Find Academic Supervisors

• Pattern Recognition
• Document Analysis
• Machine Learning
• +5 more

Nicolas Ragot is an Associate Professor at the Computer Science Department of the Polytechnic School of the University of Tours (EPU) , affiliated with the LIFAT (Fundamental and Applied Computer Science Laboratory of Tours) . He has been active in Pattern Recognition , Document Analysis , and Biometrics since his 2003 Ph.D. from IRISA lab, Rennes University. Current research focuses on deep learning for document layout generation , time series forecasting , and robust OCR systems Involved in international collaborations with Indian Statistical Institute-Kolkata , BnF (French National Library) , and LITIS Rouen Lead or participated in projects like IFCPAR , ANR Digidoc , Google Digital Humanities Awards , and Technovision EPEIRES His work spans: Document Analysis : OCR quality assessment, historical document digitization, and layout generation Biometrics : Online/offline signature verification and handwritten character recognition Machine Learning : One-class classification, incremental learning, and hybrid neural network architectures Scientific contributions include: Google Digital Humanities Award (2-year grant for digitization projects) Reviewer for top journals ( IEEE PAMI , Pattern Recognition ) and conferences ( ICPR , ICDAR ) Supervisor of RFAI group (since 2017) and extensive administrative involvement at Polytech Tours Key collaborations and networks: Academic: Indian Statistical Institute , LITIS Rouen , French National Library Industrial: ATOS Worldline , Nexter Research Networks: IFCPAR , ANR projects

• Complex systems
• Data analysis
• Statistical analysis
• +7 more

Anna Filomena Carbone is a Full Professor in the Department of Applied Science and Technology (DISAT) at the Polytechnic University of Turin, where she directs the NOISELAB research laboratory. Her academic career spans over three decades since earning her PhD in Physics in 1993, with significant contributions to interdisciplinary research at the intersection of physics, data science, and complex systems. Her research interests encompass complex systems, data analysis, statistical analysis, modeling and simulation, and time series analysis, with a particular focus on noise in physical systems. Dr. Carbone has authored over 100 articles in international journals and conference proceedings, with recent publications (2023-2025) demonstrating continued productivity in areas including financial time series analysis, urban scaling laws, quantum information, and brainwave dynamics. Her work shows a clear trend toward increasingly interdisciplinary applications of statistical physics methods to real-world complex systems across multiple domains. Member of the Board of the Nonlinear and Statistical Physics (NSP Board) of the European Physical Society (EPS) since 2009 Member of Scientific Committee - European Physical Society, Belgium (2009-2015) Editorial board member for multiple journals including Physica A, European Physical Journal B, and Chaos, Solitons and Fractals Program chair for multiple International Conferences on Data Science Challenges Dr. Carbone actively supervises PhD students (including Chiara Panico in Computer and Systems Engineering) and serves as Course Instructor for Quantum Information and Quantum Computing courses. Her research projects include TED4LAT (2022-2025), FuturICT 2.0 (2017-2020), and Challenges in Data Science (2016). She maintains active collaborations with institutions including the European Commission and the Department for Digital Transformation of the Presidency of the Council of Ministers.

Marsil ZakourView profile

Researcher

• Computer Vision
• Machine Learning
• Human-Object Interaction
• +2 more

Marsil Zakour is a Ph.D. Candidate and Researcher at the Chair of Media Technology (Technical University of Munich). He holds a Master of Science in Computer Science from TUM (2021) and a Bachelor of Science in Software Engineering from Al-Baath University (2016). His work focuses on 3D reconstruction, understanding, and synthesis of hand-object interactions. Research Interests 3D Hand-Object Interaction Modeling Human Activity Understanding Computer Vision Machine Learning Key Projects Centre for Tactile Internet with Human-in-the-Loop (CeTI) 5G Testbed Bayern (eHealth focus) KMU-Innovativ: KIMaps IEEE P1918.1.1 Haptic Codecs Publications His research spans action segmentation, embodied AI, and 3D object feature modeling, with recent works on procedural mistake detection (ICCV 2025), vision-language models (CVPR 2025), and domain adaptation (IROS 2024). Supervision Zakour mentors students in projects like Hand Pose Estimation Using Multi-View RGB-D Sequences , requiring expertise in computer vision and deep learning frameworks.

