جست‌وجوی استاد و پژوهشگر

• Multimedia Signal Processing
• Light Field Coding
• 3D Holoscopic Video
• +۷ مورد دیگر

Paulo Jorge Lourenço Nunes is an Associate Professor in the Department of Information Science and Technology at ISCTE – Instituto Universitário de Lisboa, where he also serves as Coordinator of the Multimedia Signal Processing Group at the Institute of Telecommunications - IUL. He is an Integrated Researcher at the same institute, contributing to advanced research in multimedia and signal processing. PhD in Electrical and Computer Engineering, Higher Technical Institute - UTL (2007) Master's in Electrical and Computer Engineering, Higher Technical Institute - UTL (1995) Bachelor's in Electrical and Computer Engineering, Higher Technical Institute - UTL (1992) His research focuses on multimedia signal processing , particularly in light field coding , 3D holoscopic video , and scalable video representation . He applies deep learning and advanced signal processing techniques to problems in immersive systems and image compression. His work bridges theoretical innovation with practical implementation in next-generation visual media. The recent articles highlight a strong trend in light field processing , including segmentation, coding, disparity estimation, and view synthesis using neural networks. Keywords across publications include computer vision, image compression, deep learning, and immersive media, reflecting a cohesive and impactful research trajectory in next-generation visual technologies. Notable scientific contributions include highly cited works in IEEE Transactions and Signal Processing journals, with over 1300 citations on Google Scholar. While no formal awards are listed, his extensive publication record and leadership in funded research projects underscore significant recognition in the field. He actively supervises postdoctoral researchers, PhD, and Master’s students. His advising portfolio includes ongoing and completed theses on light field coding, deep learning for immersive systems, and multimedia communication. He has also secured and led multiple research projects in multimedia and telecommunications. His teaching includes courses such as Multimedia Communication Systems and Fundamentals of Computer Networks. He leads the Multimedia Signal Processing Group at the Institute of Telecommunications - IUL, a research team focused on advanced multimedia analysis, compression, and delivery. The group works on cutting-edge topics including light field technologies, error-resilient video coding, and machine learning for multimedia.

Liuxi Xingمشاهده پروفایل

پژوهشگر

• Biomedical Engineering
• Medical Microrobots
• Magnetic Microswimmers
• +۳ مورد دیگر

Liuxi Xing is a Researcher at the Institute for Quantitative Health Science & Engineering within the College of Engineering at Michigan State University. Their work focuses on the development of magnetic microrobots and microagent systems for biomedical applications, including targeted therapy, cartilage regeneration, and cell delivery. They specialize in designing magnetic control systems, microscale robotics, and automated navigation techniques for dynamic environments. Research interests include biomedical engineering, robotics, magnetic microswimmers, and adherent cell manipulation. Notable contributions involve engineering magnetotactic bacteria as medical microrobots and creating decellularized magnetic carriers for stem cell delivery. Their methodologies often integrate deep learning and image-guided motion planning to enhance precision in microscale systems. Key technologies developed include rotating gradient magnetic fields for microagent control, dual-module microinjection systems, and automated 3D electromagnetic manipulation. These innovations address challenges in targeted drug delivery, tissue engineering, and minimally invasive medical procedures. No scientific awards are explicitly mentioned. Their research involves collaborations across disciplines, leveraging robotics, materials science, and biomedical engineering to advance therapeutic and diagnostic tools.

Ola Ringdahlمشاهده پروفایل

دانشیار

• Robotics
• Artificial Intelligence
• Machine Learning
• +۶ مورد دیگر

Ola Ringdahl is an Associate Professor at the Department of Computer Science, Umeå University, specializing in robotics for agriculture and forestry. He serves as the Director of the MSc program in AI and teaches multiple courses. Research Group: Intelligent Robotics Affiliation: Umeå University, Department of Computer Science His research focuses on developing novel artificial intelligence and machine learning algorithms for autonomous and semi-autonomous robotic navigation, industrial manipulator path planning using 3D localization, and perception algorithms for semantic data extraction from sensors. Projects include EU initiatives Sweeper and CROPS for fruit harvesting robots. Publications highlight applications in precision agriculture/forestry and sensor fusion. Recent publications analyze advancements in agricultural robotics using machine learning, human-robot interaction via multi-camera systems, and grape vine detection with RGB-D data. The majority of his work addresses outdoor environments and sensor-driven decision-making in autonomous systems. Key Collaborators: Polina Kurtser, Thomas Hellström, Yael Edan Ola leads the Intelligent Robotics group and has participated in long-term projects like PRECISION (2018-2021), SOCRATES (2016-2020), Sweeper (2015-2018), and CROPS (2010-2014). His work combines academic research with practical implementation in real-world agricultural and forestry settings.

