جست‌وجوی استاد و پژوهشگر

Mengyu Chuمشاهده پروفایل

استادیار

• Physics-Enhanced Deep Learning
• Fluid Dynamics Simulation
• Computer Graphics
• +۳ مورد دیگر

Mengyu (Rachel) Chu is a tenure-track Assistant Professor at the School of Intelligence Science and Technology, Peking University, affiliated with the Visual Computing and Learning Lab. Previously, she was a Lise Meitner Postdoctoral Research Fellow at the Max Planck Institute for Informatics (2020–2022), and completed her Ph.D. in Computer Science at Technical University of Munich (2014–2020). She holds a B.Eng. in Software Engineering from Southeast University (2007–2011) and an M.Eng. in Computer Science from Zhejiang University (2011–2014). Her research focuses on Physics-Enhanced Deep Learning , combining deep learning with physical simulations to enhance fluid dynamics modeling, video synthesis, and neural network training. Key areas include fluid reconstruction, manipulation, synthesis, and temporally coherent video generation. Her work bridges physics-based principles with modern AI techniques for realistic simulations and generative models. Notable contributions include Physics Informed Neural Fields for sparse data reconstruction (SIGGRAPH 2022), Learning Meaningful Controls for Fluids (SIGGRAPH 2021), and TempoGAN for fluid flow super-resolution (SIGGRAPH 2018). Her research emphasizes real-world applications in graphics, visualization, and computational physics. She has been recognized with the Lise Meitner Postdoctoral Fellowship (2020) and Summa Cum Laude distinction for her Ph.D. (2020). Her work spans academic publications, patents, and open-source projects, with collaborations across institutions like TU Munich and Max Planck Institute.

Evangelos Boukasمشاهده پروفایل

دانشیار

• Deep Learning
• Unmanned Aerial Vehicles
• Computer Vision
• +۵ مورد دیگر

Evangelos Boukas is an Associate Professor in the Department of Electrical and Photonics Engineering at the Technical University of Denmark (DTU), Faculty of Engineering. His research focuses on autonomous robotic systems for marine vessel inspection, confined space navigation, and man overboard detection using UAVs and deep learning techniques. His core research interests include Deep Learning , Unmanned Aerial Vehicles , Computer Vision , and Robotics , applied to solve challenges in marine robotics and autonomous inspection. He develops uncertainty-aware navigation systems, probabilistic segmentation methods, and reinforcement learning frameworks for real-world deployment in complex environments. Recent publications demonstrate a strong trend toward GPU-accelerated deep learning for confined space inspection, with emphasis on uncertainty estimation, domain adaptation, and real-time processing. Key application areas include marine vessel classification, ballast tank inspection, and search-and-rescue operations, often leveraging multimodal sensor fusion. Dr. Boukas actively supervises five PhD students across major research projects: Probabilistic Deep Learning for Autonomous Aerial Inspection (2025-2028) Aerial Robots Design for Confined Spaces Inspection (2024-2027) Active Semantic Segmentation for Confined Spaces using Aerial Robots (2024-2027) Autonomous Aerial Robotics for Man Overboard Incidents (2023-2026) Visual and Multimodal Perception for Construction Robotics (2023-2026) He leads the "Perception and Cognition for Autonomous Systems" research group at DTU, which develops advanced perception algorithms for robots operating in challenging environments like ship ballast tanks and marine vessels, contributing to UN Sustainable Development Goals for industry innovation and marine conservation.

• Surveying
• LiDAR Technology
• Cadastral Systems
• +۴ مورد دیگر

Glenn Campbell is an Associate Professor (Surveying) at the University of Southern Queensland's School of Surveying and Built Environment. His research spans spatial data law, LiDAR applications, cadastral systems, and remote sensing of water resources. Campbell employs advanced techniques including machine learning for topographic feature extraction and matrix inversion methods for water quality assessment. Research Focus: Geospatial law and indigenous land boundaries LiDAR processing for urban feature extraction Water quality remote sensing techniques Cadastral system modernization His publications demonstrate consistent focus on measurement accuracy, spatial data governance, and advanced geospatial analysis techniques. Recent work shows increasing emphasis on digital copyright issues in spatial data and machine learning applications for LiDAR processing. Awards & Recognition: No major scientific awards reported. Student Advising: No advisee information available.

