جست‌وجوی استاد و پژوهشگر

• visual perception
• color vision
• transparency
• +۸ مورد دیگر

Frederick Kingdom is a Senior Scientist at the McGill Vision Research unit within the Research Institute of the McGill University Health Centre (RI-MUHC), Montreal General Hospital site. He holds the academic rank of Professor in the Department of Ophthalmology and Visual Sciences at McGill University 's Faculty of Medicine and Health Sciences. His research focuses on bridging local feature detection (edges, bars, surface markings) with intermediate visual processing that forms contours, textures, and surfaces. Key domains include spatial vision , color vision , stereopsis , binocular vision , and transparency perception , combining psychophysical methods with natural scene image analysis and mathematical modeling . Recent publications explore stereoscopic depth adaptation , color-enhanced edge classification , co-circularity in texture , and binocular contrast adaptation . His work appears in journals like Vision Research and PLoS Computational Biology . Kingdom's lab maintains the Palamedes Toolbox for psychophysical data analysis. He investigates perceptual mechanisms in contexts ranging from 2D visual illusions to 3D environmental interpretation , with ongoing projects examining visual biases (e.g., falling objects) and contextual modulation in neural coding.

Maria Magnussonمشاهده پروفایل

مدرس

• Computer Vision
• Image Processing
• Scene Flow Estimation
• +۳ مورد دیگر

Maria Magnusson is a Lecturer at the Computer Vision Group within the Department of Systems Engineering at Linköping University . Her work bridges artificial vision systems with practical applications in medical imaging and computational photography . Research Focus : Computer Vision, Scene Flow Estimation, CT Reconstruction, and Machine Learning. Teaching : Courses in Digital Image Processing, Signal and Image Processing, Medical Images, and Computational Photography.

• Dwarf spheroidal galaxies
• Stellar populations
• Galactic chemical evolution
• +۷ مورد دیگر

Eline Tolstoy is Professor of Astronomy at the University of Groningen , Faculty of Science and Engineering. She leads a research program devoted to understanding the formation and evolution of dwarf spheroidal galaxies through detailed chemo-dynamical studies of resolved stellar populations. Research Interests Tolstoy’s work centers on the astrophysics of dwarf galaxies , using multi-wavelength, high-resolution spectroscopic data to trace star-formation histories, metallicity evolution, and dark matter content. Her expertise spans: Dwarf spheroidal galaxy dynamics and dark matter halos Chemical tagging of stellar populations via spectroscopic surveys Star formation histories inferred from color-magnitude diagrams and spectroscopy Next-generation instrumentation (WEAVE, WST, Euclid, MICADO) Galactic archaeology and near-field cosmology Recent Research Trends Recent publications demonstrate a strong focus on 3D chemo-dynamical mapping of Local Group dwarf galaxies, leveraging Gaia astrometry and VLT/FLAMES spectroscopy to derive precise kinematics and metallicities for thousands of individual stars. Collaborative papers on the WEAVE and WST facilities highlight her leadership in designing future wide-field spectroscopic surveys that will extend these studies to larger galactic samples and higher redshifts. Scientific Awards George Darwin Lectureship, Royal Astronomical Society (2013) Pastor Schmeits Prize (2007) NWO VICI Research Grant under the Innovational Research Incentives Scheme (2007) Data, Grants & Collaborations Tolstoy has secured major funding through the highly competitive NWO VICI program and participates in large international consortia including the Euclid space mission, the WEAVE spectroscopic survey, and the MICADO first-light imager for the ELT. She has released 31 curated datasets via the Strasbourg and Groningen astronomical data centers, underpinning reproducibility and open science. Labs & Teams She heads a dynamic research group within the Kapteyn Astronomical Institute at Groningen, supervising post-docs, PhD students, and international visitors. The group operates at the intersection of observation, theory, and instrumentation, fostering strong collaborations with ESO, ESA, and institutes across Europe and North America.