Maria Chizhovaمشاهده پروفایل

استادیار

• Digital Heritage Technologies
• 3D Reconstruction
• Photogrammetry
• +۵ مورد دیگر

Maria Chizhova is an Assistant Professor in Digital Technologies in Heritage Conservation at the University of Bamberg's Centre for Heritage Conservation Studies and Technologies (KDWT). She holds a Dr.-Ing. degree from Technical University of Munich and has a Dipl. Eng. in Surveying from State Academy of Agriculture in Ivanovo. Doctorate: 2014-2019, Technical University of Munich (Civil, Geo and Environmental Engineering) Diploma: 2006-2011, State Agricultural Academy in Ivanovo Her research focuses on 3D digitalization, photogrammetry, laser scanning, and AI applications for heritage conservation. Key projects include VRScan3D (virtual laser scanner simulator), GeoRek (geodetic methods in Ukraine), and VirScan3D (3D reconstruction of historical objects). She has developed automated systems for timber structure analysis and orthodoxy church reconstruction. Recent publications show expertise in 3D simulation , point cloud segmentation , and multi-sensor integration . She has held research fellowships at Technical University of Warsaw, Fondazione Bruno Kessler (Italy), Carleton University (Canada), and Michigan Tech University (USA). DAAD-funded VRScan3D project (2019-2021) Research on Jewish cemeteries in Franconia Developed methodologies for historic timber analysis Her work combines machine learning , Bayesian networks , and cellular automata for heritage documentation, with applications in digital twins and mixed reality environments.

Pieter Peersمشاهده پروفایل

دانشیار

• Relighting
• Appearance Modeling
• Neural Rendering
• +۷ مورد دیگر

Pieter Peers is an Associate Professor in the Department of Computer Science at the College of William & Mary. Prior to this, he was a senior researcher at the Graphics Laboratory at the University of Southern California's Institute for Creative Technologies and a Research Assistant Professor at USC's Viterbi School of Engineering. His educational background includes a Ph.D. in Computer Science from K.U.Leuven (Belgium) in 2006 and a BS/MS in the same field from the same institution in 2000. Peers' research focuses on relighting, appearance modeling, and neural rendering—central topics in computer graphics and vision. His work bridges traditional rendering techniques with modern deep learning, particularly in inverse rendering, material modeling, and image-based relighting. He has made significant contributions to subsurface scattering, photometric stereo, and neural rendering systems. His recent publications, including work in SIGGRAPH, CVPR, and ICCV, demonstrate a strong trend toward integrating diffusion models and transformer architectures into appearance modeling and relighting tasks. These works often address real-world challenges such as single-image relighting, material estimation, and lighting control with minimal user input. RenderFormer (SIGGRAPH 2025): Transformer-based neural rendering with global illumination. ScribbleLight (CVPR 2025): Scribble-driven indoor relighting using diffusion models. MatFusion (SIGGRAPH Asia 2023): Diffusion-based SVBRDF capture. He has mentored and collaborated with numerous students and researchers, including Chong Zeng, Jun Myeong Choi, and James Bieron, indicating active involvement in advising and research supervision. While no formal grants or awards are listed, his consistent publication record in top venues suggests sustained research funding and recognition in the graphics community. Peers has led research in advanced rendering systems, including work on compressive light transport sensing, wavelet environment matting, and compact representations of heterogeneous subsurface scattering. His early work at USC and K.U.Leuven laid the foundation for his current research in neural appearance modeling and inverse rendering.

