Find Academic Supervisors

Kede Ma is an Associate Professor in the Department of Computer Science at City University of Hong Kong (CityUHK). He received his B.E. from the University of Science and Technology of China (USTC) in 2012, and MASc and Ph.D. degrees from the University of Waterloo in 2014 and 2017, respectively. From 2018 to 2019, he was a Research Associate with the Howard Hughes Medical Institute and New York University. Prof. Ma has been named to the Highly Cited Researchers list by Clarivate Analytics in 2024 and currently serves on the editorial boards of IEEE Transactions on Image Processing, IEEE Transactions on Information Forensics and Security, and IEEE Signal Processing Letters. Prof. Ma leads the Multimedia Analytics (MA) Laboratory, an interdisciplinary research group focused on computational vision, computational modeling of human visual perception, perceptual multimedia signal processing, quality assessment, and multimedia forensics. His research spans computational photography, high dynamic range imaging and rendering, omnidirectional video analysis, camera processing pipeline design, and artificial intelligence safety in multimedia systems. His work integrates machine learning techniques including reinforcement learning, generative modeling, self-supervised learning, and continual learning for multimedia signal processing applications. His recent publications demonstrate a strong focus on image quality assessment, deep learning for multimedia processing, and multimedia forensics. His work bridges theoretical computer vision principles with practical applications in multimedia systems. The research trends show increasing integration of foundation models with specialized multimedia processing tasks, particularly in quality assessment and security applications. Highly Cited Researchers list by Clarivate Analytics (2024) Best Paper Award at IEEE International Conference on Virtual Reality and Visualization (2021) Best Paper Runner-Up at International Joint Conference on Artificial Intelligence Workshop (2021) Top 10% Award at IEEE International Conference on Image Processing (2015) Finalist for the Governor General's Gold Medal, University of Waterloo (2017) Spotlight presentation at NeurIPS (2022) Highlight paper at ICCV (2025) Oral presentation at ICLR (2025) Prof. Ma advises numerous PhD students and postdoctoral fellows in the MA Laboratory. His research is supported by various grants enabling work in multimedia analytics, image processing, and computer vision. The laboratory maintains active collaborations with researchers at institutions including SUSTech, ZJU, and HIT. Current projects focus on advancing image quality assessment methodologies, developing more robust deep learning techniques for multimedia forensics, and exploring new approaches to HDR imaging and omnidirectional video processing. The Multimedia Analytics Laboratory maintains a strong focus on both theoretical foundations and practical applications of multimedia processing. Current research directions include integrating large language models with image quality assessment, developing more robust deepfake detection methods, and advancing techniques for continual learning in multimedia applications. The lab emphasizes rigorous evaluation methodologies and maintains multiple datasets for multimedia quality assessment research.

• Image Quality Assessment
• Computational Photography
• High Dynamic Range Imaging
• +7 more

Luisa Verdoliva is an Associate Professor at the Department of Industrial Engineering, University Federico II of Naples, Italy. She holds a Hans Fischer Senior Fellowship at the Technical University of Munich (TUM) Institute for Advanced Study (2020–present), hosted by Prof. Matthias Nießner. Her research focuses on multimedia forensics, deepfake detection, and generative AI analysis. She has been a visiting professor at Friedrich-Alexander-University (FAU) and a visiting scientist at Google AI's Perception team. Her research interests include image/video forgery detection, GAN fingerprints, biometrics liveness detection, and remote sensing applications. Verdoliva’s work has been funded by DARPA, Google, and the Italian Ministry of Research. She serves as Chair of the IEEE Signal Processing Society’s Information Forensics and Security Technical Committee and is an IEEE Fellow (2021). Key achievements include pioneering FaceForensics++ (a benchmark dataset for manipulated facial images), winning the IEEE Signal Processing Cup (2018), and receiving the Google Faculty Research Award (2018). Her awards span best paper recognitions at CVPR, ICIP, and ICIAP conferences. As part of TUM’s Visual Computing Focus Group, her fellowship research advances digital twin technology for built environments and AI-driven media forensics. Collaborations span academia and industry, with impactful contributions to combating synthetic media misuse and improving multimedia trustworthiness.

• Image and Video Forgery Detection
• Deepfake Video Detection
• GAN Fingerprints Attribution
• +5 more

Huili Chen is an Assistant Professor in the Department of Electrical and Computer Engineering at the University of California San Diego's Jacobs School of Engineering. Her research spans the intersection of hardware security, deep learning, and human-robot interaction, with a particular focus on intellectual property protection for AI systems and socially interactive robotics for education and family settings. Her research interests focus on hardware-software co-design for secure and robust deep learning systems, with specific expertise in neural network watermarking, hardware Trojan detection, and privacy-preserving AI. She has made significant contributions to federated learning security, developing frameworks like GALU for logic unlocking and AdaTest for hardware Trojan detection. In human-robot interaction, she investigates long-term multi-person interactions, particularly in home environments with children and parents, exploring how robots can enhance engagement and learning through adaptive role-playing. Her publication trends reveal a dual research trajectory: one branch focused on deep learning security and hardware co-design (accounting for approximately 60% of her recent work), and another dedicated to socially assistive robotics and human-robot interaction (40%). The security research often involves innovative approaches combining reinforcement learning with hardware constraints, while her HRI work emphasizes longitudinal studies of robot-child-parent dynamics in naturalistic settings. Dr. Chen actively collaborates with leading researchers including Farinaz Koushanfar at UC San Diego and Cynthia Breazeal at MIT Media Lab. Her work has been published in top-tier venues including IEEE Transactions on Affective Computing, ACM Transactions on Embedded Computing Systems, International Conference on Computer Vision (ICCV), and the ACM/IEEE International Conference on Human-Robot Interaction (HRI). She is a key contributor to the DAMI-P2C project, which has developed datasets and models for analyzing parent-child multimodal interactions, and leads research on hardware security frameworks for deep neural networks. Her laboratory combines expertise in computer architecture, machine learning, and social robotics to develop systems that are both technically secure and socially effective.

• Hardware-Software Co-design
• Deep Learning Security
• Intellectual Property Protection
• +5 more

Patrizio Campisi is an academic affiliated with Roma Tre University in Rome, Italy. His primary research focuses on biometric systems, information forensics, and signal processing. He has published extensively in top-tier journals and conferences, including IEEE Transactions on Information Forensics and Security, IEEE Signal Processing Magazine, and EUSIPCO. His work spans areas such as vein recognition, EEG-based biometrics, and cryptographic methods for privacy preservation. He has collaborated with numerous researchers globally and contributed to standards for biometric authentication in the EU. Research Interests: Biometric systems (finger/hand vein, EEG, keystroke dynamics) Secure template protection mechanisms Forensic analysis of digital media Machine learning applications in pattern recognition Medical imaging and wearable devices Recent work emphasizes developing explainable AI for biometric systems and creating secure, unlinkable authentication methods. He has also contributed to policy initiatives like the European Association for Biometrics' position paper on Schengen travel security.

• Biometrics
• Image Processing
• Signal Processing
• +4 more