Shubham Tulsianiمشاهده پروفایل

استادیار

• Computer Vision
• Robotics
• 3D Reconstruction
• +۳ مورد دیگر

Shubham Tulsiani is an Assistant Professor at Carnegie Mellon University's Robotics Institute and part of the Computer Vision group. His research focuses on building perception systems that infer spatial and physical structures from visual data, with applications in 3D vision and robotics. University: Carnegie Mellon University Academic Rank: Assistant Professor Research Group: Computer Vision His work emphasizes reducing reliance on manual supervision by leveraging physical world structure as a 'meta-supervisory' signal. Recent publications at CVPR, ECCV, and NeurIPS explore diffusion models for 3D reconstruction, physics-aware neural networks, and video-based perception systems. Scientific recognition includes: Best Student Paper Award, CVPR 2015 Finalist for Best Paper Award in Robot Manipulation, ICRA 2024 The group actively mentors PhD and MS students, with current advisees including Hanzhe Hu, Himangi Mittal, Qitao Zhao, and Yehonathan Litman. Former students like Yufei Ye and Homanga Bharadhwaj have moved to postdoctoral positions at Stanford and Meta respectively.

Qianni Zhangمشاهده پروفایل

مدرس ارشد

• Machine learning
• Computer vision
• Medical image computing
• +۲ مورد دیگر

Qianni Zhang is a Senior Lecturer and PhD/PDRA Engagement Lead at the Centre for Multimodal AI within the School of Electronic Engineering and Computer Science at Queen Mary University of London. She leads research initiatives at the intersection of artificial intelligence and healthcare applications, with a particular focus on medical image analysis. Dr. Zhang's research interests center on machine learning and computer vision with specific applications in medical image computing . Her work spans multiple domains including medical imaging analysis for cardiology, ophthalmology, and oncology. She has developed numerous deep learning approaches for image segmentation, registration, and analysis, particularly focused on intravascular ultrasound, optical coherence tomography, and MRI applications. Her research bridges theoretical computer vision with practical clinical needs, creating tools that have potential to improve diagnostic accuracy and treatment planning in healthcare settings. Her recent publications demonstrate a clear trajectory toward increasingly sophisticated multimodal AI approaches for medical imaging. The trend shows progression from basic image segmentation techniques to complex fusion networks that combine multiple imaging modalities and incorporate anatomical knowledge. Many of her papers focus on cardiovascular applications, particularly intravascular ultrasound analysis, while others address ophthalmological and general medical imaging challenges. The consistent theme across her work is the application of cutting-edge deep learning techniques to solve real-world medical imaging problems with clinical relevance. ARCNET (Barts and the London Charity, £15,496, 2025-2026) Deep Learning based Multispectral Image Analysis for Retinal Lesion Detection (Royal Society, £12,000, 2022-2025) Anatomical And Functional Analysis Of The Soft Palate (Barts Health NHS, £132,620, 2022-2025) Machine learning for improved graphics in sport broadcast (Innovate UK, £214,061, 2022-2024) Dr. Zhang supervises a diverse group of PhD students working on various aspects of medical image computing and multimodal AI. Her students' projects span multiple healthcare domains including cardiovascular imaging, ophthalmology, dentistry, and general medical diagnostics. She has established herself as a leading researcher in applying deep learning to medical imaging challenges, with particular expertise in segmentation, registration, and multimodal fusion techniques for clinical applications.

Changjae Ohمشاهده پروفایل

مدرس

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

Dr. Changjae Oh is a Lecturer in Multimedia at the School of Electronic Engineering and Computer Science (EECS), Queen Mary University of London (QMUL). He is affiliated with the Centre for Multimodal AI, Centre for Intelligent Sensing, Computer Vision Group, and Advanced Robotics at Queen Mary. His research focuses on embodied agents, combining robotics and computer vision to enable precise environmental perception and action execution. Current research interests include human-to-robot handover, 3D computer vision, robust machine learning, and vision-language models for robot perception. Research group includes PhD students working on topics like adversarial policy learning, vision-language models, and federated learning for malaria prediction. Recent publications emphasize stereo vision, object pose estimation, and transformer-based architectures. Grants include funding from the Royal Society and Korea Institute for Advancement of Technology for projects on generative models and multi-modal foundational models.

