Find Academic Supervisors

David DownesView profile

Senior Lecturer

• X-ray systems
• image processing
• interaction design
• +4 more

David Downes is a Senior Lecturer at the Nottingham School of Art & Design, Nottingham Trent University, where he teaches scripting for animators, procedural animation, and motion capture applications while supporting students across multiple courses. He actively supervises postgraduate research in his specialized domains. His research centers on X-ray systems and image processing for security applications, interaction design, interactive environments, computational creativity, procedural animation, and motion capture. A sustained focus involves developing X-ray imaging systems for security screening, conducted within the Imaging Science Group led by Prof. Paul Evans. This work bridges engineering, computer science, and creative design to solve real-world security challenges. Downes' recent publications (2023-2024) reveal two dominant research trajectories: advanced X-ray imaging techniques (conical shell beam tomography/diffraction for medical/security applications) and machine learning-driven virtual reality exposure therapy for mental health. His work demonstrates interdisciplinary innovation spanning physics, computer vision, and clinical psychology. Professional recognition includes: Fellow of the Higher Education Academy Downes supervises PhD students including Hogg (2024) on focal construct geometry for X-ray diffraction. His research is funded by Defence and Security Accelerator (DASA), EPSRC, US Department of Homeland Security (DHS), and Cranfield University, with collaborations extending to Roma Patel of The Society of British Theatre Design. Key collaborators: Roma Patel (The Society of British Theatre Design) Primary sponsors: DASA, EPSRC, DHS, Cranfield University As a core member of the Imaging Science Group, Downes contributes to internationally recognized research in security-focused X-ray systems. The group maintains active GitHub repositories and ResearchGate presence, with projects emphasizing human-centered design validated through ergonomics studies and real-world security implementations.

Akihiko ToriiView profile

Assistant Professor

• Computer Vision
• 3D Reconstruction
• Place Recognition
• +6 more

Akihiko Torii is an Assistant Professor (Research Associate) at the Okutomi & Tanaka Lab in Tokyo Institute of Technology. He holds a PhD from Chiba University and completed a postdoctoral fellowship at the Center for Machine Perception (CMP) at Czech Technical University in Prague. His research focuses on computer vision, with expertise in 3D reconstruction, place recognition, localization, and structure from motion. He has contributed to influential datasets like the 24/7 Tokyo, Pittsburgh (Pitts250k), SF Revisited, and InLoc datasets, advancing visual localization and feature matching techniques. **Education and Background:** PhD in Computer Science, Chiba University Postdoctoral Researcher, Czech Technical University (2014–2018) **Research Interests:** His work spans Computer Vision , including 3D Reconstruction , Place Recognition , Feature Matching , and Multi-View Stereo . He emphasizes practical applications such as indoor/outdoor localization under changing conditions. **Awards and Recognition:** 2017: CVPR Outstanding Reviewers Award 2016: IEEE Japan Chapter Young Author Award 2015: Tokyo Tech Young Investigator Award Multiple Best Paper Awards (2013–2014) **Key Projects:** Developed algorithms like Multi-View Inverse Rendering and NetVLAD , and contributed to benchmarking frameworks for visual localization accuracy. His work bridges theoretical advancements and real-world applications in robotics and autonomous systems.

Szymon KobylarzView profile

Professor

• Painting
• Visual Arts
• Installation Art
• +2 more

Szymon Kobylarz (born 1981) is a Professor and currently serves as Dean of the Faculty of Art at the Academy of Fine Arts in Katowice (ASP Katowice), Poland. He is affiliated with the Painting Studio III where he teaches. Kobylarz is a prominent figure in the Polish contemporary art scene, with his work frequently presented both in Poland and internationally. His research interests span across multiple disciplines within visual arts, with a strong focus on painting, installation art, and sculpture. Kobylarz's work often explores conceptual frameworks, mathematical structures in art, philosophical inquiries, and sociopolitical commentary. His artistic practice demonstrates a sophisticated blend of traditional painting techniques with contemporary conceptual approaches. The analysis of Kobylarz's recent works reveals a consistent exploration of geometric forms, temporal concepts, and philosophical inquiries. His pieces often incorporate mathematical structures (such as the dodecahedron tree), existential themes (as seen in 'A Man Who Did Not Live Through the End of the World'), and conceptual frameworks (like 'Unknown unknowns'). His work shows a progression from more traditional painting towards increasingly conceptual and multimedia approaches, while maintaining a strong foundation in visual arts. Scientific Awards: Grantee of the Minister of Culture and National Heritage (awarded twice) Kobylarz has made significant contributions to the academic community through his leadership as Dean of the Faculty of Art and his teaching in the Painting Studio III. His work has been instrumental in promoting contemporary art practices within the academic setting. He has likely supervised numerous students through their artistic development, though specific names are not documented in the available information. His studio serves as an important space for developing emerging artists in the region. Kobylarz maintains an active studio practice while fulfilling his administrative responsibilities, demonstrating a commitment to both artistic creation and academic leadership. His work bridges the gap between traditional art forms and contemporary conceptual approaches, making him a significant figure in the Polish art education landscape.

