جست‌وجوی استاد و پژوهشگر

Sun-Yuan Kungمشاهده پروفایل

استاد

• Machine Learning
• Deep Learning
• Neural Networks
• +۷ مورد دیگر

Sun-Yuan Kung is a Professor of Electrical and Computer Engineering at Princeton University specializing in high-performance learning networks and explainable AI. His research develops beyond back-propagation paradigms to create optimal neural architectures through structural learning and discriminant information metrics. His academic credentials include: Ph.D. in Electrical Engineering, Stanford University (1977) M.S. in Electrical Engineering, University of Rochester (1974) B.S. in Electrical Engineering, National Taiwan University (1971) Professor Kung pioneered Explainable Neural Networks (XNN) incorporating Internal Neuron's Learnability (INL) using internal teacher labels and discriminant information (DI) for node/layer ranking. This enables deep compression while enhancing model robustness and adaptability for real-time applications in image processing, privacy protection, and security-sensitive environments. His work directly addresses DARPA's Explainable AI (XAI) initiatives through end-user-adaptive labeling mechanisms. Recent publications (2023-2025) demonstrate sustained innovation in efficient deep learning architectures, with dominant themes in remote sensing applications (object detection, image captioning, change detection), quantum-inspired algorithms, and multimodal representation learning. Key trends include neural architecture search, model compression techniques, and reinforcement learning integration for specialized domains. His distinguished honors include: Life Fellow of IEEE (2016) IEEE Third Millennium Medal (2000) IEEE Signal Processing Society Best Paper Award (1996) IEEE Signal Processing Society Technical Achievement Award (1992) IEEE Fellow (1988) Professor Kung mentors graduate researchers including Katherine Shu-Min Li, Xiaxin Shen, and Zhuoqing Song, with funding supporting projects in deep compression, privacy-preserving ML, and XAI frameworks. His group develops foundational techniques for discriminant information-based network pruning and structural gradient methods. He leads a research team advancing the XNN framework for DARPA's Explainable AI initiatives, focusing on real-time decision support through internal neuron explainability and channel exploration for model optimization.

Julien Milleمشاهده پروفایل

دانشیار

• Computer Science
• Pattern Recognition
• Image Analysis
• +۵ مورد دیگر

Julien Mille is an Associate Professor at INSA Centre Val de Loire and Ecole Polytechnique de l'Université de Tours , France. He conducts research with the RFAI team (Reconnaissance des Formes et Analyse d'Images) at the Laboratoire d'Informatique Fondamentale et Appliquée in Tours. Previously, he was an associate professor at Université Claude Bernard Lyon 1 (2009-2015), affiliated with the LIRIS laboratory and Imagine team . Key research areas: Pattern recognition, image analysis, active contours/surfaces, optimal transport, human activity recognition Technical contributions: Developed open-source tools for image labeling ( PixelLabeling ), DeepFlowCUDA optimization Scientific contributions span computer vision, biomedical imaging, and plant science applications. Notable work includes: Optimal transport methods for image restoration Hierarchical skeletonization for shape matching Pose-driven attention mechanisms for video analysis 3D segmentation of medical images His research has been published in leading journals like SIAM Journal on Imaging Sciences , International Journal of Computer Vision , and Computer Vision and Image Understanding , along with major conferences including CVPR , ECCV , and ICIP .

• Information Visualization
• Machine Learning
• Data Mining
• +۵ مورد دیگر

Gilles Venturini is a Professor in Computer Science at the University of Tours, France, affiliated with PolytechTours and the Computer Science Lab. He has held this position since 1998 following his appointment as Assistant Professor from 1994-1998. His academic credentials include a Research Supervisor Degree (HdR) from the University of Tours (1997), a PhD in Computer Science from the University of the South of Paris (1994) supervised by Yves Kodratoff, and dual qualifications in Computer Science (MSc, 1990) and Electrical Engineering (ESIEE, 1990). Professor Venturini's research concentrates on information visualization, machine learning, and data mining with emphasis on genetic algorithms, neural networks, and computer vision. His work develops practical tools for visual data exploration, automatic dashboard generation, and analysis of large datasets, particularly addressing usability challenges for novice users in open data contexts. His 2023-2025 publications reveal sustained innovation in ternarization of vision-language models for edge devices, few-shot object detection, and backpropagation alternatives for binary neural networks. These contributions bridge theoretical machine learning advancements with applications in cultural heritage visualization and human resources analytics. No scientific awards were documented in the source materials. While specific grant details and student supervision records are absent from the provided text, his professorial role implies active involvement in research funding acquisition and academic mentoring. His work frequently intersects with interdisciplinary teams, particularly in digital humanities projects. He remains operationally active within the University of Tours' Computer Science Lab, driving research in visualization techniques and machine learning applications through this primary institutional affiliation.