Hsiao-Chun Wuمشاهده پروفایل

استاد

• Statistical Learning
• Digital Signal Processing
• Wireless Communications
• +۹ مورد دیگر

Hsiao-Chun Wu is a Professor and holder of the Michel B. Voorhies Professorship at Louisiana State University (LSU), affiliated with the Division of Electrical & Computer Engineering within the School of Electrical Engineering and Computer Science. He earned his Ph.D. in 1999 from the University of Florida. His research focuses on statistical learning, embedded algorithms, digital signal processing, and wireless communications. Key areas include optimization techniques for detection and estimation, image/speech processing, and networked systems design. He has contributed to advancements in sensor deployment strategies, tensor-based signal processing, and machine learning applications for posture recognition and multimedia classification. Notable technical interests span computational photography, robust multichannel decorrelation, and energy-efficient data collection in wireless sensor networks. His work often integrates tensor analysis and graph convolutional networks to address challenges in high-dimensional data processing. Dr. Wu's academic contributions include pioneering methods for indoor line-of-sight coverage optimization and developing novel modulation recognition techniques. His research also addresses industrial IoT performance optimization and biomedical applications such as noninvasive activity recognition using mmWave radar.

• Computer Vision
• Machine Learning
• Autonomous Driving
• +۳ مورد دیگر

Adrien Gaidon is an Adjunct Professor with a focus on Human-Centered Action Recognition and advanced visual representation learning. His current projects include collaborations with MIT on Physical and Functional Inductive Biases for visual systems, while completed works span Robust Machine Learning and Interaction-Aware Control for autonomous vehicles. Research Trends : His 2025 publications emphasize 3D Scene Understanding , Depth Estimation , and Neural Radiance Fields , alongside innovations in Uncertainty-Aware Perception and Self-Supervised Learning . Key subfields include Autonomous Driving , Robotics , and Geometric Learning for dynamic environments. Advising and Grants : No explicit details about students, teams, or grants were found in the provided text.

Giuseppe Savaréمشاهده پروفایل

استاد

• Mathematical Analysis
• Optimal Transport
• Gradient Flows
• +۴ مورد دیگر

Giuseppe Savaré is a Full Professor of Mathematical Analysis at the Department of Mathematics, University of Pavia, and a Hans Fischer Senior Fellow at the Technical University of Munich's Institute for Advanced Study (TUM-IAS) since 2019. His research focuses on variational methods for evolution problems, including gradient flows, rate-independent models, nonlinear PDEs, and optimal transport theory in metric spaces. Education: PhD in Mathematics (1988) from University of Pavia. His work bridges optimal transport, metric measure spaces, and analysis in non-Euclidean geometries, with applications to PDEs, curvature bounds, and generalized gradient flows. Key contributions include foundational studies on Wasserstein gradient flows, entropy-transport problems, and abstract action spaces in dynamical systems. Scientific awards include the prestigious Ennio De Giorgi Prize (2011) and the Gioachino Japichino Prize (1994), alongside an invitation as a speaker at the 7th European Congress of Mathematics (2016). Collaborations with researchers like Massimo Fornasier and Alexander Mielke have advanced consensus-based optimization, multi-agent control, and quantum drift-diffusion models.

António Manuel Gonçalves Pinheiroمشاهده پروفایل

دانشیار

• Image Processing
• Multimedia Quality Evaluation
• 3D Imaging Technologies
• +۱ مورد دیگر

António Pinheiro is an Associate Professor in the Department of Physics at Universidade da Beira Interior and researcher at Instituto de Telecomunicações. He specializes in image processing, multimedia quality evaluation, emerging 3D imaging technologies, and medical image analysis. Research interests span: Multimedia quality assessment methodologies Point cloud compression and processing Medical image analysis for diagnostic applications JPEG standardization and emerging imaging formats 5G multimedia streaming technologies He has received multiple scientific awards including: 2022 Best Paper at 3D Imaging and Applications 2020 Award-winning ETRI Journal Papers 2014 Top 10% Paper Award at IEEE MMSP As director of the 'Eletrónica Digital: Circuitos e Sistemas' program, he teaches courses on digital systems, microprocessors, and signal/image processing. He actively contributes to ISO/IEC JPEG standardization as Communication Subgroup chair.

