جستجوی استاد راهنمای دانشگاهی

Xiaoming Liuمشاهده پروفایل

استاد

• Computer Vision
• Pattern Recognition
• Image and Video Processing
• +۴ مورد دیگر

Xiaoming Liu is the Anil K. and Nandita Jain Endowed Professor of Engineering and MSU Foundation Professor in the Department of Computer Science and Engineering at Michigan State University . Holding a Ph.D. from Carnegie Mellon University (2004), he leads cutting-edge research in computer vision and machine learning. Research Interests : Computer Vision Pattern Recognition Image and Video Processing Machine Learning Medical Image Analysis Multimedia Retrieval Recent Research Trends : Focus on 3D object detection and depth estimation Development of robust biometric recognition systems Integration of radar-camera fusion for autonomous systems Advancements in self-supervised and multimodal learning Exploration of adversarial AI security Creation of interpretable forgery detection frameworks Teaching : Spring 2013: CSE891-006 Computer Vision Seminar Fall 2012-2015: CSE803 Computer Vision Spring 2014-2017: CSE 471 Media Processing and Multimedia Contact Information : Email: liuxm@cse.msu.edu Office: EB 3137, Michigan State University Phone: +1 (517) 355-2359

Abdullah Balمشاهده پروفایل

پژوهشگر

• Data Science
• Machine Learning
• Deep Learning
• +۵ مورد دیگر

Dr. Abdullah Bal is a researcher at Georgia State University's College of Arts & Sciences, Department of Computer Science, with over 25 years of academic experience. He holds a Ph.D. in Electrical Engineering from Yildiz Technical University (2002) and has taught graduate and undergraduate courses in algorithms, machine learning, and optical pattern recognition. B.Sc., Electronics and Communication Engineering, Istanbul Technical University (1993) M.Sc., Electrical Engineering, Yildiz Technical University (1997) Ph.D., Electrical Engineering, Yildiz Technical University (2002) His research focuses on data science, machine learning, and hyperspectral imaging applications in fields ranging from forensic analysis to historical structure preservation. He has led projects funded by the U.S. Army Research Office and the Scientific and Technological Research Council of Turkey, including real-time target detection systems and digital imaging for historical structures. Recent publications demonstrate his expertise in kernel-based transforms, ensemble learning, and hyperspectral data analysis. His work spans food safety inspection, infrared target tracking, and biometric verification systems. Faculty Outstanding Research Publication Award (2006) Turkish Air Force Academy Science Competition Winner (2009) Best Paper Award at ICFCT (2016) Previously, he chaired YTU's Informatics Department (2009-2016) and participated in academic governance through the Electrical and Electronics College Executive Committee (2012-2015). You can contact him at abal@gsu.edu in room 739, 25 Park Place.

Anand Bhattadمشاهده پروفایل

استادیار

• Computer Vision
• Computer Graphics
• Generative Modeling
• +۲ مورد دیگر

Anand Bhattad is an Assistant Professor in the Department of Computer Science at Johns Hopkins University, starting Fall 2025. Previously, he held positions as a Research Assistant Professor at the Toyota Technological Institute at Chicago (TTIC) and a visiting scholar at UC Berkeley. His research focuses on the intersection of computer vision, generative modeling, and physical reasoning, aiming to develop perception-driven and physics-aware visual models. His academic journey includes a PhD in Computer Science from the University of Illinois Urbana-Champaign under David Forsyth, with mentorship from Derek Hoiem, Svetlana Lazebnik, Greg Shakhnarovich, and Shenlong Wang. Prior to his PhD, he earned dual master’s degrees in Computer Science and Civil and Environmental Engineering at UIUC and a bachelor’s in Civil Engineering from NITK Surathkal, India. Research interests center on how generative models encode physical and perceptual knowledge, with key contributions in intrinsic image emergence, projective geometry limitations, and physics-aware relighting techniques. His work bridges classical computer vision concepts with modern deep learning, producing state-of-the-art methods for 3D scene synthesis and image editing. Articles span topics like 3P Vision , diffusion models, and 360° video datasets, reflecting interdisciplinary approaches in computer graphics and computational photography. Scientific awards include Outstanding Reviewer at ICCV 2023, CVPR 2022 Best Paper Finalist, and multiple conference service roles as workshop organizer and area chair. He designed the TTIC course Past Meets Present: A Tale of Two Visions , teaching connections between historical and modern computer vision research.

