جست‌وجوی استاد و پژوهشگر

• Computer Vision
• 3D Reconstruction
• SLAM
• +۵ مورد دیگر

Victor Adrian Prisacariu is an Associate Professor of Engineering Science at the University of Oxford. He holds a BSc from Gheorghe Asachi Technical University, Iasi, Romania, and a DPhil from Oxford. Previously, he served as an EPSRC Postdoctoral Researcher and Dyson Senior Research Fellow. His current research focuses on real-time computer vision techniques for AR/VR on mobile platforms, with emphasis on semantic visual tracking, 3D reconstruction, and SLAM. He co-founded 6D.ai (acquired by Niantic), developing crowdsourced 3D mapping technologies. He leads the Active Vision Lab, which explores computational vision applications in robotics, wearable computing, and navigation. His work bridges academia and industry, emphasizing scalable solutions for real-world AR/VR challenges. Education : BSc (First Class Honors) in Computer Engineering, Gheorghe Asachi Technical University (2008) DPhil in Engineering Science, University of Oxford (2012) Research Interests : AR/VR system optimization for mobile and wearable devices Real-time 3D reconstruction and semantic mapping SLAM algorithms for navigation and localization Computer vision techniques for scene understanding and object tracking Industry-academia collaboration in AR/VR technologies Key Projects : Active Vision Lab Code Repository (AVLCode) 6D.ai SDK (Niantic's real-time 3D semantic mapping) Development of Gaussian splatting techniques for efficient 3D rendering Awards & Recognition : Contributions acknowledged in CVPR 2025 Best Paper Award (group recognition) Lab & Teams : The Active Vision Lab collaborates on projects like 3D reconstruction, visual localization, and AR system development. His work integrates academic rigor with industry-driven applications through partnerships like Niantic.

Yichao Shiمشاهده پروفایل

مدرس

• Computational Design
• Parametric Design
• Shape Grammars
• +۶ مورد دیگر

Yichao Shi is a doctoral student and Instructor in the Architecture Design Computation program at Georgia Institute of Technology (Georgia Tech). He holds an M.S.Arch. in Design Computation from Georgia Tech, an M.Arch. in Architectural Design from University College London (UCL), and a B.Eng. in Architectural Engineering from Tongji University. His research focuses on computational tools in architectural design, including shape grammars, digital heritage, and AI integration with tools like Stable Diffusion and Midjourney. He explores applications in cultural preservation, parametric design, and human-computer interaction. Key research areas include generative adversarial networks (GANs), interactive architectural design systems, and parametric modeling of traditional architectural elements (e.g., Chinese Dougong brackets). His work bridges computational methods with cultural and historical contexts, addressing challenges in urban planning, disaster resilience, and mental health through AI-driven solutions. Yichao’s publications span topics from AI-assisted sound therapy systems for older adults to automated generative design in archaeological reconstruction. His 2022 work on shape-changing architectural modules highlights innovations in robotic actuation and adaptive structures. Though no academic awards are listed, his interdisciplinary approach reflects a commitment to advancing computational design methodologies.

• Computer Vision
• Artificial Intelligence (AI)
• Distributed Ledger Technology (DLT)
• +۵ مورد دیگر

John Collomosse is a Professor of Computer Vision and AI at the University of Surrey, leading DECaDE (UKRI/EPSRC Centre for the Decentralised Digital Economy) and the Centre for Vision, Speech and Signal Processing (CVSSP). He also serves as a Principal Scientist at Adobe Research, managing the Cross-Modal Representation Learning (XRL) group. His research focuses on AI, Distributed Ledger Technology (DLT), media provenance, and blockchain applications to combat misinformation and enhance data integrity. Collaborations include the Content Authenticity Initiative (CAI) and the ARCHANGEL project, which pioneered AI and blockchain for tamper-proof archives. He holds a PhD, is a Fellow of the IET, and has advised UK/EU bodies on digital economy policies. His work bridges academia and industry, with contributions to generative AI, watermarking, and decentralized systems. Publications span content authenticity, style transfer, and generative models. Awards include a 2024 prestigious fellowship. His labs include Surrey Institute for People-Centred AI (PAI) and DECaDE, fostering interdisciplinary research in AI ethics, provenance, and digital economy frameworks.