• Applied Mathematics
• Scientific Computing
• Machine Learning
• +۷ مورد دیگر

Yimin Zhong is an Assistant Professor of Mathematics and Statistics at Auburn University. He holds a Ph.D. from the University of Texas at Austin (2017). His research focuses on applied mathematics, scientific computing, and machine learning, with expertise in inverse problems, radiative transfer, and nonlinear optics. He leads undergraduate research initiatives and collaborates on projects involving biomedical imaging and transport models. Key research areas include PDE learning, neural networks for high-frequency approximation, intrinsic complexity of datasets, and imaging with physical models. Zhong's work bridges theoretical analysis with computational methods, addressing challenges in data-driven modeling and inverse problem uniqueness/stability. He has contributed to fast algorithms for radiative transport and implicit boundary integration techniques for macromolecular electrostatics. His projects span collaborations with industry (e.g., Boeing) and academic networks, emphasizing interdisciplinary applications. Current interests also include graph theory, randomized algorithms, and geometric measure theory. Despite no explicit awards listed, his extensive publication record reflects recognition in computational and applied mathematics fields. Education: Ph.D. in Mathematics, University of Texas at Austin (2017) Advising: Mentored undergraduate research in inverse problems and numerical methods Labs/Teams: Leads Auburn's Undergraduate Research Network in Mathematics Open Problems: Active in transport equation analysis, nonlinear diffusion, and geometric measure theory challenges

• Artificial Intelligence
• Machine Learning
• Cybersecurity
• +۳ مورد دیگر

Md. Ismail Hossain is an active academic researcher with a focus on Artificial Intelligence , Machine Learning , and Cybersecurity . His work spans both theoretical and applied domains, including Neural Network Pruning , Electric Vehicle Charging Systems , and Security Analysis of emerging technologies. Key Research Themes : Neural network optimization, deepfake detection, and energy systems integration Recent Trends : Articles from 2022-2025 show increasing focus on AI model efficiency and security frameworks

• Sub-Riemannian Geometry
• Mathematical Analysis
• Neurogeometry
• +۳ مورد دیگر

Giovanna Citti is a Full Professor in the Department of Mathematics at the University of Bologna. Her research focuses on sub-Riemannian geometry, mathematical analysis, and neurogeometry, with a particular emphasis on modeling the functional architecture of the visual and motor cortices. She develops geometric frameworks to understand neural processing in the brain, including models of visual perception and motor control. Her work integrates concepts from differential geometry, partial differential equations (PDEs), and Lie group theory to analyze sub-Riemannian structures. She explores regularity properties of subelliptic PDEs and applies these to biological systems, such as the cortical organization of the visual cortex and motor pathways. Recent efforts include developing brain-inspired neural networks and studying neurogeometric models of stereo vision and 3D perception. Key contributions include sub-Riemannian models of perceptual completion, cortical-based optimal transport frameworks, and analysis of geometric optical illusions. Her research bridges pure mathematics and neuroscience, addressing challenges in both fields through innovative interdisciplinary approaches.

Matthew Hirnمشاهده پروفایل

دانشیار

• computational mathematics
• harmonic analysis
• data science
• +۷ مورد دیگر

Matthew Hirn is a computational mathematician with expertise in harmonic analysis, data science, and machine learning. He was a tenured Associate Professor at Michigan State University (MSU), jointly appointed in the Department of Computational Mathematics, Science & Engineering and the Department of Mathematics. As the scientific leader of the ComplEx Data Analysis Research (CEDAR) Team at MSU, he developed innovative methods for analyzing complex data, including wavelet scattering transforms for atomistic systems and geometric deep learning techniques. He is currently a Senior Quantitative Researcher at Citadel LLC, contributing to algorithmic trading strategies. His research bridges theoretical mathematics and applied data science, with notable contributions to graph neural networks, scattering transforms, and privacy-preserving methods. His academic career included organizing conferences such as the SIAM Mathematics of Data Science mini-symposium on geometric learning and co-authoring influential software like the Kymatio library for wavelet scattering transforms. He advised PhD students Ryan LaRose, Xavier Brumwell, and Jieqian He, who have since pursued impactful roles in academia and industry. His work on 3D wavelet scattering networks for material science and geometric scattering on manifolds has advanced the intersection of mathematics and machine learning. Matthew’s research interests span signal processing, graph representation learning, and applications in bioinformatics and many-particle physics. He has published extensively in top journals and conferences, including the Journal of Chemical Physics and the Journal of Machine Learning Research.

