fingerprinting (MF)—which allow for disentangling crossing fibers and estimating properties of multiple fiber populations within a voxel. We then examine tractography, the reconstruction of white matter pathways, and how it complements voxel-wise analyses by enabling tract-specific assessments of damage or degeneration. Using real case studies (e.g., hippocampal-parahippocampal pathways in Alzheimer’s, or corticospinal tract in stroke), we present how to extract and analyze metrics along tracts. The UNRAVEL framework will be introduced as a robust method to attribute fixel-level properties to tract segments, with a focus on angular weighting, which improves accuracy in regions of complex fiber geometry. In the second part of the tutorial, we turn to AI integration, showing how these rich dMRI-derived features can be used with Vision Transformers (ViTs)—specifically the Swin Transformer—to develop predictive models. Participants will learn strategies to reshape and adapt 3D microstructural maps for compatibility with 2D ViTs, manage data scarcity with transfer learning and LoRA-based fine-tuning, and interpret results using tools like Grad-CAM to highlight clinically relevant regions. The tutorial emphasizes practical implementation, with demos using public datasets like ADNI. We’ll show how to build an end-to-end pipeline—from acquisition and modeling to prediction and explainability—capable of detecting disease signatures and tracking progression or treatment response.

Biography

Benoît Macq is Full Professor at the Louvain School of Engineering (UCLouvain, Belgium) and Editor-in-Chief of IEEE Transactions on Image Processing. A Fellow of the IEEE and member of the Royal Academy of Science of Belgium, he has led pioneering research in image compression, medical imaging, and trusted AI systems. He has supervised over 60 PhDs and co-founded 11 spin-off companies. He served as Vice-President of UCLouvain (2009–2014), and is currently Director of the Royal Academy’s “Technology and Society” class and Head of the TRAIL Institute (Trusted AI Labs). His international roles have included visiting positions at MIT, McGill, and Telecom Paris.

Multimedia content protection: from data hiding to encryption, through obscuration and secret sharing

Tutorial

Abstract

More and more multimedia data, such as images, videos and 3D content, are transmitted over digital networks, stored or shared in the Cloud, and shared and visualized on social networks. In addition to the need to compress this multimedia data, which is very voluminous, for reasons of confidentiality, privacy or secret information, it is increasingly necessary to protect multimedia content directly, and not only the access to networks. In this tutorial, after detailing the specifics of each type of multimedia data, both in terms of compression and protection, we will present the various possible facets for protecting this multimedia content and illustrate with different applications from medical imaging to the Metaverse, passing through the manufacturing industry for fashion and videos from drones. The first part will be dedicated to data hiding, in order to differentiate between watermarking and steganography, and will finish with a discussion of steganalysis. The second part will detail the cryptographic aspects applied to multimedia content, distinguishing selective encryption from partial encryption, and concluding with crypto-compression (image, video and 3D object). The third part will present different methods of image darkening, reversible or not, visible or not. We will see that non-visible image obscuration relies mainly on the generation of false images. And finally, methods for sharing secrets applied to images will be discussed. Then we will end on a discussion of the cat and mouse game, to highlight the adversarial attacks and defenses that need to be taken into account.

Biography

William Puech received the diploma of Electrical Engineering from the Univ. Montpellier, France (1991) and a Ph.D. Degree in Signal-Image-Speech from the Polytechnic National Institute of Grenoble, France (1997) with research activities in image processing and computer vision. He served as a Visiting Research Associate to the University of Thessaloniki, Greece. From 1997 to 2008, he has been an Associate Professor at the Univ. Montpellier, France. Since 2009, he is a full Professor in image processing at the Univ. Montpellier, France. His current interests are in the areas of image forensics and security for safe transfer, storage and visualization by combining data hiding, compression, cryptography and machine learning. He is head of the ICAR team (Image and Interaction) in the LIRMM and has published more than 50 journal papers and 160 conference papers and is currently Associate Editor for 4 journals (SPIC, SP, JVCIR and IEEE TCSVT) in the areas of image forensics and security and Senior Area Editor for IEEE TIFS. Since 2017 he has been the general chair of the IEEE Signal Processing French Chapter. He has been a member of the IEEE Information Forensics and Security TC between 2018 and 2020 and then again between 2022 and 2024. Since 2021 he has also been a member of the IEEE Image, Video and Multidimensional Signal Processing TC, and since 2025 member of the IEEE Multimedia Signal Processing TC.

Images, perception, and the subjective space of privacy

Plenary Talk

Abstract

Accurately predicting image privacy in a manner that aligns with human understanding is a significant challenge, often compounded by the varied interpretations of 'private'. To address this interpretability gap, the talk will present how to predict image privacy using intuitive natural language descriptors linked to collective human privacy perceptions, leveraging multimodal alignment. Additionally, the talk will introduce eight privacy personas that characterize diverse user groups based on their privacy knowledge, behavior, self-confidence, and perceived importance of privacy protection. This nuanced understanding of differences among people is fundamental for developing contextually aware and personalized enhancing technologies, thus giving individuals more control.