Jean-Yves Guillemautمشاهده پروفایل

مدرس ارشد

• 3D Computer Vision
• 3D Reconstruction
• Computational Photography
• +۴ مورد دیگر

Dr. Jean-Yves Guillemaut is a Senior Lecturer in 3D Computer Vision and Postgraduate Research Director at the Centre for Vision, Speech and Signal Processing (CVSSP) within the School of Computer Science and Electronic Engineering at the University of Surrey. His research focuses on 3D reconstruction of complex dynamic scenes, particularly addressing challenges with glossy materials and uncontrolled outdoor environments. He collaborates with industry to apply his work in AR/VR, immersive content production, and free-viewpoint video. Education: He holds an MEng (hons), PhD, and is a member of professional bodies including MIEEE, MBMVA, and FHEA. His technical expertise spans computational photography, lightfield imaging, and artificial intelligence. Current PhD students: Matthew Bailey, Yue Zhang, Gianmarco Addari Laboratory affiliations: CVSSP Research interests include scene modeling from multi-view video, dynamic scene reconstruction, and applications in creative industries. Recent projects involve developing algorithms for illumination estimation, pedestrian tracking, and neural rendering. Grants and collaborations are centered on industry partnerships enhancing creative technology sectors. Future work aims to expand outdoor scene modeling and AI-driven medical imaging applications.

• Robotics
• Algorithmic Automation
• Simulation
• +۳ مورد دیگر

Prof. AF (Frank) van der Stappen is a Professor of Robotics and Automation at Utrecht University's Faculty of Science, Department of Information and Computing Sciences. He also holds a position at University College Roosevelt. His research focuses on robotics (grasping, manipulation, motion), algorithmic automation, simulation, computational geometry, and computer animation. He has been an IEEE Fellow since 2017. His work emphasizes geometric computing and its applications in automation, with contributions to form-closure grasping, path planning, and virtual character animation. Education: PhD in Motion Planning from Utrecht University (1994), MSc in Distributed Data Structures from Eindhoven University of Technology (1988). Research Interests: Robotics (manipulation/grasping), algorithmic automation, geometric algorithms, computer animation, and crowd simulation. His work bridges theoretical foundations with practical applications in manufacturing, virtual environments, and agricultural robotics. Awards: IEEE Fellow (2017). Advisees/Grants: No explicitly listed students, but extensive collaborative work with researchers like Elon Rimon, Ken Goldberg, and Mark Overmars. His research includes grants related to motion planning, caging, and automation. Labs/Teams: Involved in geometric computing and robotics teams at Utrecht University, contributing to Game Research themes and interdisciplinary projects.

Chinmay Hegdeمشاهده پروفایل

دانشیار

• Machine Learning
• Algorithms
• Big Data
• +۶ مورد دیگر

Chinmay Hegde is an Associate Professor at the Tandon School of Engineering, NYU, with a joint appointment in Computer Science and Electrical Engineering. His research focuses on machine learning, signal processing, and their applications in cybersecurity, imaging, and materials science. He leads the DICE Lab, exploring data-driven solutions for complex engineering problems. Previously, he held positions at Iowa State University and MIT. Education: Ph.D. in Electrical and Computer Engineering, Rice University (2012) M.S. in Electrical and Computer Engineering, Rice University (2010) B.Tech. in Electrical Engineering, IIT Madras (2006) Research Interests: Machine Learning, Algorithms, Big Data, Signal Processing, Generative Models, Scientific Computing. Awards: NSF CAREER Award (2018-2023) NeurIPS Top Reviewer Award (2019) MRS Open Data Challenge Award (2019) Ralph Budd Award for Best Thesis (2013) Labs & Teams: Director of the DICE Lab, collaborating with industry partners on projects like real-time deepfake detection (GOTCHA), generative models for microstructure design, and AI-driven materials science.