Murat Tahtaliمشاهده پروفایل

مدرس ارشد

• Medical Imaging
• Light Field CT and SPECT
• Adaptive Optics
• +۶ مورد دیگر

Dr. Murat Tahtali is a Senior Lecturer at UNSW Canberra within the School of Engineering and Information Technology at the University of New South Wales. His academic career spans multiple engineering disciplines with a strong focus on interdisciplinary research connecting engineering principles with medical applications. Dr. Tahtali's research interests span several interconnected fields including Medical Imaging , particularly Light Field CT and SPECT (L-SPECT), Adaptive Optics , Computer-Aided Design , Finite Element Analysis , Vibration Analysis , and Image Processing . His work bridges theoretical engineering concepts with practical medical applications, developing novel imaging techniques that can operate through challenging environments and media. His research has significant implications for both defense applications and medical diagnostics. An analysis of Dr. Tahtali's recent publications reveals a strong trend toward integrating machine learning techniques with traditional engineering approaches. His work spans medical imaging innovations, structural health monitoring using vibration analysis, computer vision for challenging environments, and deep learning applications. The interdisciplinary nature of his research connects mechanical engineering principles with computational methods and medical applications, demonstrating consistent innovation across multiple domains. Dr. Tahtali actively supervises research students and offers PhD scholarships ($35,000 per year) for high-achieving students in Computer Science, Electrical Engineering, or Mechanical Engineering. His research group works on cutting-edge problems at the intersection of engineering disciplines, with particular emphasis on medical imaging technologies and computational methods for challenging environments. His laboratory work focuses on developing novel imaging systems, particularly Light Field SPECT technology, as well as computational methods for image restoration through turbulent media. The research team combines experimental work with sophisticated computational modeling to advance imaging capabilities in both medical and defense contexts.

• Machine Learning
• Signal Processing
• Data Science
• +۳ مورد دیگر

Salah Bourennane is a Lecturer and researcher in the Computer Science department at the Fresnel Institute , with a focus on advanced machine learning and multidimensional signal processing techniques. His research interests span: Machine Learning (deep learning, transfer learning, optimization algorithms) Signal Processing (hyperspectral analysis, tensor decomposition, noise reduction) Medical Imaging (diagnostic systems, brain mapping, cancer detection) Computer Vision (face recognition, surveillance systems, 3D verification) Security Applications (mask detection, concealed object classification, steganalysis) Recent publications highlight his work in: Tensor-driven methods for low-resolution face recognition Hybrid multilinear-linear architectures for camera network identification Deep learning frameworks for medical diagnostics (e.g., breast cancer segmentation, Alzheimer's disease mapping) Optimization algorithms (e.g., grey wolf optimizer variants) for sensor systems and image processing Real-time pandemic response technologies like social distance monitoring His work is implemented within the Fresnel Institute research laboratory, specializing in computer vision and data science applications.

• Machine Learning
• Computer Vision
• Distance Metric Learning
• +۴ مورد دیگر

Xiaochen Yang is an Assistant Professor in the Department of Artificial Intelligence at the School of Computer Science and Control Engineering, University of Chinese Academy of Sciences. With a PhD from University College London completed in 2020, Dr. Yang has established a prolific research career spanning machine learning, computer vision, and computational mathematics. Their work bridges theoretical foundations with practical applications across multiple domains. Dr. Yang's research interests focus on advancing machine learning methodologies, particularly in distance metric learning, few-shot learning, and multimodal systems. Their work spans both theoretical aspects of numerical methods for stochastic differential equations and practical applications in computer vision, hyperspectral imaging, and security of large language models. This interdisciplinary approach has led to significant contributions in multiple fields. Analysis of Dr. Yang's recent publications reveals a strong trajectory in developing novel machine learning architectures, with particular emphasis on few-shot learning techniques, multimodal fusion approaches, and applications of diffusion models. Their work demonstrates increasing sophistication in handling complex data modalities while maintaining mathematical rigor, particularly evident in their publications from 2023-2025. Dr. Yang has established productive collaborations across institutions, as evidenced by their extensive co-author network spanning Chinese academic institutions and international partners. Their research has been published in top-tier venues including IEEE Transactions, Pattern Recognition, NeurIPS, and CVPR, reflecting the high impact of their contributions to the field.