Biography

Andrea Cavallaro is the Idiap Director and a Full Professor at EPFL. He is a Fellow of the Higher Education Academy, a Fellow of the International Association for Pattern Recognition, and an ELLIS Fellow. His research interests include machine learning for multimodal perception, computer vision, machine listening, and information privacy.Andrea received his PhD in Electrical Engineering from EPFL in 2002. He was a Research Fellow with British Telecommunications in 2004 and was awarded the Royal Academy of Engineering Teaching Prize in 2007; three student paper awards on target tracking and perceptually sensitive coding at IEEE ICASSP in 2005, 2007 and 2009; and the best paper award at IEEE AVSS 2009. In 2010, he was promoted to Full Professor at Queen Mary University of London, where he was the founding Director of the Centre for Intelligent Sensing and the Director of Research of the School of Electronic Engineering and Computer Science. He was a Turing Fellow (2018-2023) at The Alan Turing Institute, the UK National Institute for Data Science and Artificial Intelligence.He was selected as IEEE Signal Processing Society Distinguished Lecturer (2020-2021) and served as Chair of the IEEE Image, Video, and Multidimensional Signal Processing Technical Committee (2020-2021). He also served as member of the Technical Directions Board of the IEEE Signal Processing Society and as elected member of the IEEE Multimedia Signal Processing Technical Committee and chair of the Awards committee of the IEEE Signal Processing Society, Image, Video, and Multidimensional Signal Processing Technical Committee.He served as Senior Area Editor for the IEEE Transactions on Image Processing and served as Editor-in-Chief of Signal Processing: Image Communication (2020-2023); as Area Editor for the IEEE Signal Processing Magazine (2012-2014); and as Associate Editor for the IEEE Transactions on Image Processing (2011-2015), IEEE Transactions on Signal Processing (2009-2011), IEEE Transactions on Multimedia (2009-2010), IEEE Signal Processing Magazine (2008-2011) and IEEE Multimedia (2016-2018). He also served as Guest Editor the IEEE Transactions on Multimedia (2019), IEEE Transactions on Circuits and Systems for Video Technology (2017, 2011), Pattern Recognition Letters (2016), IEEE Transactions on Information Forensics and Security (2013), International Journal of Computer Vision (2011), IEEE Signal Processing Magazine (2010), Computer Vision and Image Understanding (2010), Annals of the British Machine Vision Association (2010), Journal of Image and Video Processing (2010, 2008), and Journal on Signal, Image and Video Processing (2007).He published a monograph on Video tracking (2011, Wiley) and three edited books: Multi-camera networks (2009, Elsevier); Analysis, retrieval and delivery of multimedia content (2012, Springer); and Intelligent multimedia surveillance (2013, Springer).

Perceptual Organization and Image Aesthetic Assessment in Humans and Machines

Plenary Talk

Abstract

Several developments in the past decade, such as convolutional neural networks, deep learning, and Vision Transformers, have boosted the performance of machine vision enormously. Although dedicated machine vision models often outperform humans in several tasks, the similarity of their way of working with visual information processing has been overrated. For instance, convolution is just one of the operations that early cortical layers in the human brain are conducting, and describing Vision Transformers as attention networks is misleading. In this lecture, I will focus on some fundamental differences between human and computer vision, such as their way of learning and their flexibility in doing multiple tasks with the same fixed architecture. I will highlight the fundamental role of perceptual organization in human vision, which is almost completely ignored in machine vision nowadays. I will also sketch our ongoing research program to try to predict, explain, and understand human preferences for images based on their perceptual organization. Finally, I will also demonstrate how image aesthetic assessment can profit from a proper collaboration between human vision and computer vision scientists.

Biography

Johan Wagemans is Full Professor at the Department of Brain & Cognition at the University of Leuven (KU Leuven) in Belgium. He has published more than 350 papers in international peer- reviewed journals, has edited the Oxford Handbook of Perceptual Organization, and is Senior Editor of Cognition, and Editor-in-Chief of Art & Perception. He is currently leading two large interdisciplinary research programs on perception and appreciation of images and art, one funded by the Flemish Government (Methusalem) and one funded by the European Research Council (GRAPPA).

Towards hyper-realistic and immersive visual communications

Plenary Talk

Abstract

Nowadays, thanks to rapid technological progresses over the last decades, digital images and video sequences are ubiquitous, with many remarkable and successful applications and services. A key driver to research and development activities has been the objective to provide an ever-improving visual quality and user experience.In this context, one of the next frontiers is to be able to faithfully represent the physical world and to deliver a perceptually hyperrealist and immersive visual experience. On the one hand, the human visual system is able to perceive a wide range of colors, luminous intensities, and depth, as present in a real scene. However, current traditional imaging technologies cannot capture nor reproduce such a rich visual information. On the other hand, immersive applications aim at giving to the user the sense of being present and immersed in one location or environment, without being physically there.Recent research innovations have made it possible to address current bottlenecks in multimedia systems. As a result, new multimedia signal processing areas have emerged such as ultra-high definition, high dynamic range imaging, light fields, and point clouds. These technologies have the potential to bring a leap forward for upcoming multimedia systems. However, the effective deployment of hyper-realistic video technologies entails many technical and scientific challenges.In this talk, I will discuss a few recent research activities related to hyper-realistic and immersive imaging. I will first consider point clouds, a very promising type of representation. One major distinguishing feature of point clouds is that, unlike images, they do not have a regular structure. Moreover, they can also be very sparse. For these reasons, point cloud processing presents significant challenges. Here, I will present recent learning-based approaches for point cloud compression and quality assessment. In a second phase, I will discuss high dynamic range imaging and in particular tone mapping operators (TMO). TMOs are used to compress the dynamic range with the aim of preserving the perceptual cues of the scene. Here, I will show how we can leverage semantic information as well as contextual cues from the scene to drive a TMO in a way similar to how expert photographers retouch images.