Sanjeev R. KulkarniView profile

Professor

• Machine Learning
• Pattern Recognition
• Information Theory
• +6 more

Sanjeev R. Kulkarni is the William R. Kenan, Jr., Professor of Electrical and Computer Engineering and Professor of Operations Research and Financial Engineering at Princeton University. He serves as Dean of the Faculty and is affiliated with the Department of Philosophy and the Center for Statistics and Machine Learning. His career spans roles as Dean of the Graduate School (2014-2017), Director of the Keller Center (2011-2014), and Master of Butler College (2004-2012). His research intersects machine learning , information theory , and wireless networks , focusing on statistical pattern recognition, nonparametric estimation, and econometrics. He has pioneered work in universal information estimation , energy-efficient wireless communication , and distributed learning in sensor networks. Recent publications highlight his work in forecast aggregation , robust geometric fitting , and variational Bayesian methods . These span communications , machine learning , and signal processing applications. Scientific awards include the ARO Young Investigator Award , NSF Young Investigator Award , and IEEE Fellowship . He has received Princeton's President's Award for Distinguished Teaching and multiple Undergraduate Engineering Council Excellence Awards . Prof. Kulkarni has advised 19 PhD students, including notable alumni at IBM, Google, Amazon, and RAND Corporation. His teaching spans four departments and includes courses like Learning Theory and Epistemology (cross-listed with Philosophy) and Wireless Revolution (telecom policy).

Bodo RosenhahnView profile

Professor

• Computer Vision
• Machine Learning
• Big Data Analysis
• +7 more

Bodo Rosenhahn is a Full Professor at Leibniz University Hannover, heading the Institute for Information Processing since September 2008. His research focuses on automated image interpretation with profound expertise in Computer Vision, Machine Learning, and Big Data Analysis. He has established himself as a leading researcher through extensive contributions to the field and successful industry transfer of his work. Rosenhahn received his Computer Science education at the University of Kiel, earning his Dipl.-Inf. in 1999 and Dr.-Ing. in 2003. His academic journey included a postdoctoral position at the University of Auckland (2003-2005), funded by the German Research Foundation, followed by senior researcher work at the Max-Planck Institute for Informatics in Saarbruecken (2005-2008). His research interests span multiple cutting-edge areas including Computer Vision, Machine Learning, 3D Human Pose Estimation, Motion Capture, Object Tracking, Anomaly Detection, and Reinforcement Learning. His work bridges theoretical foundations with practical applications, particularly in medical imaging, autonomous systems, and industrial quality control. The group he leads has developed innovative approaches for video-based motion capture, semantic scene analysis, and multi-object tracking that have achieved state-of-the-art results in numerous challenges. His most recent publications demonstrate strong trends toward explainable AI systems, uncertainty quantification in vision models, robust multi-model fitting techniques, and the integration of quantum principles with machine learning. These works reflect his commitment to developing both theoretically sound and practically applicable computer vision solutions that address real-world challenges in industry and medicine. DAGM-Prize 2002 Dr.-Ing. Siegfried Werth Prize 2003 DAGM-Main Prize 2005 ERC-Starting Grant 2011 (EUR 1.43 million) CVPR 2017 Multi-Object Tracking Challenge PhysRev-A Editors Suggestion 2023 TÜV-Süd Innovation award 2018 As head coach of the LUH AI competition team, Rosenhahn has mentored numerous students who have achieved success in international competitions. His research has been supported by prestigious grants including the ERC Starting Grant and POC Grant. He has also received the Erskine Fellowship for research at the University of Canterbury. Since 2023, he serves as associate editor for IEEE TPAMI, the highest-ranked journal in computer science. Rosenhahn leads a vibrant research group focused on automated image interpretation with multiple ongoing projects including Multiple People Tracking, Relational Object Tracking, Physics-based modeling, Video-based Motion Capture, and Quantum Learning. His group has developed significant datasets such as the Multimodal Motion Capture Indoor Dataset (MPI08) and Multimodal Motion Capture Dataset (TNT15) that have become valuable resources for the computer vision community. The group maintains strong industry connections, successfully transferring research into practical applications while continuing to push the boundaries of fundamental research in computer vision and machine learning.