• Computer Vision
• Medical Informatics
• 3D Scene Understanding
• +5 more

Overview Pedro Hermosilla Casajus is an Assistant Professor at the Department of Computer Vision within the Faculty of Informatics at Technische Universität Wien (TU Wien). His research focuses on advanced computer vision techniques with applications in medical imaging, 3D scene understanding, and deep learning methodologies. He is actively involved in teaching multiple courses including Fundamentals of Computer Vision, Deep Learning for Visual Computing, and Scientific Research and Writing. Projects & Collaborations MyeFLOW (2020–2025) : Developing automated analysis systems for flow cytometry data. EVOCATION (2018–2022) : Real-time shape acquisition technologies. Modeling the World at Scale (2020–2026) : Large-scale 3D modeling techniques. Research Highlights His work bridges computer vision with medical diagnostics, particularly in measurable residual disease detection using flow cytometry. He explores geometric deep learning for 3D point cloud analysis and scene graph generation, advancing unsupervised semantic segmentation methods. Recent contributions include stylized Gaussian splatting for neural rendering and open-vocabulary 3D scene understanding frameworks. Teaching He teaches core courses like Fundamentals of Computer Vision and supervises student projects in medical informatics, visual computing, and human-centered computing.

Justus ThiesView profile

Professor

• Computer Graphics
• Computer Vision
• Machine Learning
• +3 more

Justus Thies is a Professor at the Technical University Darmstadt (since September 2023), leading research at the intersection of computer graphics , computer vision , and machine learning . His work focuses on real-time 3D reconstruction, tracking, and photorealistic rendering of humans and environments using commodity hardware, with applications in AR/VR , movie production , and 3D telepresence for collaborative virtual environments. Current faculty member at Technical University Darmstadt Research themes: 3D reconstruction, neural rendering, hybrid machine learning/Graphics methods Applications: AR/VR, telepresence, human-environment modeling His research emphasizes neural rendering and deep learning approaches for facial and body modeling, including projects like GEM (Gaussian Eigen Models), SynShot (synthetic prior inversion), and TeCH (text-guided clothed human reconstruction). Collaborations include institutions like Max Planck Institute for Intelligent Systems and Google . Key trends in his recent publications include: neural Gaussian splatting for real-time avatars, diffusion models for speech/audio-driven animation, and hybrid approaches that combine classical computer graphics principles with modern machine learning techniques. These methods address challenges in generalizability , controllability , and editability of 3D representations. Notable research contributions since 2014 include advancements in monocular facial reconstruction , real-time expression transfer , and neural rendering techniques that enable 3D scene synthesis from unpaired or sparse data. His work has received significant recognition, including Face2Face featured in Communications of the ACM (2019) and multiple publications at top venues like CVPR , ECCV , and SIGGRAPH .