Biography

Dr. Frederic Dufaux is a CNRS Research Director at Université Paris-Saclay, CNRS, CentraleSupélec, Laboratoire des Signaux et Systèmes (L2S, UMR 8506), where he is head of the Telecom and Networking research hub. He is a Fellow of IEEE.Frederic received the M.Sc. in physics and Ph.D. in electrical engineering from the Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland, in 1990 and 1994 respectively. He has over 30 years of experience in research, previously holding positions at EPFL, Emitall Surveillance, Genimedia, Compaq, Digital Equipment, and MIT.Frederic was Vice General Chair of ICIP 2014, General Chair of MMSP 2018, and Technical Program co-Chair of ICIP 2019 and ICIP 2021. He is Technical Program co-Chair of ICIP 2025 and MMSP 2025, and General Chair of ICME 2026. He served as Chair of the IEEE SPS Multimedia Signal Processing (MMSP) Technical Committee in 2018 and 2019. He was a member of the IEEE SPS Technical Directions Board from 2018 to 2021. He was Chair of the Steering Committee of ICME in 2022 and 2023. Since 2025, he is IEEE SPS Vice President Technical Directions, and member of the IEEE SPS Board of Governors and Executive Committee. He was also a founding member and the Chair of the EURASIP Technical Area Committee on Visual Information Processing from 2015 to 2021.He was Editor-in-Chief of Signal Processing: Image Communication from 2010 until 2019. Since 2021, he is Specialty Chief Editor of the section on Image Processing in the journal Frontiers in Signal Processing. In 2022, he received the EURASIP Meritorious Service Award, “for his leadership and contributions for the development of visual information processing within EURASIP”.Frederic is on the Executive Board of Systematic Paris-Region since 2019, a European competitiveness cluster which brings together and drives an ecosystem of excellence in digital technologies and DeepTech.He has been involved in the standardization of digital video and imaging technologies for more than 15 years, participating both in the MPEG and JPEG committees. He was co-chairman of JPEG 2000 over wireless (JPWL) and co-chairman of JPSearch. He is the recipient of two ISO awards for these contributions.His research interests include image and video coding, 3D video, high dynamic range imaging, visual quality assessment, video surveillance, privacy protection, image and video analysis, multimedia content search and retrieval, video transmission over wireless network. He is author or co-author of 3 books, more than 250 research publications (h-index=53, 11000+ citations) and more than 25 patents issued or pending. He is in the « World’s Top 2% Scientists » list from Stanford University.

General Information

Webmaster

Registration

TBD

Program

• Program at a Glance
• Plenary Talks
• Tutorials
• Special Sessions

Special Sessions

Density Map Modeling on the Edge: Towards Sustainable Agri-Food Supply Chains

Special Session

Abstract

Given the global urgency to reduce food waste and enhance the sustainability of Agri-Food Supply Chains (AFSCs), responsive inventory planning in agri-food retail has become increasingly imperative for businesses striving toward operational excellence. Beyond environmental repercussions, food waste imposes significant financial burdens due to overstocking incidents and misallocated resources that lead to unnecessary expenditures. To address these timely challenges, this session contributes to the EUVIP 2025 themes by bridging visual computing and image processing concepts for socially impactful applications. It does this by introducing an edge-based visual counting methodology designed to support real-time replenishment strategies based on the On-Shelf Availability (OSA) index. Our key contributions are as follows:1. A novel density-map modeling approach is used to provide a pixel-wise spatial representation of the OSA index.
2. A benchmark dataset called AgriShelf is annotated with centroid labels to generate ground truth density maps and made publicly available on Mendeley Data.
3. A lightweight adaptation of the Multi-Column Convolutional Neural Network (MCNN), called mMCNN, is proposed for edge deployment.
4. A real-life pilot prototype using Jetson Nano and Jetson Orin Nano devices is demonstrated to validate the system’s practical value for real-life retail environments.The system demonstrates high inference efficiency with negligible compromise in accuracy on both edge devices. This session will conclude with a real-life pilot prototype, showcasing its potential for real-world integration. To this end, it advances insights into the visual computing capacity for sustainable transformation in AFSCs, which is an essential pillar of EUVIP 2025.