• Computational Biology
• Biophysics
• Image Analysis
• +6 more

Albert Alonso is a Research Fellow at the Department of Computer Science within the Faculty of Science at the University of Copenhagen . He is affiliated with the Niels Bohr Institute and holds the position of Guest PhD Student in addition to his postdoctoral role. Postdoctoral Fellow in Biocomplexity and Biophysics Guest PhD Student Image Analysis and Computational Modeling Albert’s research focuses on computational biology , biophysics , and image analysis , with particular emphasis on gradient sensing and biological transport networks . His work bridges theoretical physics and computer science to develop differentiable computational methods for understanding microorganism behavior and cell motility . Recent publications highlight advancements in optimal node positioning , non-reciprocal chaotic systems , and chemotaxis strategies . His studies often integrate computational modeling with biological systems , including applications in high-density microscopy data analysis and receptor dynamics for spatial gradient sensing. Albert’s work has been published in high-impact journals such as Physical Review Letters , PNAS , and Communications Biology . He employs open-access platforms and collaborates with institutions globally, with a focus on Denmark and international networks .

• Machine Learning
• Natural Language Processing
• Sustainable Artificial Intelligence
• +3 more

Casper Dorph-Jensen serves as a Lecturer in the Department of Computer Science at the University of Copenhagen, where he is an active member of the Machine Learning section. His academic work bridges theoretical machine learning foundations with practical applications across diverse domains, contributing to both research and educational initiatives within Denmark's premier computing institution. His research spans multiple critical frontiers in artificial intelligence. Key interests include: Natural Language Processing with emphasis on emotion-aware dialogue systems and cross-cultural adaptation frameworks Sustainable AI development addressing environmental impacts of large models Quantum machine learning applications for biomolecular simulations Medical image analysis techniques for clinical diagnostics Fairness-aware information retrieval systems and recommender algorithms Analysis of his 2024-2025 publications reveals strong interdisciplinary trends combining machine learning with quantum physics, healthcare informatics, and sustainability science. Notable patterns include the application of large language models to clinical contexts (particularly nursing values evaluation), energy efficiency concerns in AI infrastructure, and novel quantum-classical hybrid approaches for scientific computing. His work frequently addresses real-world implementation challenges in noisy environments and resource-constrained settings. No scientific awards were documented in available sources. Information regarding student supervision or specific research grants remains unavailable in current public records, though his Machine Learning section affiliation suggests participation in broader departmental initiatives like the SCIENCE AI Centre and TreeSense remote sensing project. He operates within the Department of Computer Science's Machine Learning section, which maintains dedicated high-performance computing resources and participates in the university-wide SCIENCE AI Centre. This section focuses on both theoretical ML foundations and applications in medical imaging, biological data modeling, and sustainability-focused computing, with recent projects including quantum computing initiatives and environmental monitoring systems.

• Image Analysis
• Computational Modelling
• Geometry
• +4 more

Hang Yin is a Tenure Track Assistant Professor at the Department of Computer Science, University of Copenhagen. His research focuses on Image Analysis, Computational Modelling, and Geometry, with applications in robotics, motion capture, and multimodal learning. Research interests: Geometric representations in robotics Motion capture artifact removal Diffusion-based motion style transfer Human-robot interaction analysis Research output trends show significant contributions in AI-driven robotics (2025), motion capture optimization (2024), and multimodal human movement analysis (2023). His work combines computational geometry with machine learning for practical applications in autonomous systems. Contact: hayi@di.ku.dk

Manolis SangriotisView profile

Associate Professor

• Image Processing
• Computer Vision
• Stereo Image Coding
• +4 more

Manolis Sangriotis is an Associate Professor at the National and Kapodistrian University of Athens, affiliated with the Department of Informatics and Telecommunications. His academic journey began with a B.Sc. in Physics (1970), followed by M.Sc. degrees in Electronics and Radioelectrology (1973) and Electronic Automation (1975), culminating in a Ph.D. in Informatics and Telecommunications (1980) from the University of Athens. His research focuses on image processing , computer vision , and 3D imaging , with emphasis on stereo image coding, integral photography, and real-time compression architectures. He explores applications in medical imaging, autostereoscopic displays, and multimedia systems, leveraging wavelet transforms, morphological operations, and statistical clustering. Recent publications (2012–2004) reveal a strong trend toward integral imaging innovations , including rectification frameworks, watermarking, and 3D-DCT compression. His work consistently addresses challenges in multiview data representation, disparity estimation, and photorealistic rendering, bridging computer vision with optical engineering. Scientific Awards: Best Paper Award at IEEE 8th International Conference on Intelligent Information Hiding and Multimedia Signal Processing (2012) He actively advises PhD students, including Eirini Kostopoulou, Tzanoukos Georgios, and Papageorgiou Louis. His research group collaborates on projects related to real-time systems and image datasets, often supported by institutional grants. As part of the RTSImage laboratory, he contributes to developing computational tools for image analysis and compression, with applications spanning medical diagnostics and 3D display technologies. Future directions include advancing omnidirectional imaging and robustness in automated biomedical assessments.