Sheng Wangمشاهده پروفایل

استادیار

• Generative AI
• Biomedical Imaging
• Chromatin Structure Prediction
• +۵ مورد دیگر

Sheng Wang is an Assistant Professor at the Paul G. Allen School of Computer Science & Engineering , University of Washington Seattle. His work bridges Artificial Intelligence and Biomedical Applications through foundation models, generative AI, and large-scale biomedical data analysis. He holds a B.S. and Ph.D. in Computer Science from Peking University and University of Illinois at Urbana-Champaign, followed by postdoctoral research at Stanford School of Medicine. Research Interests: Developing generative AI for biomedical imaging (e.g., 40,000x40,000 pixel digital pathology via GigaPath ) Chromatin structure prediction using neural radiance fields ( CryoNeRF ) Genomics-based drug discovery through multi-modal data augmentation ( Pisces ) Multi-omics analysis with foundation models Collaborations: His work is deployed at institutions like Mayo Clinic , Chan Zuckerberg Biohub , and Providence Genomics . Current projects are supported by R01 and R21 grants for biomedical imaging and chromatin modeling. Teaching: Spring: AI for Drug Discovery Fall: AI for Medicine

Rafiq Ahmadمشاهده پروفایل

دانشیار

• Design and Manufacturing
• Additive Manufacturing
• Sustainable Production
• +۷ مورد دیگر

Dr. Rafiq Ahmad (PhD, P.Eng) is an Associate Professor at the University of Alberta’s Faculty of Engineering, Department of Mechanical Engineering. He directs the Smart & Sustainable Manufacturing Systems Laboratory (SMART LAB) and the Aquaponics 4.0 Learning Factory (AllFactory) . His work bridges fundamental research in design and manufacturing with advanced industrial applications. Education : PhD & MSc from French institutions (Ecole Centrale de Nantes and Ecole Arts et Metiers Paris), Postdoc at University of Luxembourg Research : Focuses on Smart Manufacturing (zero-defect production), Green Technologies (3R systems), Industrial Robotics (autonomous systems), and Sustainable Production (Aquaponics 4.0). The 15 most recent publications (2025) explore digital twins, robotics for extreme environments, hybrid manufacturing optimization, and sustainable food production. Articles span additive manufacturing, topology optimization, and AI-driven automation. Scientific Awards : 2023 ASTech Award for Digital Innovation; 2022 Edify Top 40 Under 40; multiple NSERC, Mitacs, and Alberta Innovates grants. Teaching : Offers courses in Manufacturing Systems, Lean Manufacturing, and Mechanical Measurements. Labs : SMART Lab (founded 2016) specializes in hybrid manufacturing and robotics; AllFactory focuses on sustainable aquaponics systems.

Brett Byramمشاهده پروفایل

دانشیار

• Medical Ultrasound
• Signal Processing
• Elasticity Imaging
• +۴ مورد دیگر

Brett Byram serves as Associate Professor of Biomedical Engineering at Vanderbilt University's School of Engineering and holds the Hoy Family Faculty Fellow distinction. He maintains dual affiliations with the Vanderbilt Institute for Surgery and Engineering (VISE) and the Vanderbilt University Institute of Imaging Science (VUIIS). Currently, he is the incoming Faculty Director of ACCRE—Vanderbilt’s High Performance Compute Center—and incoming chair for the NIH’s Image Technology Development (ITD) Panel, where he has served as a standing member. Educational Background: Ph.D. in Biomedical Engineering, Duke University (2011) B.S. in Biomedical Engineering and Mathematics, Vanderbilt University Dr. Byram's research centers on medical ultrasound with emphases in signal processing, elasticity imaging, and beamforming. His work spans beamforming/image formation, motion estimation, blood flow imaging, and hardware development—frequently integrating deep learning. The BEAM Laboratory, which he founded in 2013, develops ultrasound solutions for clinical challenges including transcranial imaging, placenta analysis, and kidney stone characterization. His methodology bridges advanced signal processing with tangible medical applications, particularly through AI-enhanced imaging techniques. Recent publications (2024-2025) reveal three dominant trends: deep learning integration for image reconstruction/stitching (e.g., SynStitch, LOTUS), clinical metric refinement (gCNR for lesion detectability), and specialized applications in obstetrics (placenta segmentation) and neuroimaging (transcranial ultrasound). These works consistently address data scarcity through synthetic training and domain adaptation while advancing quantitative assessment frameworks. Scientific Awards: Hoy Family Faculty Fellow Dr. Byram leads the BEAM Laboratory (Biomedical Elasticity and Acoustic Measurement), established in 2013 as part of Vanderbilt's Biomedical Engineering Department with VISE affiliation. His NIH ITD Panel leadership and ACCRE directorship reflect significant institutional trust. While specific grants aren't detailed, his 11+ years of continuous lab operation indicate sustained funding for projects spanning Siemens Healthcare collaborations, transcranial imaging development, and deep learning beamformer research—often translating academic innovations to clinical tools. The BEAM Lab functions as Vanderbilt's nexus for ultrasound innovation, maintaining strong VISE/VUIIS ties while pursuing hardware/software co-design. Current initiatives include real-time deep learning beamformers for echocardiography, transcranial functional ultrasound validation, and placenta segmentation systems. The lab's industry partnerships (notably with Siemens) and NIH panel involvement position it at the forefront of translating ultrasound research into clinical practice, with emerging work on diffusion models for 3D imaging and standardized biomechanical phantoms.

