Documents

Information Conference Details Technical Program Program Committee Event Chairs Keynote Lectures Best Paper Awards Satellite Events Workshops Special Sessions Tutorials Demos Panels Partners Academic Partners Industrial Partners Institutional Partners Media Partners Partner Events Publication Partners Previous Conferences Abstracts Awards

Keynote Lectures

Observing People
Modesto Castrillón-Santana, Universidad de Las Palmas de Gran Canaria (ULPGC), Spain

Beyond the Fixed Gaze: Active Vision in the Age of UAVs
Gian Luca Foresti, Unversity of Udine, Italy

Face Recognition: Past, Present and Future
Massimo Tistarelli, Università degli Studi di Sassari, Italy

Observing People

Modesto Castrillón-Santana
Universidad de Las Palmas de Gran Canaria (ULPGC), Spain

Short Bio
Modesto Castrillón-Santana is a full professor at the University of Las Palmas de Gran Canaria. He obtained his PhD with the thesis entitled "On Real-Time Face Detection in Video Streams: An Opportunistic Approach". His research activities began in the 90s with a focus on the automatic facial analysis problem. Since then, he has also explored various topics in computer vision, perceptual interaction, human-machine interaction, biometrics, and computer graphics. Modesto has collaborated as a co-author on several papers in JCR indexed journals, book chapters, and national and international conferences. He has participated in various research projects and contracts, and is an active reviewer for different high-quality JCR journals and conference program committees. Currently, Modesto serves as an Associate Editor for Pattern Recognition Letters and Image and Vision Computing, and has previously served as an Associate Editor for the IEEE Biometrics Council Newsletter and a Guest Editor for different journals. He is a member of the AEPIA and AERFAI (Spanish Association for Pattern Recognition and Image Analysis).

Abstract
Observing people is a core problem in computer vision and artificial intelligence, with applications covering from human–computer interaction to intelligent surveillance systems. Research in this area has progressively moved from the analysis of facial appearance in controlled conditions to the study of human attributes and behavior in unconstrained, real-world scenarios. This keynote presents a perspective on visual analysis of people in images and video, covering topics such as facial description, gender classification, soft biometric attributes, and the use of holistic and part-based representations. Recent advances in zero-shot and multimodal approaches for pedestrian attribute recognition are also discussed, particularly in the context of in-the-wild data. The talk highlights the challenges posed by variability, bias, limited annotations, and privacy, and outlines open research directions toward more robust and human-centered visual intelligence systems.

Beyond the Fixed Gaze: Active Vision in the Age of UAVs

Gian Luca Foresti
Unversity of Udine, Italy

Short Bio
Prof. Gian Luca Foresti Full Professor in Computer Science, University of Udine, Italy

Abstract
Traditional surveillance and monitoring systems have long relied on fixed cameras — stationary sensors whose field of view is determined once and for all at installation time. While effective in controlled scenarios, such systems are inherently limited in their ability to adapt to dynamic environments, moving targets, or unpredictable events. Active vision offers a conceptual and practical shift: rather than passively recording what falls within a given environment, the imaging system actively controls its own viewpoint to maximize the information gathered. This talk explores the transition from classical active vision — as studied in the context of pan-tilt-zoom cameras and multi-camera networks — to its modern incarnation aboard Unmanned Aerial Vehicles. UAVs introduce a fundamentally new degree of freedom: the entire platform can move, hover, and reorient in three-dimensional space, turning the camera into a fully mobile agent. We discuss how this shift redefines core problems such as target detection and tracking, gaze control, sensor fusion, and situational awareness. The talk concludes by outlining open research directions, including multi-UAV coordination, onboard processing under resource constraints, and the integration of event-based and infrared sensors for robust all-condition perception.

Face Recognition: Past, Present and Future

Massimo Tistarelli
Università degli Studi di Sassari, Italy

Short Bio
Massimo Tistarelli received the Phd in Computer Science and Robotics in 1991 from the University of Genoa. He is Full Professor in Computer Science (with tenure) and director of the Computer Vision Laboratory at the University of Sassari, Italy. Since 1986 he has been involved as project coordinator and task manager in several projects on computer vision and biometrics funded by the European Community. Since 1994 he has been the director of the Computer Vision Laboratory at the Department of Communication, Computer and Systems Science of the University of Genoa, and now at the University of Sassari, leading several National and European projects on computer vision applications and image-based biometrics. Prof. Tistarelli is a founding member of the Biosecure Foundation, which includes all major European research centers working in biometrics. His main research interests cover biological and artificial vision (particularly in the area of recognition, three-dimensional reconstruction and dynamic scene analysis), pattern recognition, biometrics, visual sensors, robotic navigation and visuo-motor coordination. He is one of the world-recognized leading researchers in the area of biometrics, especially in the field of face recognition and multimodal fusion. He is coauthor of about 200 scientific papers in peer reviewed books, conferences and international journals. Prof. Tistarelli organized and chaired several world-recognized several scientific events and conferences in the area of Computer Vision and Biometrics. He has been associate editor for several scientific journals. Since 2003 he is the founding director for the Int.l Summer School on Biometrics. He served as vice president of the IEEE Biometrics Council, first vice president of the IAPR and chair of the IAPR Fellow committee. He is a Fellow member of the IAPR and Senior member of the IEEE. In 2022 he was awarded the IEEE Biometrics Council Meritorious Service Award.

Abstract
Face recognition is possibly one of the most successful applications of Computer Vision and AI. Machine Learning, and more specifically Deep Learning, allows now to deploy face recognition in several domains, ranging from automated border control to mobile device authentication. Even though the progress in computing power and Machine Learning facilitated the implementation of fast and efficient systems, there are still several issues which remain unsolved. On the other hand, the basic "face recognition pipeline", conceived 30 years ago, still remains unaltered. As such, we need to learn from the past and address some research questions which are still unanswered. Among them: 1. If face recognition is a "solved" problem, why are we still doing research on this topic? 2. What are the drawbacks and limitations of current deep learning models? How far can we go by exploiting increasing amounts of face data? 3. Is the human visual system still the best comparative face recognition model? If so, what can we learn from the way humans recognize faces? 4. How can we build "ethical" systems which properly address current privacy concerns? In this talk we'll address these questions, trying to envisage a path forward with the aim of driving our research curiosity towards the design of tomorrow's Intelligent Machines.