Biography

Eng. Tala Jano is a Research Assistant holding BSc and MSc degrees in Electrical Engineering from Qatar University. Her work focuses on Artificial Intelligence (AI) in sustainability-oriented research. As part of her MSc thesis, she earned a Best Paper Award at an international conference in Japan and published a benchmark dataset to support computer vision applications in the agri- food industry. She has also submitted additional journal and conference papers related to her thesis work.Prof. Ridha Hamila is a Full Professor of Electrical Engineering at Qatar University with expertise in communication systems, signal processing, and applied machine learning. He has been involved in numerous industrial projects, including collaborations with Ooredoo, the Qatar Research, Development, and Innovation (QRDI) Council, the Finnish Academy, Nokia, and several European Union (EU) research and education programs.Dr. Mohamed Kharbeche is a Research Assistant Professor at the Qatar Transportation and Traffic Safety Center at the College of Engineering at Qatar University. He holds a Ph.D. in Operations Research and Management Science and serves as the Principal Investigator for several research projects on traffic systems and supply chain modeling, funded by the QRDI Council.

Recent Advancements in Medical Imaging
and Image-guided diagnostic and treatment

Special Session

Abstract

Medical imaging analysis plays a vital role in modern healthcare, enabling earlier diagnosis, precise treatment planning, and improved patient outcomes. In recent years, advances in visual information processing have significantly trans formed the landscape of medical imaging, particularly with the integration of deep learning, multimodal fusion, and self-supervised learning. However, chal lenges such as data scarcity, domain shift, annotation bottlenecks, and model interpretability remain central issues in the field.This special session aims to bring together researchers and practitioners working at the intersection of medical imaging and signal/image processing to present novel methods, applications, and perspectives. Topics of interest include but are not limited to segmentation, classification, registration, and synthesis of medical images using advanced machine learning models; domain adaptation and generalization techniques; multimodal fusion of imaging and non-imaging data; uncertainty quantification; and explainability in AI-driven medical analysis.The session is particularly well suited for EUVIP 2025, given the conference’s emphasis on signal and visual information processing. Medical imaging provides a highly relevant and impactful domain where methodological advances in image processing and machine learning can be rigorously applied and evaluated.The session will not only showcase cutting-edge solutions but also foster interdisciplinary dialogue between signal processing researchers, clinicians, and healthcare technologists. It aligns with the growing interest in applying vision and signal processing tools to real-world, high-stakes applications, and offers a platform for presenting both theoretical contributions and clinically relevant use cases.

Biography

Fares Bougourzi received the Master’s degree in Electronics with a specialization in Telecommunications in 2013 from the University of Biskra, Algeria, and the Ph.D. degree in Electronics in 2020 from the University of Abderrahmane Mira, B ́eja ̈ıa, Algeria. He is currently affiliated with Junia, UMR 8520 IEMN, CNRS, Centrale Lille, and the University of Polytechnique Hauts-de-France, Lille, France. His current research interests include deep learning, computer vision, pattern recognition, generative AI, medical imaging, biometrics, and face analysis. He has published over 30 papers in top-tier journals and international conferences.Abdelmalik Taleb-Ahmed received in 1992 PhD in electronics and microelectronics from universit ́e des Sciences et Technologies de Lille 1. He was associate professor in Calais until 2004. He joined the Universit ́e Polytechnique des Hauts de France in 2004, where he is presently Full Professor. He joined the laboratory IEMN DOAE. his research focused on computer vision and artificial intelligence and machine vision. His research interests include segmentation, classification, data fusion, pattern recognition, computer vision, and machine learning, with applications in biometrics, video surveillance, autonomous driving, and medical imaging. He has (co-)authored over 85 peer-reviewed papers and (co-)supervised 20 graduate students in these areas of research. His recent research revolves mainly around : Enhanced Perception and HD Mapping in intelligent Transportation, Digitalization of Road and the Signaling, E-Health and Artificial Intelligence, pattern recognition, computer vision, and information fusion, with applications in affective computing, biometrics, medical image analysis, and video analytic and surveillance.Fadi Dornaika received the Master of Science degree in Signal, Image and Speech Processing in 1992 and the Ph.D. degree in Computer Science in 1995 from Grenoble Institute of Technology, Grenoble, France. He has held various research positions in Europe, China and Canada. He is currently a research professor at Ikerbasque, Basque Foundation for Science, Bilbao, Spain, and the University of the Basque Country UPV/EHU, San Sebastian, Spain. He has published more than 350 papers in the field of computer vision, pattern recognition and machine learning, including 150 peer-reviewed journal articles in (IEEE Trans. Robotics & Automation, IEEE Trans. Cybernetics, IEEE Trans. Neural Networks and Learning Systems, IEEE Trans. CSVT, IEEE Trans. SMC, Information Fusion, Information Sciences, Neural Networks, Pattern Recognition, Knowledge-based Systems, Int. Journal of Computer Vision, Int. Journal of Robotics Research, etc.). His current research interests include: Manifold Learning, Supervised Learning, Multiview Clustering, Scalable Semi-Supervised Learning, Structured Semi-Supervised Learning, Deep Learning with applications to Covid-19 recognition from medical imaging, face age estimation, face beauty prediction, emotion recognition, sleepiness detection, and kinship
verification.

Calls

• Call for Papers
• Call for special sessions
• Call for Project Dissemination Papers
• Call for industrial exhibition and demo papers
• Call for student session
• Call for Tutorials

Call for Papers

The 13th European Workshop on Visual Information Processing will be held on 13th - 16th October 2025, in Valletta, Malta; the first day will be dedicated to (one-day) tutorials. The workshop will bring together leading experts from academia and industry interested in visual information processing, applications and performance assessment for all types of visual modalities. The program will feature lecture, poster and plenary sessions, as well as special sessions and tutorials.