Cemil ÖZView profile

Professor

• Computer Science
• Artificial Intelligence
• Computer Vision
• +9 more

Prof. Cemil ÖZ is a full-time Professor at Sakarya University's Faculty of Computer and Information Sciences, where he has held academic positions since 1998. He leads research in computer vision, artificial intelligence, and medical imaging applications, with ongoing projects in virtual simulation systems and machine learning diagnostics. Education PhD in Electrical and Electronics Engineering, Sakarya University (1995-1998), specializing in neural network-based robotic trajectory control Master's in Electronics and Computer Education, Marmara University (1989-1993), focusing on adaptive robotic control systems Bachelor's in Electronics and Communication Engineering, Yıldız University (1986-1989) Research Focus Prof. ÖZ's interdisciplinary research bridges computer science with healthcare, industrial applications, and security. Primary domains include: Medical AI : Machine learning for neuroimaging diagnostics (e.g., multiple sclerosis differentiation) Virtual Simulation : Industrial and educational systems (welding/driving simulators) Computer Vision : 3D reconstruction, object detection, and facial analysis Applied ML : Hybrid algorithms for predictive modeling in security and social media Publication Trends Recent articles (2019-2024) demonstrate strong emphasis on AI-driven healthcare solutions (38% of works), particularly neurological disorder diagnostics using MRI/spectroscopy data. Virtual training systems constitute 27% of output, focusing on industrial/educational simulations. Remaining publications advance computer vision techniques (3D reconstruction, object detection) and security applications (terrorism prediction, sentiment analysis). Methodologically, deep learning (YOLO, CNN) and sensor integration (Kinect) are predominant.

Magdalena WysockiView profile

Researcher

• Medical Ultrasound Imaging
• 3D Computer Vision
• Neural Radiance Fields
• +3 more

Magdalena Wysocki is a researcher at Technical University of Munich's Department of Computer Science within the School of Computation, Information and Technology. She works under Prof. Nassir Navab's Chair of Computer Aided Medical Procedures at the Garching campus, focusing on medical ultrasound imaging and neural radiance fields for surgical applications. Her research integrates deep learning with medical physics to solve reconstruction challenges in ultrasound imaging. Her primary research interests include: Medical Ultrasound Imaging with neural field applications Physics-consistent 3D reconstruction from sparse views Geometry-aware deep learning for medical imaging Real-time surgical data science applications Confidence mapping in neural implicit representations Her recent publication trends show concentrated work on neural radiance fields for ultrasound (Ultra-NeRF), with expanding applications to tissue property estimation (UltRAP-Net) and surgical activity understanding (EgoExOR). Key methodological threads include physics-based constraints in deep learning and confidence quantification for clinical deployment. She actively supervises multiple Master's students on projects including: 4D Ultrasound SLAM (Sebastian Herz) Cardiac Shape Reconstruction with Motion Correction (Abdulkader Ghandoura) Confidence Maps research leading to MIUA 2024 publication (Bugra Yesilkaynak) Her GitHub repositories (ultra-nerf, ultron) demonstrate strong software engineering contributions to the medical imaging community. She contributes to the NARVIS and RobUSt research groups focusing on surgical vision systems and robotics.

Francesca OdoneView profile

Professor

• Computer Vision
• Machine Learning
• Biomedical Image Processing
• +3 more

Francesca Odone serves as a Full Professor in the Department of Computer Science, Bioengineering, Robotics, and Systems Engineering (DIBRIS) at the University of Genoa, Italy. She holds a position on the Department Board and teaches core courses including Computational Vision , Algorithms and Data Structures , and Fundamentals of Signal and Image Processing across undergraduate and graduate programs in Computer Science and Biomedical Engineering. Her research centers on Computer Vision and Machine Learning with critical applications in Biomedical Engineering . Key focus areas include markerless motion analysis for neurological disorders (particularly multiple sclerosis), video-based assessment of motor functions in spinal cord injury and preterm infants, and deep learning for medical image interpretation . She integrates robotics and signal processing to develop non-invasive clinical diagnostic tools, emphasizing practical healthcare solutions through interdisciplinary collaboration. Analysis of her 15 most recent publications (2024-2025) reveals three dominant trends: (1) Proliferation of markerless video-based clinical assessment tools for gait/motion analysis, (2) Advanced deep learning architectures (diffusion models, disentangled representations) applied to medical imaging challenges, and (3) Cross-cutting work on AI fairness/debiasing techniques. Her research consistently bridges computer vision with neurology, rehabilitation medicine, and neonatology. Professor Odone actively contributes to DIBRIS's research ecosystem through ongoing projects in biomedical computer vision, with strong connections to clinical partners. Her work demonstrates sustained focus on translating computer vision innovations into practical healthcare applications, particularly for neurological and developmental conditions.