• Cognition-Aware Systems
• Intelligent Reading Interfaces
• Digital Health
• +۳ مورد دیگر

Dr. Tilman Dingler is an Associate Professor in the Knowledge and Intelligence Design (KInD) section at the Faculty of Industrial Design Engineering (IDE), Delft University of Technology. He holds a PhD in Computer Science from the University of Stuttgart and has held roles at the University of Melbourne and Osaka Prefecture University. His research focuses on cognition-aware systems, intelligent reading interfaces, and digital health technologies. He is an expert in designing systems that adapt to cognitive states to enhance information processing and mitigate biases. Education: PhD in Computer Science, University of Stuttgart (Germany) Master of Science in Web Science, University of San Francisco (USA) Honours Degree in Technology Management, University of Munich (Germany) Research Interests: Cognition-Aware Systems: Sensing cognitive states like attention and alertness Bias-Aware Systems: Detecting and mitigating cognitive biases in decision-making Digital Health: Proactive monitoring systems for chronic disease management Intelligent Reading Interfaces: Enhancing readability and reading habits Article Trends: Recent work explores interventions to reduce social media addiction, AI-generated content for non-native readers, and tools for analyzing 360° video. His studies often bridge HCI, AI ethics, and health tech. Awards: Wolfgang Heilmann Award (twice) Fulbright Scholar Grants & Collaborations: Secured funding from NHMRC and Japan Science and Technology Agency. Leads projects like ODECO (Open Data Ecosystem) and SmartHeart (home-based heart failure monitoring). Labs & Teams: Active in IDE’s Human-Centred AI and Sustainable Design Engineering groups. Co-founded the SIGCHI Melbourne Local Chapter.

Usman Alimمشاهده پروفایل

دانشیار

• Computer Graphics
• Visualization Techniques
• Volume Rendering
• +۶ مورد دیگر

Usman Alim is an Associate Professor in the Department of Computer Science at the University of Calgary, and Director of the Data Science Program. He holds a dual Bachelor's in Mathematics and Physics from the University of Rochester (2001), an M.Sc. in Computer Science from Rochester Institute of Technology (2007), and a Ph.D. in Computer Science from Simon Fraser University (2012). His research focuses on global illumination, physically-based modeling, and signal processing applications in computer graphics and visualization. He is particularly noted for innovations in volume visualization, VR interfaces, and haptic systems. Key research areas include: Interactive visualization systems for multivariate data Uncertainty visualization in geological and medical datasets Efficient rendering techniques for large-scale datasets Low-code frameworks for data workflow automation Notable achievements include winning the 2019 IEEE SciVis Contest's Best Report Cover and multiple awards in Compute Canada's Visualize This contest. His work bridges theoretical foundations with practical applications in fields like environmental science, healthcare, and urban analytics. Current initiatives include advancing haptic interaction design, developing cloud-deployable medical imaging pipelines, and exploring AI-driven solutions for oil sands analysis. He teaches graduate courses like DATA 601 (Data Visualization) and special topics in computer science, contributing to both academic research and applied data science education.

• Scientific Visualization
• Medical Visualization
• Computer Graphics
• +۴ مورد دیگر

Eduard Gröller is a Professor at the Department of Informatics, University of Bergen. His research focuses on scientific visualization, medical visualization, and computer graphics, with emphasis on volume rendering, interactive systems, and visualization of complex data such as seismic volumes and protein dynamics. He has contributed to tools like VolumeShop and ViSlang, and his work spans medical imaging, climate data analysis, and bioinformatics. He has supervised PhD students including Daniel Patel and Johannes Kehrer. His recent articles address challenges in medical visualization, protein-protein interactions, and interactive navigation systems.