Topics of interest include, but are not limited to:

Prospective authors are invited to submit full-length papers, with a maximum of 6 pages of technical content, figures, and references, through the submission system (page 6 should contain only references). Submitted papers will undergo a double-blind review process. Accepted papers will be presented in a lecture or poster session. Regular papers presented at the conference will be included in the workshop proceedings. As for the previous EUVIP workshops, all accepted regular papers will be included in IEEE Xplore. Regular papers presented at the conference will be included in the workshop proceedings. As for the previous EUVIP workshops, all accepted regular papers will be included in IEEE Xplore. EUVIP 2025 will recognize outstanding contributions with the Best Paper Award, for the most distinguished regular paper, as well as the Best Student Paper Award and the Student poster/demo Award.

Objective

Following the success of previous editions, the EUVIP 2025 Project Dissemination Session is an opportunity for project leaders and/or partners to present their project objectives and achievements and interact with colleagues from academia and industry, working in similar or complementary research areas, thus contributing to the dissemination outcomes of the project and the sharing of good practices and achievements.

Submission of Project Paper and Assessment Criteria

Potential authors are invited to submit a two-page project paper by 30th July, 2025, following the same EUVIP 2025 template for full papers provided here. Accepted project papers will be included in the conference booklet.The selection of project papers will be based on the following criteria:Relevance of the project topic to the EUVIP 2025 themes.
Novelty of the project technical objectives.
Excellence of the project results already achieved.
Editorial quality of the project paper.

Submission Instructions

Project papers should be submitted by e-mail to the Project Dissemination Chair:

Proponents of Project Papers will be informed of the decisions by the Project Dissemination Chairs by email.Authors of regular papers, successfully submitted and approved in the EUVIP 2025 double-blind peer review process, may be invited to present their work in the Project Dissemination Session, notably if the paper contains the description of work developed in a project, according to the criteria and objectives of this Session.

The EUVIP 2025 committee is hereby releasing a call for:Demonstrations of recent research outputs or innovations related to the topics covered by the conference, and
Exhibitions of new equipment or technology related to the topics covered by the conference.

The objective is that the demo and exhibition session will provide a lively forum for researchers in both industry and academia to present their work and to foster stimulating discussions and constructive feedback from leading experts in the field.

Submission Instructions

For the exhibitions, we ask the interested participants to submit a short description of their proposed exhibition – maximum 1 page, in PDF format. The exhibition could be, for example, showing new research equipment related to the topics covered by the conference, new tools or software that could be relevant to the conference attendees, etc.For the demos, we ask the interested participants to submit a 1-2 page description (also in PDF) of their proposed demonstration. The description should include the following:

The demo could be, for example, an implemented algorithm of a new technology (related to the topics in the conference) that can run on a computer and generate visible output, or videos showing recent research outputs, etc. Note that the demos can relate to previously published work, or to ongoing research that the authors have the right to disclose publicly.For both the exhibition and demo proposals, these will be judged for acceptance based on:

At the conference, before the start of the Demo & Exhibition session, we will ask one representative for each of the accepted exhibitions and demos to present a 1-minute “advertisement” (with 1 PowerPoint or PDF slide) to the audience, to encourage them to come and see the demo/exhibition.

Publication

Demo proposals will not appear in the EUVIP 2025 proceedings published in IEEE Xplore. However, they will appear online in the proceedings of the Demo Session on the website of the EUVIP 2025 workshop.Please note that at least one person needs to register to EUVIP 2025 for presenting the demo/exhibition. Registration of a regular paper will also cover presenting a demonstration if the authors wish to do so. In this case, we would ask the authors to also submit a demo proposal as described in the Submission Instructions above.

Important Dates

Deadline for Industrial Exhibition and Demo Paper Proposals: 30th July 2025.

Submission

Submissions (and any questions related to the industrial exhibitions and demos) should be emailed to the exhibition and demo session chairs using the following contact details:

Awards

There will be a prize offered for the Best Demo at the conference award ceremony.

Objective

The EUVIP 2025 Organizing Committee invites proposals for Special Sessions on new or emerging topics in visual information processing. Special Sessions supplement the regular program and are intended to highlight important research directions in a field of special interest to EUVIP participants. As such, topics not previously covered in regular EUVIP sessions of the past and which have the potential for a major impact on the field in the near future are of particular interest.

Required Proposal Information

Special Session proposals must contain the following information:

Evaluation Criteria

Proposals will be evaluated based on:

Contributed Papers

Upon acceptance of the Special Session proposal, contributed papers will be submitted just like regular papers and will undergo a review process similar to that of regular papers submitted to EUVIP 2025. At most one paper in the Special Session may be authored by the organizers.All Special Sessions will also be open for submissions by other interested authors until 15th June, 2025. With this approach, an even more interesting Special Session will hopefully be achieved.

Submission Instructions

Special Session proposals should be submitted by e-mail to the Special Sessions Chairs:

Proponents of Special Sessions will be informed of the decisions by the Special Sessions Chairs by email.Further questions regarding Special Sessions may be directed to the Special Sessions Chairs.