• Image Processing
• Computer Science
• Mathematics
• +۷ مورد دیگر

Carole Le Guyader is an Associate Professor at the Department of Mathematical and Software Engineering at the National Institute of Applied Sciences of Rouen (INSA Rouen). Her research focuses on hybrid variational/deep learning methods under topological and geometric constraints, with applications in biomedical imaging, geophysics, and high-performance computing (HPC). She supervises Ph.D. students and collaborates with institutions such as UCLA , Cambridge University , and University of Pau . Teaching: Mathematical Engineering (PDEs, CAGD in M1; Variational Methods in Image Processing in M2), L1/L2 STPI courses. Administrative Roles: LMI correspondent for GDR MIA (since 2021), Head of Mathematics Teaching at STPI INSA Rouen (since 2019), Deputy Director of GM Department (2018-2020). Her recent work emphasizes integrating deep learning with variational methods for tasks like semantic segmentation in medical imaging and nonlinear elasticity models for image registration. She has contributed to parallel computing implementations and industrial partnerships with Siemens-Gamesa and Dassault Systèmes .

• Computer Vision
• Artificial Intelligence
• Neuroscience
• +۵ مورد دیگر

John K Tsotsos is a Distinguished Research Professor and Director of the Centre for Innovation in Computing at the Lassonde School of Engineering, York University. He also holds adjunct professorships in Computer Science and Ophthalmology & Vision Sciences at the University of Toronto. With a PhD in Computer Science from the University of Toronto (1980), his work bridges computer vision, neuroscience, and autonomous systems. His research focuses on visual attention mechanisms, active vision, and their applications in driver behavior analysis, autonomous vehicles, and cognitive modeling. Notable projects include SCOUT+ for drivers’ gaze prediction and studies on 3D visuospatial problem-solving. His publications span over 400 articles, emphasizing interdisciplinary approaches to understanding human and machine vision. Recent work explores data limitations in vision datasets, perceptual grouping in neural networks, and temporal attention effects. While no specific awards are highlighted, his leadership roles and prolific output reflect significant contributions to the field. His research group at York University drives innovation in AI-driven perception systems and human-centric autonomous technologies.

Stefan Rothمشاهده پروفایل

استاد

• Computer Vision
• Machine Learning
• Semantic Scene Understanding
• +۳ مورد دیگر

Stefan Roth is a Professor of Computer Science at Technische Universität Darmstadt, where he leads the Visual Inference Lab. His research focuses on statistical models for visual inference problems, with expertise in computer vision, machine learning, and deep learning applications. Specific areas include semantic scene understanding, image motion estimation, and probabilistic models for low-level vision tasks. Key research areas: Semantic scene understanding and segmentation Optical flow and scene flow estimation Deep learning architectures for vision Probabilistic modeling in computer vision Video analysis and understanding Professor Roth's recent publications explore transformer-based scene graph generation, unsupervised segmentation techniques, and foundation models for depth estimation. His work demonstrates strong interdisciplinary connections between computer vision, machine learning, and autonomous systems, with applications in urban scene understanding and intelligent transportation systems.

Hang Daiمشاهده پروفایل

استاد

• Computer Vision
• Medical Image Segmentation
• 3D Object Detection
• +۲ مورد دیگر

Dr. Hang Dai is transitioning to a Full Professor position at Wuhan University after serving as Honorary Research Fellow at the University of Glasgow's School of Computing Science. His research spans computer vision, medical image analysis, and autonomous driving systems. With over 26 publications, he develops deep learning methods for 3D segmentation, object detection, and video enhancement. Research areas include: Advanced 3D semantic segmentation for LiDAR data Semi-supervised medical image analysis Multi-modal fusion for autonomous vehicles Current projects focus on certainty-guided contrastive learning for medical imaging and attention mechanisms for depth super-resolution.