Disi Chenمشاهده پروفایل

مدرس

• Machine Vision
• Machine Learning
• Robotics
• +۵ مورد دیگر

Dr. Disi Chen is a Lecturer in Robotics and Machine Vision at the Faculty of Environment and Technology (FET), University of the West of England, Bristol. He is affiliated with the Centre for Machine Vision (CMV) and Bristol Robotics Laboratory (BRL). BEng in Mechanical Engineering MEng in Engineering PhD in Probabilistic Framework for Human-Robot Skill Transfer (University of Portsmouth) His research focuses on Machine Vision , Machine Learning , and Robotics , with specific expertise in human-robot skill transfer, gesture recognition, and surface electromyography (sEMG) signal processing. He has developed novel frameworks like the Curved Gaussian Mixture Model (CGMM) and Virtual Reality systems for intuitive skill demonstration perception. Disi Chen's publications emphasize gesture recognition , sEMG signal analysis , and robotic control systems , often integrating deep learning , image segmentation , and human-computer interaction . His work spans applications in prosthetic limbs , rehabilitation robotics , and urban computing . He is part of the Centre for Machine Vision and Bristol Robotics Laboratory , collaborating with institutions like the University of Portsmouth and Wuhan University of Science and Technology. His teaching includes modules on Machine Vision and Robotics .

• Artificial Intelligence
• Neuro-Symbolic Integration
• Knowledge Graphs
• +۴ مورد دیگر

Luciano Serafini is a researcher at Fondazione Bruno Kessler in Trento, Italy, specializing in Artificial Intelligence with a focus on Neuro-Symbolic Integration and Knowledge Graphs . His work bridges Machine Learning and Symbolic Reasoning , emphasizing Planning , Relational Learning , and Visual-Textual Grounding . Key Research Areas : Neuro-symbolic systems, logic-based knowledge representation, planning under uncertainty, and computer vision. Recent Publications highlight trends in Embodied AI for open-world tasks, Weighted Model Counting , and Graph Generative Models . His contributions include Logic Tensor Networks for integrating deep learning with formal logic and methods to mitigate Data Sparsity through knowledge transfer. Collaborations span institutions like the University of Trento and research teams in Computer Vision and Reasoning , with applications in Social Navigation and Event Recognition .

Arkadiusz Tomczykمشاهده پروفایل

پژوهشگر

• Image Analysis
• Machine Learning
• Computer Vision
• +۵ مورد دیگر

Arkadiusz Tomczyk is a researcher at the Institute of Information Technology of the Lodz University of Technology , where he has worked since 2002. His academic career focuses on image processing , machine learning , and computer vision , with notable contributions to active contour methods and graph neural networks . He has led and collaborated on multiple funded projects, including a National Science Centre grant (2013-2017) on Cognitive Hierarchical Active Partitioning. Education: MSc in Computer Science (2002), PhD in Computer Science (2011) from Lodz University of Technology His research spans convolutional neural networks , transformers , and graph neural networks , with applications in medical imaging and natural image analysis . Recent work emphasizes structured prediction and explainability in attention mechanisms for chemical molecule analysis. Tomczyk contributes to applied machine learning in projects like METERNET-EnMS (energy management) and FIF (edge devices for zero-emission goals). He teaches object-oriented programming , deep learning , and supervises laboratory infrastructure projects.

Gabriel Taubinمشاهده پروفایل

استاد

• Applied Computational Geometry
• Computer Graphics
• Geometric Modeling
• +۲ مورد دیگر

Gabriel Taubin is a Professor of Engineering and Computer Science at Brown University. He holds a PhD in Electrical Engineering from Brown (1991) and a Licenciado en Ciencias Matemáticas from the University of Buenos Aires (1981). Previously, he worked at IBM Research (1990-2003) as a Research Staff Member and Manager. Education: PhD in Electrical Engineering, Brown University (1991); Licenciado en Ciencias Matemáticas, University of Buenos Aires (1981). His research spans Applied Computational Geometry, Computer Graphics, Geometric Modeling, 3D Photography, and Computer Vision , focusing on algorithms for 3D object representation, low-cost 3D scanning, and digital fabrication. Key contributions include 3D mesh processing, camera networks, and surface reconstruction techniques. Recent publications emphasize 3D scanning for printing , super-resolution imaging , and geometric optimization . His work has been cited in ACM Transactions on Graphics , IEEE Transactions on Pattern Analysis , and interdisciplinary journals. Scientific Awards: IEEE Fellow (2001), Fulbright Specialist (2014), IBM Master Inventor (2001), Eurographics Best Paper (2002), Best Poster (ICDP 2011).