Important Dates

Deadline for Special Session Proposals: 21st May 1st June 2025.Notification of Special Session Acceptance: 27th May 10th June 2025.

Objective

The EUVIP 2025 organizing committee invites proposals for tutorials on established or emerging topics of interest for the visual information processing community. Half-day (about 3 hours each) tutorials on areas related to the conference topics are welcome. Tutorial sessions will be held on 13th October 2025.An EUVIP tutorial should aim to give a comprehensive overview of a specific topic related to Visual Information Processing. A good tutorial should be educational rather than just a cursory survey of techniques. The topic should be of sufficient relevance and importance to attract significant interest from the EUVIP community. Typical tutorial audiences consist of graduate students studying visual information processing, but also include researchers and practitioners from both academia and industry.

Required Proposal Information

Each proposal shall include the following information:

Evaluation Criteria

Proposals will be reviewed by the Tutorial Committee using the following criteria:

Submission Instructions

Prospective tutorial proposers are welcome to submit their proposals to the Tutorials Chairs, who would be happy to also answer questions and provide preliminary feedback:

Important Dates

Deadline for Tutorial Proposals: 21st May, 2025.Notification of Tutorial Acceptance: 27th May, 2025.

EUVIP 2025 invites students to contribute to EUVIP 2025 Student Poster/Demo Session!The EUVIP 2025 student poster poster session aims at promoting interactions and exchanges between early-stage researchers, providing them with the opportunity to integrate in an international conference.To participate students are encouraged to submit a two-pages extended abstract presenting their research, results and scientific perspectives. All submissions must be in English, and use the IEEE one-column format. The template can be downloaded from the following link: here.We strongly encourage students to submit a demo to accompany the poster (this is not compulsory but may give the poster more credit).The submission of an extended abstract implies the intention of the student to register to EUVIP 2025 and present their work in the student poster session.All contributions will be peer-reviewed, and evaluated according to their scientific rigour, originality and their potential for future developments.

Best student poster

The best student poster and/or demo, selected by a dedicated committee, will receive an award certificate.

Important dates

Submission deadline for the Student poster session: 30th July, 2025.Notification of Acceptance for the Student poster session: 7th August, 2025.Camera ready deadline for the student poster session: 10th August, 2025.

Submission

Proposals should be submitted via this submission link.

Contacts

Further questions regarding the Student Session may be directed to the Student Session Chairs:

Important Dates

Click on a date to add it to your Google Calendar.

General Chairs

Technical Program Chairs

Plenary Chairs

Special Sessions Chairs

Tutorials Chairs

Student Session Chairs

Awards Chairs

Industry Liaison Chairs

Demos & Exhibition Session Chairs

Panel Discussion Chair

Project Dissemination Chair

Publications Chairs

Publicity Committee

Web Chair

Information for Authors

• Important Dates
• Paper Kit & Guidelines
• Paper Submission
• Project Dissemination
• Student Session
• Social Program

Paper Kit & Guidelines

Full Papers may be no longer than six (6) pages (4 minimum), including figures, tables and references. Project Dissemination Papers may be no longer than two (2) pages, including figures, tables and references. All submissions must be in A4-sized PDF. All fonts and subsets must be embedded in the PDF file. We recommend that you use the Word or LaTeX IEEE conference templates to produce your document, since they have been set up to meet the formatting guidelines required. When using these files, please double-check the paper size in your page setup to make sure you are using the A4-size paper layout. The papers that do not conform to the formatting guidelines will not be considered.

Given the double-blind review process, applicable to Full Papers only, authors should not know the names of the reviewers of their papers, and reviewers should not know the names of the authors. Please prepare your paper in a way that preserves the anonymity of the authors.

EUVIP 2025 requires each accepted paper to be presented by one of the authors in-person at the conference site according to the schedule published. One of the authors must register for the conference at one of the non-student rates offered, and must register before the deadline given for author registration. Any paper accepted into the technical program, but not presented on-site will be withdrawn from the official proceedings archived on IEEE Xplore.

By submitting a manuscript, the authors guarantee that it is not previously published or under review elsewhere in substantially similar form. Furthermore, no paper which contains significant overlap with the contributions of the submission should be submitted during the review period to either a journal or a conference. If there are papers that may appear to violate any of these conditions, then it is the authors’ responsibility to (a) cite these papers (preserving anonymity), (b) argue in the body of your paper why your paper is nontrivially different from these concurrent submissions, and (c) include anonymized versions of those papers with the submission.

Paper Submission

Full Papers

Prospective authors are invited to electronically submit their full papers in English, not exceeding six (6) pages using the format described in the author kit. Full papers must describe original and unpublished work on the topics of the Conference. The language of the Conference is English. Submit an anonymized version of the paper. Submitted papers will undergo a double-blind review process.

Submissions will be judged on suitability, originality, significance, correctness, validation, thoroughness, replicability, and clarity. Submitted papers will be blindly peer-reviewed by at least 2 experts in the field. Final versions of accepted papers must take into account reviewers comments.