• Metrology
• Optical Engineering
• Manufacturing Engineering
• +۴ مورد دیگر

Dr. Jon Petzing is a Senior Lecturer in Metrology and Director of Undergraduate Admissions at Loughborough University's Wolfson School of Mechanical, Electrical & Manufacturing Engineering. He holds a BEng (Hons) in Mechanical Engineering, a Diploma of Industrial Studies (DIS), and a PhD in Optical Metrology, all from Loughborough University. His career spans roles in aerospace, confectionery manufacturing, and academia, with a focus on optical metrology and precision engineering. Research interests include flow cytometry data analysis, low-coherence interferometry, surface texture parameters, and manufacturing process optimization. Notable contributions include advancements in automated data analysis for cell therapy manufacturing and innovations in in-situ measurement techniques. Key awards include Chartered Engineer status (CEng), Fellow of the Higher Education Academy (FHEA), and the Helmut N Friedlaender Award for Leadership. Publications highlight trends in synthetic data applications, operator variability reduction, and interdisciplinary metrology solutions for biomedical and industrial challenges. His work bridges academic research with practical manufacturing and clinical applications, emphasizing precision and automation.

Dena Bazazianمشاهده پروفایل

مدرس

• Robotics
• Machine Vision
• Artificial Intelligence
• +۳ مورد دیگر

Dr. Dena Bazazian is a Lecturer in Robotics and Machine Vision at the University of Plymouth's School of Engineering, Computing and Mathematics. Previously, she held positions as a Senior Research Associate at the University of Bristol's Visual Information Laboratory, Research Scientist at CTTC (Barcelona), and postdoctoral researcher at Universitat Autònoma de Barcelona, where she earned her PhD in 2018. Her international research includes visiting positions at Barcelona Supercomputing Center (2024), NAVER LABS Europe (2019), and University of Florence (2017). Her research focuses on robotic vision, underwater technologies, and AI-driven applications. Key interests include: 3D reconstruction and neural rendering techniques Anomaly detection using graph neural networks Underwater perception systems for marine environments Intergenerational co-design of immersive technologies Point cloud processing and geometric deep learning Publication analysis reveals strong emphasis on computer vision applications across robotics, industrial inspection, heritage preservation, and marine technology. Recent works increasingly integrate human-centered approaches with XR technologies and underwater systems. She currently supervises 8 PhD students across robotics, healthcare, and environmental monitoring domains: Offshore wind turbine maintenance drones (EPSRC-UDLA funded) Autonomous sea vessel swarms for climate forecasting (ARIA funded) AI for marine biodiversity monitoring (Cefas funded) Elderly fall detection systems (URS General funded) Healthcare anxiety detection through visual analysis (EPSRC DTP HMT funded) Dr. Bazazian leads modules including Artificial Vision and Deep Learning and Computer Vision . She co-organizes workshops including the Deep Learning for Geometric Computing series (CVPR/ICCV) and Women in Computer Vision workshops (CVPR/ECCV).

Abdulrahman Kerimمشاهده پروفایل

پژوهشگر ارشد

• Computer Vision
• Machine Learning
• Explainable AI
• +۲ مورد دیگر

Dr. Abdulrahman Kerim is a Research Fellow in Explainable Machine Learning at the University of Surrey's School of Computer Science and Electronic Engineering. With expertise spanning computer vision, machine learning, and synthetic data generation, his research develops robust AI systems capable of operating under adverse conditions. He holds a PhD in Computer Science from Lancaster University and multiple undergraduate degrees in engineering disciplines. His research focuses on overcoming data limitations in computer vision through innovative synthetic data approaches. Recent work includes video stabilization algorithms resilient to weather conditions, semantic segmentation models for adverse environments, and procedural data generation frameworks. He authored the book Synthetic Data for Machine Learning detailing modern approaches to synthetic data generation including GANs and diffusion models. Dr. Kerim has received recognition as a Fellow of the British Machine Vision Association and Associate Fellow of the Higher Education Academy. He serves on the program committee for AAAI and has collaborated with industry partners including Google and Microsoft. His teaching experience includes modules on programming for data scientists, distributed AI, and game design.

