keynote speakers
One of the highlights of the upcoming ICT conference is the lineup of esteemed keynote speakers who will be sharing their insights and experiences on the latest trends and developments in the field. These experts are at the forefront of their respective areas, and their presentations will provide attendees with valuable information and inspiration. Among the keynote speakers at the conference, you can expect to hear from:
Carlos R. del Blanco
Universidad Politécnica de Madrid
Carlos R. del Blanco
PhD in Telecommunications Engineering, Universidad Politécnica de Madrid
ABSTRACT
Visual Foundation Models (VFMs) are large-scale models trained on vast image and video datasets to learn general-purpose visual representations that can be transferred across many downstream tasks. By leveraging self-supervised, contrastive, and multimodal learning strategies, these models capture rich semantic, spatial, and contextual information without requiring extensive task-specific annotation. VFMs have significantly advanced areas such as image classification, object detection, segmentation, retrieval, and action recognition, while also enabling stronger integration between vision and language. Their adaptability, scalability, and ability to generalize across domains make them a key building block for modern computer vision systems and multimodal artificial intelligence.
BIOGRAPHY
Dr. Carlos R. del Blanco (ORCID: 0000-0003-0618-3488) received the Telecommunication Engineering degree and the Ph.D. degree in Telecommunication, both from the UPM, in 2005 and 2011, respectively. Since 2005 he is a member of the GTI- UPM. In addition, since 2021 he is a member of the faculty of the E.T.S. Ingenieros de Telecomunicación as Associate Professor of Signal Theory and Communications at the Department of Signals, Systems, and Communications. He is co-author of numerous articles in relevant international journals, peer-reviewed international conferences and journals, and holds three patents. He has participated in the creation of several open access datasets. He is co-author of the IEEE International Award for the Best Paper of the Year in the Transactions on Consumer Electronics Journal, 2017 and co-winner of the 2018 ImageCLEFlifelog Challenge: Lifelog Moment Retrieval (LMRT), organized by ImageCLEF / LifeCLEF – Multimedia Retrieval in CLEF. He has participated in 20+ European and Spanish research projects financed in competitive public calls. He has been IP of public and private R&D projects. He has also been the scientific technical coordinator of several competitive projects. Also, he has participated in several international and national contract-research projects. His professional interests include artificial intelligence and machine learning, signal and image processing, computer vision, pattern recognition, and stochastic dynamic models.
TOPIC: Visual Foundation Models and Applications