Full papers may be presented orally or as posters, as determined by the Technical Program Chairs. Decisions on presentation format will be based on the nature rather than the quality of the work. EUVIP does not consider the presentation style to be any indicator of the quality of the work. There will be no distinction in the proceedings between full papers presented orally and as posters. Accepted papers will also be included in the Conference Proceedings and will be submitted for inclusion into IEEE Xplore.

Project Dissemination Papers

Project dissemination papers should be submitted using the format described here. Project dissemination papers may be no longer than two (2) pages, including figures, tables and references. Project dissemination papers will be included in the conference booklet.

Student Session

Information about the submission for student session is available here.

Special Sessions

EUVIP 2025 will organize two special sessions.

Submitted papers to these special sessions will go through the EUVIP 2025 double blind review process. And authors of accepted papers will be invited to submit extended versions of their papers to Special Issues in selected journals.

Attendees

• Registration
• Venue
• Accommodation
• Visa & Travel Information

Venue

EUVIP 2025 will be held at the University of Malta (Valletta Campus)Entrance on St Paul Street, Valletta.

Get directions to the venue here.

Visa & Travel Information

EUVIP 2025 Malta Welcome GuideWe are delighted to welcome you to Malta for EUVIP 2025. To help make your trip as smooth and enjoyable as possible, we have compiled some useful information.Visa Information
Before traveling to Malta, please ensure you have the appropriate visa or travel authorization if required. Malta is part of the Schengen Area, so visa requirements depend on your nationality and passport.For detailed visa information, requirements, and application procedures, please visit the official Malta Central Visa Unit website: https://identita.gov.mt/central-visa-unit-main-page/Important: Please check visa requirements well in advance of your travel date, as processing times may vary.Arriving at Malta International Airport (MLA)
Malta International Airport (MLA) is your arrival point. It is located approximately 10km from the capital city, Valletta.Taxis & Ride-Hailing
- Official Taxis: You can find official white taxis at the taxi stand just outside the arrivals hall. Fares to Valletta are fixed, but it's always good to confirm the price before starting your journey (approx. €17-€20).
- Ride-Hailing Apps: Services like Bolt, Uber, and eCabs are very popular, often cheaper than official taxis, and can be booked easily via their smartphone apps upon arrival.Bus Service
- This is the most budget-friendly option. The X4 express bus route takes you directly from the airport to Valletta's main bus terminal.
- Cost: A cash ticket costs €2.50.
- Journey Time: Approximately 25-30 minutes, depending on traffic.Getting Around Malta
- Public Transport (Bus): Malta has an extensive public bus network. For tourists, the Tallinja Explore Card offers unlimited travel for 7 days for €25, which is excellent value if you plan to explore the island. You can buy these cards from the airport arrivals hall or major bus terminals.
- Ferries: For a scenic and quick way to travel between Valletta, Sliema, and the Three Cities, the ferry service is highly recommended.
- Renting a Car: While renting a car offers flexibility, be aware that driving is on the left-hand side. Roads can be narrow and busy, and parking in historical areas like Valletta can be challenging.Weather in October
October in Malta is generally very pleasant. You can expect:- Average Temperature: Highs of around 25°C (77°F) and lows of 20°C (68°F) in the evening.
- Sunshine: Plenty of sunshine, with an average of 7 hours per day.
- Rainfall: It's the start of the wetter season, so occasional short rain showers are possible.
- What to Pack: Light clothing, such as t-shirts, trousers, and skirts, will be comfortable for the daytime. It's advisable to bring a light jacket or cardigan for the evenings and a small umbrella or waterproof jacket, just in case. The sea is still warm enough for swimming!Health, Safety & Emergency Information
- Safety: Malta is a very safe country with a low crime rate. However, as in any tourist destination, you should take normal precautions. Be mindful of your belongings in crowded areas and on public transport to avoid pickpocketing.
- Emergency Number: The universal emergency number for Police, Fire, and Ambulance is 112.
- Health: The main hospital is Mater Dei Hospital. For minor ailments, pharmacies (marked with a green cross) are widely available and can offer advice.
- Currency: The currency is the Euro (€). Credit and debit cards are widely accepted in most hotels, restaurants, and shops. It's always useful to have some cash on hand for smaller purchases.
- Tap Water: The tap water is safe to drink but has a high mineral content, which gives it a particular taste. Bottled water is widely available and generally preferred by visitors.---We hope this information is helpful and look forward to seeing you in Malta!

Accommodation

Important Note: When booking, participants must mention "EUVIP/University of Malta Conference" to receive these special rates.