Sitan ChenView profile

Assistant Professor

• Machine Learning
• Quantum Engineering
• Theory of Computation
• +7 more

Sitan Chen is an Assistant Professor of Computer Science at Harvard University's John A. Paulson School of Engineering and Applied Sciences. His research focuses on foundational aspects of machine learning, quantum information, and algorithm design, with a particular emphasis on provable guarantees for generative modeling, deep learning, and quantum learning. He is affiliated with the Theory of Computation group, the ML Foundations group, and the Harvard Quantum Initiative. Education: PhD in EECS from MIT (advised by Ankur Moitra) Bachelor's in Mathematics and Computer Science from Harvard (advised by Salil Vadhan and Leslie Valiant) Grants & Awards: NSF CAREER Award (CCF-2441635) NSF Small (CCF-2430375) Harvard Dean's Competitive Fund for Promising Scholarship Research Interests: Generative models and diffusion processes Quantum tomography and quantum learning Algorithmic foundations for inverse problems Provably efficient learning algorithms Advising & Teaching: Advises PhD/Masters students in quantum computing and machine learning Teaches courses like Quantum Learning Theory and Algorithms for Data Science Key Contributions: First polynomial-time algorithms for learning narrow neural networks Advances in quantum state estimation with minimal resources Provably efficient sampling methods for diffusion models

• Bio-inspired Robotics
• Flapping-Wing Vehicles
• Safety-Critical Nonlinear Control
• +10 more

Nak-seung Patrick Hyun is an Assistant Professor in the School of Electrical and Computer Engineering at Purdue University, located in West Lafayette. His office is MSEE 274, and his contact information includes the email nhyun@purdue.edu and a personal webpage at http://www.nphyun.com/. Hyun holds degrees from Korea University (B.S., Electrical Engineering, 2009) and the Georgia Institute of Technology (M.S. in Mathematics and M.S./Ph.D. in Electrical and Computer Engineering, completed in 2013 and 2018, respectively). His research focuses on a cyclic learning approach integrating biology, mathematical system theory, and robotics, with a primary emphasis on Control Theoretic Bio-Inspired Robotics. Key areas include flapping-wing vehicles, safety-critical nonlinear control, adaptive control, and impulsive systems. His work also addresses contraction theory, geometric control, optimal motion planning, and swarm robotics. Hyun's publications span topics such as insect-inspired aerial microrobotics, network control of robotic systems, and ultrafast actuators. Recent work emphasizes applications in soft robotics, microfluidic control systems, and biomimetic design. Despite his prolific output, no scientific awards are explicitly mentioned in the provided text. His research also intersects with automatic controls, communications, and signal processing, reflecting a broad interdisciplinary approach to robotics and control systems engineering. Hyun’s contributions include hardware-in-the-loop testing methodologies for flying microrobots and optimization of ultrafast systems inspired by biological mechanisms.

• Mathematical Foundation of Deep Learning
• Deep Learning Theory
• Optimization
• +3 more

Chaoyue Liu is an Assistant Professor in the Elmore Family School of Electrical and Computer Engineering at Purdue University, located in West Lafayette. His research focuses on the mathematical foundations of deep learning, deep learning theory, and optimization techniques. He holds a position in the Department of Electrical and Computer Engineering and contributes to advancing theoretical and practical aspects of machine learning systems. Research Interests: Mathematical underpinnings of deep learning architectures and their theoretical guarantees Optimization algorithms for large-scale machine learning models Federated learning and privacy-preserving techniques Analysis of neural network training dynamics and loss landscapes Key Research Trends in Publications: Recent work emphasizes optimization challenges in over-parameterized systems, federated learning frameworks, and the dynamics of neural network training. His articles explore topics like SGD batch saturation, differential privacy integration, and the emergence of linear behavior in wide neural networks. Grants & Advising: No specific grants or student advisement information is listed. Collaborations may involve Purdue's research groups in machine learning and electrical engineering. Labs/Teams: Affiliated with Purdue's Electrical and Computer Engineering research clusters, likely contributing to interdisciplinary projects in AI and signal processing.