Mona Jarrahiمشاهده پروفایل

استاد

• Terahertz Electronics
• Millimeter-wave Optoelectronics
• Microwave Photonics
• +۳ مورد دیگر

Mona Jarrahi is a Professor in the Department of Electrical and Computer Engineering at the Henry Samueli School of Engineering and Applied Science, University of California, Los Angeles (UCLA). Holding the Northrop Grumman Chair in Electrical Engineering, she leads groundbreaking research in terahertz/millimeter-wave electronics, microwave photonics, and AI-driven imaging systems. Terahertz Electronics Millimeter-wave Optoelectronics Microwave Photonics Imaging and Spectroscopy Systems AI-Driven Optical Imaging Her recent publications highlight advancements in terahertz plasmonic focal-plane arrays, single-pixel diffractive terahertz processors, and coherent terahertz synthesis. These works span keywords like Optoelectronics , Signal Processing , and Machine Learning , with sub-fields focusing on Plasmonics , Pixel-level Resolution , and Diffractive Neural Networks . Scientific Awards: Fellow of IEEE, AAAS, APS, Optica, SPIE, and IOP Guggenheim Fellowship SPIE Quantum Sensing Achievement Award IEEE Photonics Society Aron Kressel Award Moore Inventor Fellowship As head of the Terahertz Electronics Laboratory at UCLA, she drives innovations in terahertz technologies with applications in medical imaging, security, and deep-space exploration. Her work includes room-temperature terahertz sensors and photodetectors with 50 GHz speeds.

Art Gleasonمشاهده پروفایل

استاد پژوهشی

• Remote Sensing
• Marine Conservation
• Coral Reef Science
• +۳ مورد دیگر

Art Gleason is a Research Professor at the University of Miami, jointly affiliated with the Department of Physics and Department of Marine Geosciences. His research integrates geophysics, biogeography, and engineering to develop remote sensing tools for environmental conservation. He holds a Master’s degree from the University of Maryland and leads interdisciplinary teams focused on marine technology innovation. His research spans three themes: 1) Satellite product validation (e.g., AVHRR orbital drift correction for net primary production calculations), 2) Marine habitat mapping using hyperspectral/acoustic classification, and 3) Underwater photomosaic technology for coral reef monitoring. His 2020 Pew Marine Fellowship supports advanced applications of photomosaics in coral restoration. Gleason’s publications emphasize coral reef dynamics, optical oceanography, and automated image analysis. Trends include high-resolution mapping, resilience assessment, and technology development for conservation. His collaborative network includes NOAA, Scripps Institute of Oceanography, The Nature Conservancy, and international research groups. Awards & Grants: Pew Marine Fellow (2020) – For advancing underwater mosaic technology in coral reef conservation He directs the Large Area Imaging (LAI) initiative, conducting biweekly office hours and courses on underwater data acquisition. His lab partners with 15+ organizations globally to deploy photomosaic technology for reef science.