• Computer Vision
• Machine Learning
• Video Surveillance
• +۷ مورد دیگر

Professor Tao Xiang holds the position of Professor of Computer Vision and Machine Learning at the University of Surrey, where he is also a Distinguished Chair. He leads the Body Behaviour Group at Samsung AI Centre, Cambridge. His research focuses on computer vision, including video surveillance, activity analysis, and sketch-based recognition, alongside machine learning domains like zero-shot learning and domain generalization. He has published over 160 papers (h-index 60) and secured £3.9M+ in grants. Key affiliations include the Faculty of Engineering and Physical Sciences and the Centre for Vision, Speech and Signal Processing (CVSSP). His work spans generative models for sketches, 3D shape retrieval from VR sketches, and virtual try-on systems. Notable contributions include the FS-COCO dataset for scene sketches and advancements in temporal action detection via vision-language prompting. Research interests emphasize cross-modal tasks (e.g., SBIR/FG-SBIR), domain adaptation, and transformer-based vision models. Collaborations with industry (Samsung AI) and foundational contributions to datasets (e.g., VR sketch collections) underscore his interdisciplinary impact. Future work includes creative object generation (PartCraft), explainable AI for sketches, and scalable generative models.

Jun Liuمشاهده پروفایل

استاد

• Computer Vision
• Machine Learning
• Digital Health
• +۳ مورد دیگر

Jun Liu is a Professor and Chair of Digital Health at Lancaster University's School of Computing and Communications. He holds a PhD from Nanyang Technological University (NTU), an MSc from Fudan University, and a BEng from Central South University. His research focuses on computer vision, machine learning, and digital health, with notable contributions to image segmentation, AI security, and multimodal learning. He leads the VL Group (https://wp.lancs.ac.uk/vl/) and supervises 5 postgraduate students. Education: PhD (NTU), MSc (Fudan), BEng (Central South University). Research Interests: His work spans AI-driven healthcare solutions, adversarial defense in vision-language models, and advanced computer vision techniques. He has pioneered methods like LLaFS++ for few-shot image segmentation and developed frameworks to combat jailbreak attacks in large models. Publications: Over 123 peer-reviewed articles, including high-impact work in IEEE Transactions and ACM journals. Recent trends focus on AI-generated content analysis, robust model security, and cross-modal learning. Awards: Best Paper Awards (PREMIA 2016/2019), IEEE VSPC Rising Star (2024), Stanford Top 2% Scientists. Editorial Roles: Senior Area Editor (IEEE T-IP), Associate Editor (IEEE T-CASVT, ACM Computing Surveys). Grants: Principal Investigator for the 'Unrestricted Gift' project (2025-2028). Labs/Teams: Leads the Vision & Learning (VL) research group, collaborating on digital health innovations and AI ethics challenges.

Paolo Favaroمشاهده پروفایل

استاد

• Computer Vision
• Computational Photography
• Machine Learning
• +۴ مورد دیگر

Prof. Dr. Paolo Favaro is a full Professor and Head of the Computer Vision Group (CVG) at the University of Bern's Institute of Computer Science. He holds a Laurea (BSc+MSc) from the University of Padova, Italy, and M.Sc. and Ph.D. in Electrical Engineering from Washington University in St. Louis. His career includes postdoctoral roles at UCLA and Cambridge University, followed by work in medical imaging at Siemens Corporate Research. From 2006–2011, he was Lecturer and Reader at Heriot-Watt University, and Honorary Fellow at the University of Edinburgh before joining Bern in 2012. His research focuses on computer vision , computational photography , machine learning , and signal/image processing , with contributions to inverse problems and variational techniques. His work spans theoretical advancements and practical applications, such as video diffusion models, unsupervised segmentation, and image restoration. He is an active member of the IEEE Society. Recent research trends emphasize generative models (e.g., diffusion models, video generation) and self-supervised learning , addressing challenges in real-world image/video denoising and sparsity-driven methods. His articles explore topics like Kalman-based optimization, multimodal world models, and spatio-temporal representation learning. Prof. Favaro leads the CVG, fostering interdisciplinary research at the intersection of computer vision and AI. His lab develops cutting-edge solutions for 3D reconstruction, medical imaging, and autonomous systems.