Udo Freseمشاهده پروفایل

استاد

• Computer Vision
• Robotics
• Sensor Fusion
• +۳ مورد دیگر

Professor Udo Frese is a faculty member at the University of Bremen, holding the position of Professor of Multisensory Interactive Systems since March 2014. He is associated with the German Research Center for Artificial Intelligence (DFKI) in the Cyber-Physical Systems department and is a member of the research focus 'Minds, Media, Machines'. University of Paderborn (1993-1997): Computer Science Friedrich-Alexander University Erlangen-Nuremberg (2004): Doctorate Professor Frese's research focuses on computer vision, sensor fusion through probabilistic modeling, and algorithms for safety functions with applications in robotics and interaction. His work spans multiple domains including assistive robotics for people with mobility limitations, SLAM (Simultaneous Localization and Mapping) techniques, and human-robot interaction systems. His research group collaborates with DFKI to operate the robot soccer team B-Human, which has achieved remarkable success with multiple world championships. His recent publications demonstrate a strong focus on assistive robotics, with particular emphasis on adaptive control systems for users with limited mobility. His work integrates computer vision, machine learning, and human-centered design principles to develop practical assistive technologies. The research spans from theoretical foundations in probabilistic modeling to practical implementations in real-world assistive applications. Best Technical Paper award at PETRA '24 for 'Probabilistic Combination of Heuristic Behaviors for Shared Assistive Robot Control' Best paper award at EICS 2024 for 'AdaptiX – A Transitional XR Framework for Development and Evaluation of Shared Control Applications in Assistive Robotics' Multiple world championships with robot soccer team B-Human Professor Frese advises several doctoral and master's students including Felix Goldau, Max Pascher, and Moritz Schneider, who contribute significantly to his research in assistive robotics and computer vision. His research is supported through collaborations with DFKI and various projects focused on assistive technologies and robotics. His laboratory at the University of Bremen collaborates closely with DFKI's Cyber-Physical Systems department, operating the successful robot soccer team B-Human. The research group maintains strong connections with both academic and industry partners to advance research in robotics and human-computer interaction.

Rainer Lienhartمشاهده پروفایل

استاد

• Computer Vision
• Machine Learning
• Deep Learning
• +۵ مورد دیگر

Rainer Lienhart is a tenured Professor at the University of Augsburg, where he holds the Chair for Machine Learning & Computer Vision within the Faculty of Applied Computer Science's Institute of Computer Science. He has served as the executive director of the Institute for Computer Science since April 2010. His research group, the Machine Learning and Computer Vision Lab (MLCV Lab), focuses on large-scale image, video, human pose, sensor and data mining algorithms; object, human pose and action detection/recognition; and image, video, human pose and action retrieval. Dr. Lienhart received his PhD in Computer Science from the University of Mannheim, Germany in 1998. Prior to joining the University of Augsburg, he worked as a Staff Researcher at Intel's Microprocessor Research Lab in Santa Clara, California from August 1998 to July 2004. He has also taken sabbaticals at FXPAL (August 2017 to March 2018) and Willow Garage (2009). His research spans multiple areas of computer vision and machine learning with particular emphasis on object detection/recognition, human pose estimation, image/video captioning, automated visual inspection, medical image analysis, deep learning, statistical computing, and explainable AI. His work on multimedia data mining and signal processing has led to significant contributions in video content analysis, including text detection/recognition, commercial detection, face detection, shot and scene detection, and automatic video abstraction. The publication record shows a consistent research trajectory focusing on human pose estimation, winter sports analysis, scene graph generation, and segmentation techniques, with recent work emphasizing transformer-based architectures, 3D pose estimation, and physics-informed computer vision approaches. His research demonstrates a strong interdisciplinary focus, connecting computer vision with sports science, medical applications, and multimedia content analysis. Prof. Lienhart has served as general co-chair of ACM Multimedia 2017 and 2007, as well as SPIE Storage and Retrieval of Media Databases 2004 and 2005. He has served on editorial boards of three international journals and was vice chair of SIGMM from July 2009 to June 2017. His professional service includes committee membership for major conferences including ACM Multimedia, IEEE ICME, and SPIE Storage and Retrieval of Media Databases. His laboratory, the MLCV Lab, maintains an active research program with numerous collaborators and students working on cutting-edge computer vision problems. Current research directions include human pose estimation in sports contexts, winter sports equipment segmentation, scene graph generation, and medical image analysis applications.