Peter David HoffView profile

Professor

• Bayesian Inference
• Network Analysis
• Spatial Statistics
• +2 more

Peter David Hoff is Professor of Statistical Science at Duke University, specializing in Bayesian methods for relational data, covariance estimation, and spatial modeling. Current research develops statistical frameworks for network analysis, matrix-variate data, and environmental applications. Key methodological contributions: Bayesian inference for structured high-dimensional data Covariance estimation for matrix-variate observations Spatial prediction on constrained domains Applied work includes fluorescence spectroscopy analysis for water quality monitoring and species abundance prediction. Recent publications advance source apportionment techniques and spatial covariance modeling for irregular domains. Teaching encompasses Bayesian inference, linear models, and multivariate analysis courses at graduate levels. Professional service includes former directorship of Duke's Statistical Science graduate program.

Hongkai ZhaoView profile

Professor

• Computational and Applied Mathematics
• Numerical Analysis
• Scientific Computing
• +4 more

Hongkai Zhao is the Ruth F. DeVarney Distinguished Professor of Mathematics and Chair of the Department of Mathematics at Duke University's Trinity College of Arts & Sciences. He holds a Ph.D. in Mathematics from UCLA (1996) and has held prior positions including Chancellor's Professor at UC Irvine and Gábor Szegő Assistant Professor at Stanford University. His research focuses on computational and applied mathematics with applications in inverse problems, imaging, PDEs, and scientific computing. Key research areas include numerical methods for wave propagation, radiative transfer, and shape analysis. Zhao has led NSF-funded projects on PDE learning, radiative transfer, and analysis training. He has received prestigious awards including the Feng Kang Prize (2007) and SIAM Fellowship (2022). Teaching includes advanced courses on stochastic processes, numerical linear algebra, and mathematical analysis. His work bridges theory and practice, contributing to medical imaging algorithms, computational physics, and geometric modeling.

• Image Processing
• Signal Processing
• 3D Environments
• +4 more

Stuart Perry is a Professor at the University of Technology Sydney (UTS), serving as Head of Discipline for Signal Processing and Analytics in the School of Electrical and Data Engineering. He holds affiliations with UTS' Faculty of Engineering and Information Technology, the Global Big Data Technologies Centre, and the Visualization Institute. With over 20 years of experience, his career spans roles at DSTO and Canon Information Systems Research Australia (CiSRA), focusing on image processing, signal processing, and perceptual quality measurement. Perry co-directs the Perceptual Imaging Laboratory (PILab), researching 3D environments, light field technologies, and human perception in immersive realities. He actively contributes to international standards committees like ISO/TC42 and ISO/SC29/WG7, leading JPEG's point cloud coding efforts. His research emphasizes adaptive image processing, machine learning-driven object detection, and medical imaging applications. Perry has authored 60+ publications, two books, and 20 patents. Current projects include VR empathy case studies, point cloud compression, and disaster management digital transformation. Education: PhD in Engineering, University of Sydney (1999) Research Interests: His work bridges computational imaging and human perception, addressing challenges in augmented/virtual reality (AR/VR), 3D scanning, and immersive media. Key areas include light field and point cloud coding, psychophysics of visual perception, and medical diagnostics via machine learning. He explores how perceptual principles can optimize interactive technologies for education, healthcare, and entertainment. Recent Research Trends: Recent articles focus on 3D Gaussian splatting, glaucoma detection via deep learning, and JPEG Pleno standards for plenoptic imaging. His work balances technical innovation (e.g., efficient point cloud compression) with human-centric design (e.g., reducing VR motion sickness through display lag analysis). Awards & Recognition: Member of IEEE and founding SPINet participant. Over 60 refereed publications and 20 patents highlight his industry-academic impact. Grants & Leadership: Leads SmartSat CRC projects on yield estimation and Aus4innovation-funded disaster response tech. Manages grants totaling millions AUD. Editorial roles include Associate Editor of SPIE/IS&T Journal of Electronic Imaging. Labs & Collaborations: PILab collaborates internationally on perceptual imaging standards. Active in ISO committees shaping future media technologies.