• Image Processing
• Computer Vision
• Remote Sensing
• +۴ مورد دیگر

Gabriele Facciolo is a Professor at the Centre Borelli, ENS Paris-Saclay, France. He is a Senior Member of the Institut Universitaire de France (IUF) and holds an Innovation Chair (2025). His research focuses on image and video processing, remote sensing, and super-resolution techniques. Current affiliations: Centre Borelli (ENS Paris-Saclay), Institut Universitaire de France His research explores advanced algorithms for satellite stereo pipelines, real-time deblurring, denoising, and explainable AI systems for legal evidence enhancement. He coordinates projects like ANR SURECAVI (Super-resolution for visible camera systems) and ANR IMPROVED (video enhancement for judicial use), with recent work on Gaussian Splatting for Earth Observation and multi-date satellite super-resolution. Notable scientific achievements include the IGARSS 2025 Top 10 Student Paper Award and leadership in projects funded by ANR (€890k) and Prime Minister's entities (SGDSN/ANSSI). His work bridges computational imaging, defense applications, and digital forensics. Project leadership: SURECAVI, IMPROVED, BOFOR Key technologies: GPU acceleration, real-time processing, optical flow estimation, RPC refinement Gabriele actively contributes to open-source tools like S2P (Satellite Stereo Pipeline), MGM (MultiGlobal Matching), and OMNIflip. He teaches in the Master MVA program and collaborates across institutions (ENPC, UPF).

Reda Mastouriمشاهده پروفایل

استاد مدعو

• Artificial Intelligence
• Cybersecurity
• Data Science
• +۳ مورد دیگر

Reda Mastouri is an Adjunct Professor in the Department of Data Sciences within the College of Computer and Information Sciences at Saint Peter’s University. He combines academic roles with 12 years of industry experience as a Lead Cyber Security Engineer and Product Consultant, collaborating with Fortune 200 and 500 companies. His teaching includes courses such as DS-520 Data Analysis, DS-530 Big Data, and CS-332 Advanced Computing. Ph.D., AI & Data Sciences, Saint Peter’s University M.Eng., Telecommunication and Network Engineering, ENSA-M Cadi Ayyad University M.S., Data Sciences, Saint Peter’s University B.S., Computer Sciences, New Jersey Institute of Technology B.A., Applied Mathematics, Rutgers University His scholarly work focuses on AI-driven algorithms for truth demystification and cluster computing applications in high-fidelity image/video forgery detection within cybersecurity. Additional expertise spans DevSecOps, enterprise architecture, and software economics, with a dedication to innovation in business strategy and technology integration. Dr. Mastouri’s research trends emphasize heterogeneous ad hoc networks, collaborative honeypot architectures, and blockchain-based security models for IoT. His work addresses distributed attack detection, false positive/negative reduction, and protocol optimization, aligning with his specialization in cybersecurity and artificial intelligence. Certified Splunk Super User Palo Alto Networks Certified Cybersecurity Associate (PCCSA) CyberArk Certified Trustee Certified Scrum Professional SFPC Certified 10-Hr OSHA Training for the Construction Industry Certified Project Management Essentials Certified (PMEC)™ Lean Six Sigma Yellow Belt (ICYB) CPR & AED Certified AWS Certified Developer Associate Scrum Foundation Professional Certificate NSE 1 Network Security Associate NSE2 Fortinet's Network Security Expert

Kede Maمشاهده پروفایل

دانشیار

• Image Quality Assessment
• Computational Photography
• High Dynamic Range Imaging
• +۷ مورد دیگر

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.