Helwig Hauserمشاهده پروفایل

استاد

• Visualization
• Data Science
• Interactive Data Analysis
• +۵ مورد دیگر

Helwig Hauser is a Professor at the Department of Informatics, University of Bergen, specializing in visualization and data science. His research focuses on interactive visual data exploration, flow visualization, and applications in engineering, biomedical, and geoscience domains. He leads the Visualization research group and teaches courses in computer graphics and data science. Key research interests include scientific visualization, molecular dynamics analysis, high-dimensional data exploration, and visual analytics. His work spans computational fluid dynamics, medical imaging, and engineering simulation, with a focus on developing intuitive tools for complex data interpretation. Hauser has authored/co-authored over 100 peer-reviewed publications, including influential works on flow visualization, ensemble analysis, and interactive brushing techniques. He has edited conference proceedings such as PacificVis and serves on program committees for top visualization conferences. His contributions include open-source tools like the SemSeg project and collaborations with industry on automotive and biomedical applications. He advises graduate students and collaborates internationally, emphasizing interdisciplinary applications of visualization in medicine, geology, and engineering. Current projects explore AI-enhanced visualization, real-time data exploration, and multiscale molecular analysis.

Veronika Šoltészováمشاهده پروفایل

دانشیار مدعو

• Scientific Visualization
• Medical Visualization
• Volume Rendering
• +۵ مورد دیگر

Veronika Šoltészová is an Adjunct Associate Professor at the Department of Informatics , University of Bergen. Her research focuses on scientific and medical visualization, volume rendering, and perception-driven visualization techniques. She has contributed to advancements in real-time data processing, shading models, and medical imaging workflows. Education: PhD in Computer Science (2012), University of Bergen Research Interests: Volume rendering and streaming data visualization Medical imaging (ultrasound, sonar) Perception-based shading models and illumination Real-time visualization algorithms Publications Trends: Her work spans medical imaging pipelines, volume data processing, and perceptual studies. Recent contributions include output-sensitive filtering for streaming volumes and visibility-driven processing techniques. Labs/Teams: Active in the MedViz (Medical Visualization) and SciVis (Scientific Visualization) research groups.

Daniel Patelمشاهده پروفایل

پژوهشگر

• Geological Visualization
• Computer Graphics
• Scientific Visualization
• +۳ مورد دیگر

Daniel Patel is an Adjunct Researcher at the University of Bergen's Department of Informatics. His work focuses on advancing visualization techniques for geological and geophysical data, with a particular emphasis on interactive modeling, real-time rendering, and domain-specific tools for scientific communication. He has contributed to projects such as 'Geological Storytelling' and 'Rapid Sketch-Based Modeling,' which aim to bridge the gap between geologists' conceptual ideas and computational modeling. Patel’s research integrates computer graphics innovations with domain-specific challenges in geology and marine science. His research interests include volume rendering, sketch-based modeling, seismic data interpretation, and educational approaches to PhD training. He collaborates with interdisciplinary teams, including the VisGroup at UiB, to develop tools for visualizing complex geological structures and sonar data. Patel holds a PhD in expressive visualization from TU Wien (2009) and has published extensively on topics ranging from chromatic shadows in medical visualization to statistical transfer functions for noisy data. Key contributions include the development of occlusion shading models, instant convolution shadows, and knowledge-assisted visualization frameworks for seismic exploration. His work emphasizes rapid prototyping and user-centric design, enabling domain experts to rapidly communicate and explore geological hypotheses.