1. Luciano Valletta Boutique Accommodation (within walking distance from conference venue)
Merchants Street, Valletta
Email: [email protected]
- Duplex double room with St John's Cathedral view @ 200E per night on bed & breakfast basis
- Standard double room with street view @ 180E per night on bed & breakfast basis
- Economy double indoor room @ 150E per night on bed & breakfast basis2. Luciano Al Porto Boutique Accommodation (within walking distance from conference venue)
St Ursula Street, Valletta
Email: [email protected]
- Double room with street view @ 200E per night on bed & breakfast basis
- Double room with Grand Harbour view @ 240E per night on bed & breakfast basis3. Plaza Regency Hotel - 3*
248 Tower Road, Sliema
Email: [email protected]
- Single inland room @ 65E per night on bed & breakfast basis
- Double inland room @ 94E per night on bed & breakfast basis
- Single seaview room @ 95E per night on bed & breakfast basis
- Double seaview room @ 114E per night on bed & breakfast basis4. The Londoner Hotel - 3* (The Strand)
The Strand, Sliema
Email: [email protected]
- Comfort room for sole use @ 165E per night on bed & breakfast basis
- Comfort room for double use @ 180E per night on bed & breakfast basis
- Deluxe seaview room for sole use @ 185E per night on bed & breakfast basis
- Deluxe seaview room for double use @ 200E per night on bed & breakfast basis5. The Londoner Hotel - 3* (St George's Bay)
St George's Bay, St Julians
Email: [email protected]
- Comfort room for sole use @ 155E per night on bed & breakfast basis
- Comfort room for double use @ 170E per night on bed & breakfast basis
- Superior room for sole use @ 165E per night on bed & breakfast basis
- Superior room for double use @ 180E per night on bed & breakfast basis6. Osborne Hotel - 3* (within walking distance from conference venue)
50 South Street, Valletta
Email: [email protected]
- Standard room for sole use @ 145E per night on bed & breakfast basis
- Standard room for double use @ 160E per night on bed & breakfast basis7. Holiday Inn Express - 3*
St George's Bay, St Julians
Email: [email protected]
- Standard room @ 150E per night on bed & breakfast basis8. La Falconeria Boutique Hotel - 4* (within walking distance from conference venue)
62 Melita Street, Valletta
Email: [email protected]
- Standard room @ 225E per night on bed & breakfast basis9. The Gomerino Boutique Hotel - 4* (within walking distance from conference venue)
St Paul Street, Valletta
Email: [email protected]
- Standard room @ 275E per night on bed & breakfast basis10. IKYK Hotel - 4*
15 Wilga Street, St Julians
Email: [email protected]
- Economy room @ 95E per night on bed & breakfast basis
- Superior room with balcony @ 105E per night on bed & breakfast basis11. Holm Boutique Hotel - 4*
Sqaq Fabri Lane, St Julians
Email: [email protected]
- Superior room @ 150E per night on bed & breakfast basis12. Marina Verdi Hotel - 4*
St George's Bay, St Julians
Email: [email protected]; [email protected]
- Standard room for sole use @ 160E per night on bed & breakfast basis
- Standard room for double use @ 180E per night on bed & breakfast basis
- Superior seaview room for sole use @ 180E per night on bed & breakfast basis
- Superior seaview room for double use @ 200E per night on bed & breakfast basis13. Hotel Verdi - 4*
113 The Strand, Gzira
Email: [email protected]; [email protected]
- Superior side seaview room for sole use @ 170E per night on bed & breakfast basis
- Superior side seaview room for double use @ 190E per night on bed & breakfast basis14. The Victoria Hotel - 4*
Gorg Borg Olivier Street, Sliema
Email: [email protected]; [email protected]
- Classic room @ 190E per night on bed & breakfast basis15. Kennedy Nova Hotel - 4*
116 The Strand, Sliema
Email: [email protected]
- Single standard room @ 102E per night on bed & breakfast basis
- Double standard room @ 120E per night on bed & breakfast basis16. Noru Hotel - 4*
Triq Elija Zammit, St Julians
Email: [email protected]
- Standard room @ 125E per night on bed & breakfast basis
- Superior room with balcony @ 140E per night on bed & breakfast basis17. Urban Valley Resort - 4*
Triq Wied Ghollieqa, San Gwann
Email: [email protected]; [email protected]
- Superior room for sole use @ 150E per night on bed & breakfast basis
- Superior room for double use @ 160E per night on bed & breakfast basis18. Waterfront Hotel - 4*
Triq ix-Xatt, Sliema
Email: [email protected]; [email protected]
- Single room @ 190E per night on bed & breakfast basis
- Double room @ 200E per night on bed & breakfast basis19. Grand Hotel Excelsior - 5* (within walking distance from conference venue)
Great Siege Road, Floriana
Email: [email protected]
- Superior inland room for sole use @ 235E per night on bed & breakfast basis
- Superior inland room for double use @ 255E per night on bed & breakfast basis
- Superior partial seaview room for sole use @ 255E per night on bed & breakfast basis
- Superior partial seaview room for double use @ 275E per night on bed & breakfast basis20. Hyatt Centric Hotel - 5*
Triq Santu Wistin, St Julians
Email: [email protected]
- Standard room for sole use @ 240E per night on bed & breakfast basis21. The Palace Hotel - 5*
High Street, Sliema
Email: [email protected]; [email protected]
- Comfort room @ 225E per night on bed & breakfast basis22. Radisson Blu Resort - 5*
St George's Bay, St Julians
Email: [email protected]; [email protected]
- Superior seaview room for sole use @ 260E per night on bed & breakfast basis
- Superior seaview room for double use @ 280E per night on bed & breakfast basis23. Marriott Hotel - 5*
Main Street, St Julians
Email: [email protected]
- Superior room with courtyard view for sole use @ 250E per night on bed & breakfast basis
- Superior room with courtyard view for double use @ 274E per night on bed & breakfast basis