جست‌وجوی استاد و پژوهشگر

• Databases
• Data Modeling
• Software Security
• +۳ مورد دیگر

Roger Midtstraum is a Professor at the Department of Computer Science , Norwegian University of Science and Technology (NTNU), and currently serves as the Vice Dean for Education at the Faculty of Information Technology and Electrical Engineering. He previously held leadership roles including Dean of Engineering Education (2013-2017), Chairman of UHR-MNT (2016-2018), and Chairman of NRT (2013-2016). His career spans academia and technical innovation, with affiliations across institutions like Universitetet i Nordland, Tapir Akademisk Forlag, and ACM Publications. Research interests include software security , digital rights management (DRM) , multimedia systems , and data modeling . His work explores tamper protection in online clients, anti-cheating mechanisms in gaming, secure dissemination of temporal media, and metadata-driven search methodologies (e.g., the SESAM framework). Publications reflect interdisciplinary applications in supply chain management , mobile services , and image processing , with trends toward integrating security , QoS , and semantic networks . Notable collaborations include co-authors Gisle Grimen , Christian Mönch , and Alf Inge Wang . Teaching includes courses like TDT4145 - Data Modelling, Databases and Database Management Systems . He emphasizes curriculum innovation , as seen in his 2012 Textbook: IT Grunnkurs , and leadership in educational policy through roles in national councils (UHR-MNT, NRT).

Shiqi Wangمشاهده پروفایل

دانشیار

• Semantic and Visual Communication
• AI Generated Content Management
• Information Forensics and Security
• +۳ مورد دیگر

Shiqi Wang is an Associate Professor in the Department of Computer Science at City University of Hong Kong. He holds a Ph.D. from Peking University (2014) and a B.Sc. from Harbin Institute of Technology (2008). His career includes postdoctoral and research roles at the University of Waterloo, Nanyang Technological University, and Microsoft Research Asia. He specializes in semantic/visual communication, AI content management, and image/video quality assessment. Education: Ph.D. in Computer Application Technology (2014), Peking University B.Sc. in Computer Science and Technology (2008), Harbin Institute of Technology Research focuses on Large Visual-Language Models (LVLMs) , Generative Face Video Coding , and Information Forensics . Recent work includes video coding innovations, AI-driven quality assessment, and bias mitigation in facial analysis. Awards include the IEEE Multimedia Rising Star Award (2021) , NSFC Excellent Young Scientist Fund (2020) , and multiple best paper awards at IEEE conferences. He serves as Associate Editor for IEEE Transactions on Image Processing and leads MPEG standardization efforts for generative video coding. Professional activities include TPC roles at ICML, CVPR, and ACM Multimedia. His lab actively collaborates on standards for generative AI and multimedia systems, with a focus on ethical AI and cross-domain applications.

Bogdan Vrusiasمشاهده پروفایل

استاد مهمان

• Generative AI
• Large Language Models
• Foundation Models
• +۶ مورد دیگر

Bogdan Vrusias is a Visiting Professor at the University of Surrey's School of Computer Science and Electronic Engineering (part-time). He concurrently serves as Global Head of AI and Data Engineering at The Economist. His academic journey began at Surrey as an undergraduate (BSc Computing and Information Technology, 1998), followed by a PhD in multi-modal information retrieval (2004) and an MBA (2010). He is a Fellow of the Higher Education Academy (FHEA). Education: PhD, University of Surrey (2004) MBA, University of Surrey (2010) BSc Computing and Information Technology, University of Surrey (1998) His research spans Generative AI, Large Language Models, Foundation Models, Machine Learning, Deep Learning, Cloud Computing, Natural Language Processing, and Computer Vision . His work focuses on developing scalable AI architectures and semantic technologies for real-world applications. Publications consistently explore semantic systems, neural networks, and multimodal information retrieval . Recent articles emphasize video annotation frameworks and P2P network architectures, while earlier work established foundations in self-organizing maps and feature selection for high-dimensional data. Awards: FHEA (Fellow of the Higher Education Academy) He previously directed UG/PG programs at Surrey and created pioneering courses like Web Hacking Countermeasures. His industry leadership includes founding tech startups and heading Amazon Web Services' AI/ML Specialist Solutions Architects team for EMEA. At The Economist, he drives AI and data transformation.