Md Alimoor Rezaمشاهده پروفایل

استادیار

• Computer Vision
• Robotics
• Machine Learning
• +۴ مورد دیگر

Md Alimoor Reza serves as an Assistant Professor of Computer Science in the Department of Mathematics and Computer Sciences at Drake University's College of Arts & Sciences. He leads the Computer Vision and Robotics Lab and teaches courses including Introduction to Computer Science, Computer Vision, Machine Learning, and Robotics. His academic journey culminated with a Ph.D. from George Mason University under Professor Jana Kosecka. Ph.D. in Computer Science, George Mason University (Advisor: Jana Kosecka) Professor Reza specializes in computer vision, robotics, and machine learning with applications spanning cognitive science, biology, medical diagnosis, and engineering. His research bridges theoretical advances with practical implementations, particularly in 3D reconstruction, human-robot interaction, and assistive technologies. He has developed novel approaches for multi-view stereopsis, point cloud processing, and semi-automatic annotation tools that have advanced computer vision applications. His publication portfolio reveals a strong focus on solving core computer vision challenges while expanding into interdisciplinary applications. Recent work shows increasing emphasis on accessibility technologies, educational AI applications, and real-world deployment of vision systems. The trajectory demonstrates evolution from foundational geometric computer vision toward more applied, human-centered systems with societal impact. As an educator, Professor Reza has mentored numerous undergraduate and graduate students through research projects, many of whom have won awards at regional computing conferences. His teaching spans introductory programming to advanced machine learning and computer vision topics, with a documented course schedule showing consistent offerings of CS 167 (Machine Learning) and CS 195 (Computer Vision). He directs the Computer Vision and Robotics Research Group at Drake, which maintains active collaborations across disciplines and has produced significant student research output. The lab environment emphasizes both theoretical understanding and practical implementation skills, preparing students for advanced research and industry positions in computer vision fields.

• Dielectric Spectroscopy
• Recycling of Electronic Waste
• Liquid Crystal Characterization
• +۵ مورد دیگر

Pierre-Alexandre Hébert is an Associate Professor at the University of the Littoral Opal Coast. His research spans interdisciplinary domains including dielectric material analysis , electronic waste recycling , and machine learning applications for environmental monitoring. Key research focus: Liquid Crystal recycling from E-waste using dielectric spectroscopy Contributions to phytoplankton detection via automated systems and clustering algorithms Collaborations across France, Turkey, Italy, and Ireland His recent publications (2021-2023) emphasize sustainable materials processing, particularly dielectric characterization of recycled liquid crystals for circular economy applications. Earlier work (2008-2018) showcases expertise in image processing , phytoplankton classification , and data clustering techniques. Collaborative projects include: JERICO NEXT (2018), ISyDMA'6 (2021), and SFGP (2022) conferences. Current affiliations involve laboratories at Université du Littoral Côte d’Opale (ULCO) and Université d’Artois (UA).

Mikael Nilssonمشاهده پروفایل

مدرس ارشد

• Machine Learning
• Computer Vision
• Deep Learning
• +۴ مورد دیگر

Mikael Nilsson is a Senior Lecturer and key member of the Faculty of Engineering (LTH) at Lund University , Sweden. He is affiliated with the Centre for Mathematical Sciences and serves as Programme Director for the international master's program in Machine Learning, Systems and Control since 2019. Education : M.Sc.E.E. and Ph.D. in Applied Signal Processing (2007) from Blekinge Institute of Technology Research Focus : Developing novel Machine Learning models with emphasis on Deep Neural Network Designs Applications in Computer Vision (3D object estimation, traffic safety, radiation therapy) Applied research in Engineering Health and Natural & Artificial Cognition profile areas Recent Research Outputs (2022-2023): Medical imaging segmentation for cancer therapy (Radiation Oncology) Urban traffic surveillance systems (IEEE ITSC) 3D shape estimation from monocular vision Multi-view pose estimation via segmentation masks Yield forecasting using satellite-ground data fusion Key Collaborations : Swedish Government Agency for Innovation Systems (Vinnova) - DAIDESS project (2023-2026) Interdisciplinary work in Engineering Health and Medical Imaging Industrial collaboration with Axis Communications AB (2016-2019)

• Image Processing
• Deep Learning
• Signal Processing
• +۶ مورد دیگر

Adrian Munteanu is a Professor in the Department of Electronics and Computer Science at Free University of Brussels (Vrije Universiteit Brussel). He has been actively contributing to research in image processing, deep learning, and signal processing since 1995, with over 414 research outputs and an h-index of 29. His work spans diverse fields such as video compression, autonomous vehicle pose estimation, greenhouse gas emissions prediction, and real-time distributed video coding.