Yuedong Wangمشاهده پروفایل

استاد

• Biostatistics
• Computational Statistics
• Machine Learning
• +۷ مورد دیگر

Yuedong Wang is a Professor in the Department of Statistics and Applied Probability at the University of California, Santa Barbara (UCSB), part of the College of Letters and Science. He holds a PhD from the University of Wisconsin-Madison and has prior experience at the University of Michigan. His research focuses on statistical methodologies, including nonparametric and semiparametric models, smoothing splines, machine learning, and biostatistical applications in renal diseases and human circadian rhythms. He is a Fellow of the ASA, IMS, ISI, and RSS, and a member of IBS and ICSA. His work spans over 150 publications, with recent emphasis on modeling dialysis patient outcomes, SARS-CoV-2 transmission in healthcare settings, and statistical computing. Key collaborations include the MONDO initiative for dialysis outcomes research. He has developed R packages like ASSIST for nonlinear mixed-effects models and contributed to smoothing spline theory. His book *Smoothing Splines: Methods and Applications* is a seminal text in the field. Education: BS in Mathematics (USTC), MS in Operations Research (Chinese Academy of Sciences), PhD in Statistics (UW-Madison). Research interests: Machine learning applications, functional data analysis, longitudinal data modeling, and biostatistical methods in nephrology. His articles address topics like tensor product RKHS analysis, nonparametric mixture models for clinical data, and AI-driven predictive analytics for dialysis patients. Awards include recognition for contributions to statistical methodology and its biomedical applications.

Sinan Kockaraمشاهده پروفایل

مدرس

• Medical Image Processing
• Virtual Reality (VR) Surgical Simulation
• Arthroscopic Surgery Training
• +۳ مورد دیگر

Sinan Kockara is a Lecturer in the Department of Computer Science at Rice University. He holds adjunct roles at the University of Central Arkansas (Computer Science and Engineering) and the University of Arkansas at Little Rock. With a Ph.D. in Applied Computing and a BS in Computer Engineering, his expertise spans medical image processing, virtual reality (VR) surgical simulation, and high-performance computing. His research focuses on dermatology imaging and arthroscopic surgery training systems, with $2.4+ million in funding from NIH, NSF, and industry partners. He has authored 40+ publications and holds over 640 citations. Education: BS, Computer Engineering, Dokuz Eylul University (Izmir, Turkey) PhD, Applied Computing, University of Arkansas at Little Rock Research Interests: Dr. Kockara develops VR-based surgical simulators for orthopedic training, including fluid dynamics simulations and bone drilling procedures. His work integrates machine learning for skill assessment and medical image analysis for dermatology applications. His lab (Biomedical Image Processing & HPC Lab) emphasizes real-time visualization and HPC optimization for medical systems. Grants & Validation: He secured major grants to validate surgical training platforms like ViRCAST and VATDEP. His studies compare novice/expert surgeon performance metrics and employ systematic validation frameworks for medical simulations. Labs & Future Work: Leads the Biomedical Image Processing & High-Performance Computing Lab, advancing real-time medical visualization and GPU-accelerated algorithms. Ongoing projects include cloud-based surgical simulators and AI-driven medical education tools.

Yu-Wing Taiمشاهده پروفایل

دانشیار

• Computer Vision
• Machine Learning
• Deep Learning
• +۳ مورد دیگر

Yu-Wing Tai is an Associate Professor of Computer Science at Dartmouth College, one of the Ivy League institutions. His research focuses on Computer Vision, Deep Learning, and Multimodalities Generative AI. He holds a PhD from the National University of Singapore and has served as an Associate Editor for IEEE TPAMI and as an Area Chair for major conferences like CVPR, ICCV, and NeurIPS. He is a Senior Member of the IEEE. Previously, he held roles as a Senior Research Director at Kuaishou Technology (2020-2023), Adjunct Professor at HKUST (2017-2023), and Research Director at Tencent (2017-2020). His work spans low-level vision, image/video editing, 3D reconstruction, and applications of large generative models. His research highlights include Motion-Agent for human motion generation, ChatCam for camera control, and Gear-NeRF for 3D reconstruction. He advises a team of PhD students and has mentored alumni now in academia and industry worldwide. His teaching includes courses on Multi-modalities Generative AI and Computer Graphics.