Abhinav Dhallمشاهده پروفایل

دانشیار

• Computer Vision
• Affective Computing
• Deep Learning
• +۳ مورد دیگر

Abhinav Dhall is an Associate Professor in the Department of Data Science & AI at Monash University. His research focuses on computer vision, affective computing, and human-centered AI, with a particular emphasis on deepfake detection, multimodal analysis, and ethical AI applications. He is actively involved in organizing workshops like the Multimodal and Responsible Affective Computing (MRAC) and chairs conferences such as ACCV. Dhall accepts PhD students and has contributed significantly to datasets like AV-Deepfake1M and EmotiW challenges. His work spans topics including HDR imaging, facial expression recognition, and AI ethics in multimedia systems.

Taylor Johnsonمشاهده پروفایل

دانشیار

• Formal Verification
• Cyber-Physical Systems (CPS)
• Artificial Intelligence
• +۷ مورد دیگر

Taylor Johnson is an Associate Professor of Computer Science and Electrical and Computer Engineering at Vanderbilt University's School of Engineering. He directs the Verification and Validation for Intelligent and Trustworthy Autonomy Laboratory (VeriVITAL) and serves as a Senior Research Scientist in the Institute for Software Integrated Systems. Previously, he was an Assistant Professor at the University of Texas at Arlington from 2013 to 2016. His research focuses on formal verification techniques for cyber-physical systems (CPS), emphasizing safety, reliability, and security through hybrid systems, formal methods, and control theory. He has published extensively on neural network verification, earning best paper awards and recognition from IEEE, IFIP, and ACM. Education: Ph.D., Electrical and Computer Engineering (University of Illinois at Urbana-Champaign, 2013) M.Sc., Electrical and Computer Engineering (University of Illinois at Urbana-Champaign, 2010) B.S.E.E., Electrical and Computer Engineering (Rice University, 2008) Research Interests: Formal verification of neural networks and CPS, safety-critical systems, autonomous systems, and AI/ML security. His work bridges theoretical foundations (e.g., hybrid systems) with practical applications in aerospace, energy systems, and robotics. Key Contributions: Developed the NNV tool for neural network verification, led the Verification of Neural Networks Competition (VNN-COMP), and pioneered techniques for robust federated learning and malware detection. Awards: AFOSR YIP Award (2016), NSF CRII Award (2015), and multiple best paper honors. His research is funded by AFRL, NSF, Intel, NVIDIA, and industry partners. Labs & Collaborations: VeriVITAL Lab (Vanderbilt), collaborations with United Technologies Research Center, Boeing, and Toyota.

Christophe Charrierمشاهده پروفایل

استاد

• Digital Image Forensics
• Video Forensics
• Biometrics
• +۷ مورد دیگر

Christophe Charrier is a Full Professor in Forensics and AI at Université de Caen Normandie, affiliated with GREYC UMR CNRS 6072 and IUT Grand Ouest Normandie's Multimedia and Internet Department (Dept. MMI). He obtained his PhD in Computer Science from Université Jean Monnet (Saint-Etienne) in 1998, followed by an HDR (Habilitation à Diriger des Recherches) in 2011 from Université de Caen Normandie. His academic journey includes roles as a Postdoctoral Researcher at Université Laval (1998-2001), Associate Professor at IUT Saint-Lô (2001), and Visiting Scholar/Professor positions at University of Texas at Austin (2008) and University of Sherbrooke (2009-2011). His research focuses on Digital Image and Video Forensics (e.g., deepfake detection), Image/Video Quality Assessment , Computational Vision , and Biometrics (fingerprint quality, template update, presentation attack detection). He leads the SAFE research group since 2016 and collaborates with the E-payment & Biometrics team at GREYC. His work integrates machine learning for quality metrics, biometric system evaluation, and forensic analysis. Recent publications highlight advancements in deepfake detection , 3D mesh quality assessment , and biometric security . Articles span journals like Intelligent Service Robotics (2024), IEEE Access (2024), and conferences such as CORESA (2024) and Cyberworlds (2023-2024). His studies on fingerprint systems, behavioral biometrics, and environmental impacts on data quality underscore his interdisciplinary approach. Scientific Awards : Best PhD Paper Award (ASONAM 2022) Best Full Paper Award (CW2022) He has mentored 14 PhD students since 2003, including notable alumni like Xinwei Liu (Zhejiang Wanli University) and Antoine Cabana (ALTEN, Toulouse). His projects span biometric certification, latent space manipulation, and 3D mesh evaluation, often in collaboration with institutions in Canada, Norway, and Morocco.