Leticia Arco Garciaمشاهده پروفایل

پژوهشگر

• Natural Language Processing
• Complex Networks
• Deep Learning
• +۵ مورد دیگر

Leticia Arco Garcia is a postdoctoral researcher at Vrije Universiteit Brussel working in the Department of Informatics and Applied Informatics with affiliations at Federated Labs AI and Robotics. Her research spans computational linguistics, complex network analysis, and more recently, interdisciplinary applications in archaeobotany. Her research interests focus on Natural Language Processing , Complex Networks , and Deep Learning methodologies. Early work centered on community detection in complex networks and customer behavior analysis, while recent publications demonstrate expansion into archaeobotanical applications using morphometric analysis of phytoliths. She employs advanced computational techniques including LSTM networks, case-based reasoning, and multi-objective optimization across diverse domains from smart power grids to electronic money systems. Analysis of her 15 most recent publications reveals an interdisciplinary trajectory moving from pure computer science applications toward biological/archaeological domains. The earliest works focus on network construction and community detection, while more recent papers apply similar analytical frameworks to botanical specimens, indicating methodological transfer between fields. Her work consistently applies computational rigor to complex data structures across diverse application areas. Her scientific contributions include: Development of novel network construction methodologies for large purchasing collections Advancements in overlapping community detection using rough clustering Application of deep learning to sentiment analysis and customer behavior prediction Recent innovative work applying morphometric analysis to archaeobotanical specimens Dr. Garcia actively presents her research at international conferences including INTERSPEECH and specialized meetings on phytolith research. Her collaborative network spans multiple institutions, with co-authorship on interdisciplinary projects connecting computer science with archaeology and plant science. While specific grant information isn't detailed in the available text, her consistent publication output across multiple domains suggests successful research funding.

David Mendlovicمشاهده پروفایل

استاد

• Optical interconnection networks
• Dynamic optical switches
• Temporal optics
• +۱۵ مورد دیگر

Prof. David Mendlovic is a Full Professor of electro-optics at the School of Electrical Engineering, The Iby and Aladar Fleischman Faculty of Engineering, Tel Aviv University. With a career spanning decades, he has established himself as a leading figure in optical engineering and signal processing, holding significant leadership positions including head of TAU Innovation Labs and board member of the Israel Innovation Authority (IIA). His academic journey began and continued at Tel Aviv University where he earned both B.Sc. and Ph.D. degrees in Electrical Engineering. His professional trajectory includes serving as Chief Scientist of the Israeli Ministry of Science (2008-2010), Co-Chair of the German Israeli Foundation for 6 years, and Vice Dean for Research of the Faculty of Engineering for a decade. Prof. Mendlovic's research spans computational photography for miniature imaging systems, advanced 3-D sensing, AI-based image processing, authentication systems, optical bio-sensing, and deep-fake detection. His work has produced worldwide breakthroughs including hollow fibers for IR transmission, extended depth of field imaging, multi-aperture camera systems, and innovations in the fractional Fourier transform. His recent publications demonstrate continued innovation with emphasis on thermal imaging applications for precision agriculture, dynamic identity authentication, light field photography, and advanced image processing leveraging deep learning approaches across computer vision, optical engineering, and thermal imaging domains. 1998 winner of ICO International Prize in Optics Ernst Abbe Medal by Carl Zeiss Fellow of The Optical Society of America Prof. Mendlovic has successfully translated research into commercial applications through multiple startups including Civcom (acquired by Padtec S/A of Brazil) and Eyesquad (acquired by Tessera Inc, later acquired by Samsung). He has mentored numerous graduate students with thesis topics spanning optical signal processing, diffractive optical elements, and imaging systems. His laboratory work bridges theoretical developments with practical implementations across security, healthcare, agriculture, and consumer electronics applications.