Sinan KALKANمشاهده پروفایل

استاد

• Computer Vision
• Machine Learning
• Imbalance Problems
• +۲ مورد دیگر

Sinan KALKAN is a full professor at the Department of Computer Engineering , Middle East Technical University (METU) , Ankara, Turkey. He actively contributes to interdisciplinary research at the intersection of Computer Vision, Machine Learning , and Robotics , with a focus on imbalanced learning, bias/fairness, and detection/segmentation tasks. As a member of multiple research centers ( METU Robotics and AI Center , METU Image Processing Lab , COVIG Lab (Denmark) , and BCCN Center (Germany) ), he drives collaborative innovation across Turkey, Denmark, and Germany. Research Interests include: Computer Vision (Object Detection, Segmentation, Recognition) Machine/Deep Learning (Imbalance Problems, Bias and Fairness) Robotics (Human-Robot Interaction, Context Modeling) Recent Article Trends show expertise in: Unified loss functions for detection/classification Uncertainty-aware neural architectures Fairness in affective computing Imbalance mitigation strategies Energy modeling under climate change Transformer-based time-series forecasting Scientific Awards : Best Paper Award, IEEE Transactions on Cognitive and Developmental Systems (2016) Labs and Teams : METU Robotics and AI Center METU Image Analysis Center METU Image Processing Laboratory METU Balance METU Energy Cambridge University AFAR

Yusuf Sahillioğluمشاهده پروفایل

استاد

• Computer Graphics
• 3D Shape Processing
• Geometric Algorithms
• +۳ مورد دیگر

Professor Yusuf Sahillioğlu is a faculty member in the Computer Engineering Department at Middle East Technical University (METU), Faculty of Engineering, specializing in computer graphics and geometric processing. His academic journey includes a BS from Bilkent University, MS from University of Florida, and PhD from Koç University, followed by postdoctoral work at Koç University and University of Pennsylvania. His research focuses on 3D shape correspondence , deformation algorithms , deep learning for 3D data , and geometry processing . Key contributions include novel methods for isometric shape matching, topologically-stable correspondence, and real-time secondary animation. His recent work integrates deep learning with traditional geometric approaches for mesh segmentation, point cloud classification, and 3D scene extrapolation. His 15 most recent publications (2021-2025) reveal a strong trend toward real-time geometric algorithms (e.g., spring-decomposed skinning), kernel computation for mesh processing, and deep generative models for 2D-to-3D conversion. The research consistently bridges theoretical geometry with practical applications in animation, reconstruction, and medical imaging. Award highlights include: METU Academic Performance Award (2018) METU Young Scientist Awards (2015-2017) TÜBİTAK 1001 Grants (2016, 2020, 2024) for 3D content analysis, shape matching, and reconstruction TÜBİTAK 3501 Career Grant (2015) for virtual medicine applications He teaches core courses including Data Structures, Operating Systems, Computer Graphics, and Advanced Digital Geometry Processing. His lab focuses on geometric algorithms with applications in medical imaging, animation, and 3D printing, maintaining strong industry and international collaborations through projects like TÜBİTAK-funded initiatives.

Anastasia Angelopoulouمشاهده پروفایل

مدرس ارشد

• Computer Vision
• Machine Learning
• Human-Computer Interaction
• +۵ مورد دیگر

Anastasia Angelopoulou is a Senior Lecturer (equivalent to Associate Professor) at the School of Computer Science and Engineering, University of Westminster , since 2005. She co-leads the Health and Social Care Modelling research group , focusing on AI systems for real-time healthcare and sustainable cities. A Fellow of the UK Higher Education Academy (FHEA) and certified STEM Ambassador, she bridges academia and industry with 5+ years of experience in image processing and software development across the UK and Greece. Research Interests: Computer Vision, Sign Language Recognition, Brain-Computer Interfaces, and Machine Learning for healthcare and sustainable systems. Grants: £65,173 from Dunhill Medical Trust for AI-based dementia diagnosis in deaf populations; NVIDIA GPU grant for depth map research; Heritage Lottery Fund grants for storytelling and health projects. Publications: 50+ works in Tier-1 journals (e.g., Neural Networks , Neurocomputing ) and top conferences (ICCV, ECCV, IJCNN). Awards: Elsevier Outstanding Review Status (2016); Westminster Teaching Excellence Team Award (2017). Her work emphasizes ethical AI, self-learning algorithms, and multimodal systems for diverse applications including clinical investigation and cultural heritage.