Mauro Barniمشاهده پروفایل

استاد

• Multimedia Security
• Digital Forensics
• Machine Learning
• +۳ مورد دیگر

Mauro Barni serves as a Full Professor in the Department of Information Engineering and Mathematical Sciences at the University of Siena, where he teaches Cybersecurity, Information Theory, and Mathematical Statistics. His office hours are held Fridays from 3:00 PM to 5:00 PM via online appointment, reflecting his active engagement with students. Professor Barni's research spans multimedia security and digital forensics, with emphasis on deep learning applications for digital watermarking, deepfake detection, and synthetic image attribution. His work addresses critical challenges in adversarial machine learning, steganography, and image manipulation detection, contributing significantly to cybersecurity and intellectual property protection frameworks. Analysis of his 2021-2025 publications reveals dominant trends in neural network watermarking robustness, synthetic media detection, and defenses against backdoor attacks. His research consistently bridges theoretical foundations with practical implementations, focusing on real-world applications like printer source attribution and physical-domain adversarial scenarios. He leads the VIPP (Vision, Image Processing, and Pattern Recognition) research group, which maintains dedicated virtual classrooms for collaborative projects in computer vision and multimedia security. The group actively develops methodologies for image forensics, synthetic media analysis, and security countermeasures against emerging threats.

• Biometrics
• Machine Learning
• Deep Learning
• +۵ مورد دیگر

Raghavendra Ramachandra is a Professor at the Department of Information Security and Communication Technology (IIK) , within the Faculty of Information Technology and Electrical Engineering at the Norwegian University of Science and Technology (NTNU) in Gjøvik. His research focuses on biometric systems, particularly in face, fingerprint, and finger vein recognition, with emphasis on presentation attack detection, morphing attack detection, and deep learning applications. Current research projects include: SALT (2022-2026) : Developing privacy-preserving facial biometric authentication systems. OffPAD (2022-2025) : Creating cryptographic tools and presentation attack detection for fingerprint biometrics. SWAN (2015-2020) : Developing biometric countermeasures against presentation attacks. His recent publications demonstrate technical expertise in: Face morphing attack detection using vision transformers and point cloud networks Image fusion techniques for multispectral biometrics GAN-based synthetic data generation for security evaluation Explainable AI approaches for biometric verification Professor Ramachandra also supervises PhD and Master’s students, and has extensive experience in leading national and EU research initiatives.

• Computer Vision
• Machine Learning
• Image and Video Processing
• +۳ مورد دیگر

Fouad Khelifi is an Associate Professor in the Department of Computer and Information Sciences at Northumbria University. His research focuses on computer vision, machine learning, image/video processing, biometrics, multimedia forensics, and medical image analysis. He obtained his PhD in Computing Science from Queen's University Belfast (2007) and held prior research roles at the University of Bradford (2007–2009) before joining Northumbria in 2010. He supervises PhD students in cybersecurity applications and palm-vein recognition systems. Education: PhD in Computing Science, Queen's University Belfast (2004–2007) Fellow of the Higher Education Academy (FHEA, 2014) Research Interests: Khelifi’s work spans advanced deep learning techniques for medical imaging (e.g., cancer detection, retinal disease analysis), source camera identification in digital forensics, and biometric authentication systems. He develops novel algorithms for feature extraction, fusion networks, and transformer-based models in healthcare and multimedia security. Advising: Supervising Egallekanda Perera (PhD, 2019–2025): Efficient Keypoint-based Palm-vein Recognition Co-supervising Ikechukwu Ikpeama (PhD, 2024–): Cybersecurity for Industrial Control Systems Labs/Teams: Active in Northumbria’s Digital Media and Systems Research groups, contributing to interdisciplinary projects in AI-driven medical imaging and multimedia forensics.