Marco Bertiniمشاهده پروفایل

دانشیار

• Computer Vision
• Multimedia
• Pattern Recognition
• +۴ مورد دیگر

Marco Bertini is an Associate Professor at the Department of Information Engineering, University of Florence, where he teaches in the School of Engineering. He is affiliated with the Media Integration and Communication Center (MICC) and is a member of GIRPR (Group for Image Recognition and Pattern Recognition). His research focuses on computer vision, multimedia, and pattern recognition with applications in video analysis and semantic processing. Laurea Degree in Electronics Engineering from University of Florence (1999) Ph.D. (2004) Dr. Bertini's research spans automatic video analysis, annotation, semantic transcoding, and social media analysis. He has led multiple EU-funded research projects including ASSAVID, DELOS Network of Excellence, VIDI-Video, IM3I, ORUSSI, and euTV. His current work focuses on smart museums and smart cities funded by the Italian Ministry of University, Instruction and Research, along with semantic video coding applications. As an active contributor to the academic community, he serves as Associate Editor for IEEE Transactions on Multimedia and has organized major conferences including European Conference on Computer Vision 2012 and ACM Multimedia 2010. He has also guest-edited special issues for Multimedia Tools and Applications journal. Associate Editor, IEEE Transactions on Multimedia Organizer, European Conference on Computer Vision 2012 Organizer, ACM Multimedia 2010 Guest Editor, Multimedia Tools and Applications Special Issue Dr. Bertini teaches undergraduate and graduate courses including Programming (OOP, C++, design patterns), Parallel Computing, and GPU Programming. He has previously taught Unix Fundamentals, CISCO CCNA, Multimedia Databases, and Information Technologies Laboratory. His research is conducted primarily at the Media Integration and Communication Center (MICC), where he collaborates with industry partners including SELEX ES on Terrestrial Trunked Radio video communication systems.

Andrea Pratiمشاهده پروفایل

استاد

• Computer Vision
• Pattern Recognition
• Video Surveillance
• +۱۲ مورد دیگر

Andrea Prati is a Full Professor in the Department of Engineering and Architecture at the University of Parma, Italy. He has previously served as an Assistant Professor at the University of Modena and Reggio Emilia and as an Associate Professor at the University IUAV of Venice. His research spans computer vision, pattern recognition, video surveillance, machine learning, and sensor networks, with applications in smart cities, traffic systems, healthcare, and industrial automation. His research interests include: Computer Vision and Pattern Recognition for creative industries (e.g., apparel analysis with Adidas) Distributed and embedded sensor networks for mobile vision Motion analysis and object tracking in multi-camera environments Semantic video transcoding and annotation Abnormal behavior detection for security and terrorism prevention Performance optimization in multimedia architectures The recent publications highlight a strong focus on trajectory modeling, anomaly detection, and multi-camera surveillance systems. Themes such as spectral graph analysis, statistical modeling of motion, and robust outdoor surveillance illustrate a consistent trajectory in advancing intelligent video analytics. His work bridges theoretical innovation with real-world applications in public safety, transportation, and ambient intelligence. Scientific honors include: IAPR Fellowship (2014) for contributions to video surveillance algorithms He has served as Program Chair and General Chair for major international conferences such as ICDSC, ICIAP, and VNBA. He is actively involved in research leadership, including editorial roles for IEEE TCSVT, Elsevier's CVIU, and MDPI Applied Sciences. He leads and collaborates on numerous research projects funded regionally (Emilia-Romagna), nationally (PRIN), European (DELOS, THIS), and internationally (NATO Science for Peace). He also co-developed a patented solution with Marchesini Group SpA. His research group, IMPLab, drives innovation in intelligent systems. He teaches courses in computer architecture, algorithms, AI, and machine learning across undergraduate and graduate programs in engineering and data science.

Yung-Lyul Leeمشاهده پروفایل

استاد

• Video Coding Standard
• 360 Video Coding
• Image Processing
• +۳ مورد دیگر

Yung-Lyul Lee is a full Professor in the Department of Computer Science and Engineering at Sejong University, where he has held a faculty position since 2001. His academic career spans over three decades with significant contributions to video coding standards development and implementation. His educational background includes: Ph.D. in Computer Science from KAIST (1992) M.S. in Computer Science from Sogang University (1988) B.S. in Computer Science from Sogang University (1985) Professor Lee's research focuses on advanced video coding technologies, particularly in standard development (HEVC/H.265, VVC), 360° video processing, and CNN-integrated compression systems. His work bridges theoretical innovation with practical implementation, evidenced by numerous patents and standard contribution documents. Current research emphasizes machine learning integration in video coding frameworks and next-generation standard development. Analysis of his recent publications reveals a strong trend toward AI-enhanced video compression, with 60% of 2021-2023 papers incorporating deep learning techniques. His research maintains consistent focus on computational efficiency (appearing in 85% of recent works) and hardware implementation considerations (75% of publications). Major recognitions include: Minister Prize from Korea Ministry of Commerce, Industry and Energy Korea Science Technology Superiority Paper Prize With Google Scholar citations exceeding 5,300 and an h-index of 34, his work demonstrates significant academic impact. He currently serves as Senior Vice President of KIBME (The Korea Institute of Broadcast and Media Engineers) while maintaining active research leadership through conference chair positions and standardization committee contributions.