• Robotics
• Precision Agriculture
• Vehicle Dynamics
• +۵ مورد دیگر

Giulio Reina serves as a Full Professor in the Department of Mechanics, Mathematics and Management at the Polytechnic University of Bari, Italy. His academic focus centers on robotics and mechanical systems with strong applications in agricultural automation and vehicle dynamics. His research spans Robotics , Precision Agriculture , and Vehicle-Terrain Interaction Modeling . Key contributions include developing path-planning frameworks for agricultural robots, deformable tire models for obstacle negotiation, and yield estimation systems using deep learning in viticulture. His work integrates mechanical engineering principles with AI-driven solutions for field robotics applications. Analysis of his recent publications reveals a strong emphasis on mobile robotics for agricultural automation , particularly in grapevine monitoring and terrain interaction. His research bridges theoretical modeling (e.g., multibody dynamics) with practical implementations in off-road vehicles and farmer robots, consistently addressing challenges in precision agriculture through sensor fusion and machine learning. No specific scientific awards were documented in the provided materials. Professor Reina leads research in agricultural robotics without explicit mention of formal student advising in the source text. His work demonstrates significant focus on practical implementations for sustainable farming, including terrain estimation systems and autonomous navigation solutions for uneven agricultural environments. His laboratory activities center on agricultural robotics development, featuring projects like the SNAP lightweight vehicle platform and POLYPUS adaptive gripper systems. Current initiatives emphasize real-world deployment of farmer robots for crop monitoring and precision viticulture applications.

Serap ÇAKAR KAMANمشاهده پروفایل

استادیار

• Computer vision
• Deep learning
• Object detection
• +۶ مورد دیگر

Serap ÇAKAR KAMAN is an Assistant Professor at Sakarya University's Faculty of Computer and Information Sciences, Department of Computer Engineering. She has maintained a continuous academic career at the university since 2000, progressing from Research Assistant to Lecturer and finally to Assistant Professor. Her educational background includes: Doctorate in Electrical Engineering (2003-2009) from Sakarya University Institute of Science with thesis on "DIGITAL IMAGE WATERMARKING METHODS BASED ON MOMENT-BASED NORMALIZATION" Master's in Computer and Information Engineering (2000-2003) from Sakarya University Institute of Science with thesis on "DETECTING, TRACKING AND TARGET IDENTIFICATION OF OBJECT MOVEMENTS ON VIDEO IMAGES" Bachelor's in Electrical-Electronics Engineering (1996-2000) from Sakarya University Faculty of Engineering Dr. ÇAKAR KAMAN's research spans multiple domains within computer vision and artificial intelligence, with particular expertise in object detection, deep learning applications, and image processing. Her work bridges theoretical computer vision with practical applications in industrial automation, medical imaging, and electric vehicle technology. She has made significant contributions to metal surface defect detection, autonomous charging systems, and facial expression recognition for healthcare applications. Her research demonstrates a consistent pattern of applying advanced computer vision techniques to solve real-world problems across diverse domains. Analysis of her publication trends reveals a clear evolution from foundational work in digital image watermarking to cutting-edge applications of deep learning in industrial settings. Her recent publications (2023-2025) focus on practical implementations in agricultural technology (hazelnut kernel analysis), business intelligence (employee feedback analysis), and marine infrastructure (shore-to-ship charging). The consistent thread through her research is the development of robust computer vision algorithms that enhance automation and precision in various technical contexts. With an H-index of 4 in Web of Science and 114 citations, Dr. ÇAKAR KAMAN maintains an active research profile. Her academic contributions include teaching in the Department of Computer Engineering and likely supervision of graduate students, though specific student information isn't documented in the available materials. Her work contributes significantly to Sakarya University's research profile in computer engineering and supports Turkey's growing expertise in artificial intelligence applications. Her laboratory work appears to focus on computer vision systems with emphasis on real-time processing applications. The research groups she participates in likely include teams working on industrial automation, electric vehicle infrastructure, and medical image analysis, though specific team structures aren't detailed in the available information.