• Digital Forensics
• Criminal Investigation
• Computer Science
• +۴ مورد دیگر

Matthew James Sorell is a Senior Lecturer at the University of Adelaide since October 2002. He holds a Doctor's Degree from George Mason University (1998), supervised by Geoff Orsak, focusing on 'Robust Importance Sampling'. His research spans Digital Forensics, Criminal Investigation, and Computer Science, with emphasis on image/video analysis, surveillance technologies, and data provenance. Education: PhD in Computer Sciences, George Mason University, 1998 Research Interests: His work focuses on digital evidence analysis, forensic science applications, and the development of methodologies for authenticating digital media. Key areas include photo-sensor fingerprinting, mobile forensics (e.g., Snapchat surveillance protocols), and health data provenance analysis (Apple Health databases). He has contributed to advancing video motion detection, smart camera systems, and forensic photography audit logs. Publications: His recent work emphasizes digital forensics in health data and social media, with notable contributions to Forensic Science International Digital Investigation and IEEE conferences. Earlier research includes biologically-inspired video enhancement and JPEG quantization analysis. Professional Roles: From 2017-2022, he worked as a Digital Investigations Consultant (part-time). He has edited conference proceedings (e.g., e-Forensics 2009) and contributed to interdisciplinary studies like food advertising patterns on Australian TV. Labs/Teams: Collaborates with teams in digital crime forensics, surveillance systems, and multimedia forensics, reflected in his conference organizing roles and journal editorships.

Peter Lambertمشاهده پروفایل

دانشیار

• multimedia signal processing
• visual communication
• computer graphics
• +۲ مورد دیگر

Peter Lambert is a full-time Associate Professor at Ghent University – imec (Belgium), affiliated with the Internet Technology and Data Science Lab (IDLab) where he coordinates the MEDIA research team since 2013. His academic background includes a Master's degree in Science (Mathematics) and Applied Informatics from Ghent University, followed by a Ph.D. in Computer Science from the same institution in 2007. Prior to his current role, he served as a Technology Developer at Ghent University (2010-2013). Lambert's research focuses on: Multimedia signal processing and visual communication systems Computer graphics and computational geometry Augmented and virtual reality (AR/VR) technologies Video compression and perceptual quality assessment Multimedia security and digital watermarking His recent publications (2024-2025) demonstrate strong emphasis on real-time multimedia systems, VR/AR applications, perceptual quality metrics, and multimedia security. Research trends include deep learning-based video forensics, light field rendering optimizations, perceptual hashing techniques, and adaptive video streaming solutions. As leader of the IDLab-MEDIA team, Lambert oversees research on emerging visual media formats with applications in immersive experiences. The team develops technologies like OpenDIBR (real-time light field renderer) and maintains datasets such as SILVR (Synthetic Immersive Large-Volume Plenoptic Dataset).

Emmanuel Giguetمشاهده پروفایل

پژوهشگر

• Computer Science
• Computer Forensics
• Natural Language Processing
• +۴ مورد دیگر

Emmanuel Giguet is a Researcher at the French National Centre for Scientific Research (CNRS), affiliated with the GREYC Laboratory (Computer Science Department) at the University of Caen, Normandy, France. He holds an HDR (Accreditation to Supervise Research) from the University of Caen (2011) and a PhD in Computer Science (1998), both focusing on multilingual natural language processing and document analysis. Roles: Cybersecurity Researcher, Communication and Scientific Mediation Adviser (GREYC Lab), Former Computer Forensics Legal Expert (2005–2015). Expertise: Digital Forensics, Natural Language Processing, Document Structure Analysis, Open Source Intelligence, Competitive Intelligence. His research spans cybersecurity, digital forensics, and NLP applications in document analysis. He co-founded Semiotime (2012), a Competitive Intelligence startup, and has contributed to tools like the GREYC Digital Investigation Platform (G'DIP). He teaches cybersecurity modules at the University of Caen, emphasizing digital forensics and information retrieval. Key Projects: Development of open-source digital investigation tools (e.g., G'DIP). Analysis of deepfake videos and forensic video forgery detection. PDF document structure extraction for financial narrative processing (FinTOC). Affiliations: GREYC Lab (CNRS UMR 6072), University of Caen. Institute for Information Sciences, University of Caen. Communication: Advises GREYC on branding and media presence, including logo guidelines, virtual backgrounds, and scientific mediation resources.