• Medical Image Analysis
• Image Segmentation
• Deep Learning
• +3 more

Chunliang Wang is a researcher with Docent title at the School of Technology and Health (STH), KTH Royal Institute of Technology, Sweden. His primary affiliation is with the Division of Biomedical Imaging at Hälsovägen 11C, Stockholm. He serves as course responsible for Deep Learning Methods for Medical Image Analysis (CM2003) and Medical Engineering, Basic Course (HL1007), while also teaching 3D Image Reconstruction and Analysis in Medicine (HL2027) and Degree Projects in Medical Engineering. His educational background includes medical training at Tianjin Medical University (1998-2005) and a PhD in Medical Science from Linköping University (2011). Prior to his academic career, he worked as a software engineer at Sectra AB in Linköping (2011-2015). Wang's research focuses on medical image analysis , specializing in image segmentation , deep learning , and statistical shape modeling . His work bridges clinical applications with computational methods, particularly in cardiovascular and neurological imaging. As the key contributor to MiaLab software (mialab.org), he develops practical tools for medical image processing. His publication portfolio spans 21 journal articles and 18 conference papers since 2007, with recent work emphasizing deep learning applications in multi-organ segmentation, coronary artery analysis, and neurological imaging. The 15 most recent publications demonstrate consistent focus on algorithm development for clinical image interpretation, particularly in segmentation challenges across multiple anatomical systems. Wang has developed significant research software including MiaLab (since 2011), CMIV CTA plug-in for OsiriX, MeVisHub, and MiaLite. His patented work on level-set based image processing (2013) demonstrates translational impact. While no formal awards are listed, his leadership in multiple MICCAI challenges and VISCERAL benchmarks highlights community recognition.

• Computer Vision
• Object Recognition
• Scene Understanding
• +7 more

Derek Hoiem is a Professor in the Department of Computer Science at the University of Illinois Urbana-Champaign (UIUC), affiliated with the Siebel School for Computing and Data Science since 2009. He holds a PhD in Robotics from Carnegie Mellon University (2007) and completed a Beckman Postdoctoral Fellowship (2008). As co-founder and Chief Science Officer of Reconstruct, he develops AI-driven tools for construction progress monitoring. His research focuses on computer vision, object recognition, scene understanding, and graphics. Key honors include IEEE Fellow (2022), University Scholar (2022), and the Sloan Research Fellowship (2013). He has received NSF CAREER and Intel Early Career awards, alongside best paper awards at CVPR (2006) and WACV (2015). His teaching excellence is reflected in numerous 'List of Teachers Ranked as Excellent' accolades across multiple semesters. Research interests span 3D reconstruction, neural networks, and multimodal models. His work addresses challenges in visual program generation, neural radiance fields, and construction monitoring through photogrammetry. He leads projects in continual learning, efficient AI systems, and explainable multimodal interactions. Professional contributions include grants from NSF and industry partnerships. He advises on cutting-edge AI applications in construction, graphics, and vision-language integration. His lab’s innovations bridge theoretical advancements with real-world systems like Reconstruct’s Visual Command Center.

Yi MaView profile

Professor

• Computer Vision
• Multiple View Geometry
• Compressive Sensing
• +3 more

Professor Yi Ma is a faculty member at the Department of Electrical Engineering and Computer Sciences (EECS) at the University of California, Berkeley, and holds the Chair Professor in AI at the School of Computing and Data Science (CDS), University of Hong Kong. He serves as Director of both CDS and the Institute of Data Science (IDS) at HKU since 2024 and 2023, respectively. His research spans artificial intelligence , computer vision , compressive sensing , and machine learning , with a focus on low-dimensional models for high-dimensional data analysis . He has pioneered work in robust principal component analysis , sparse representation , and deep learning theory , as reflected in his textbook High-Dimensional Data Analysis with Low-Dimensional Models (Cambridge, 2021) and recent position papers. Key contributions include organizing conferences like the Conference on Parsimony and Learning (CPAL) and developing course EECS 208 at Berkeley, which explores computational principles for AI and data analysis. His work is affiliated with research hubs such as the Berkeley Artificial Intelligence Research (BAIR) , Center for Augmented Cognition , and Vive Center for Enhanced Reality . Scientific Honors: Society for Industrial & Applied Mathematics (SIAM) Fellow (2020) Association for Computing Machinery (ACM) Fellow (2017) Institute of Electrical & Electronics Engineers (IEEE) Fellow (2013) Office of Naval Research Young Investigator (2005) NSF CAREER Award (2004) CS TCPAMI ICCV Best Paper Award/David Marr Prize (1999) He has held leadership roles at institutions including ShanghaiTech University and Microsoft Research Asia, blending theoretical and applied research in structured data modeling and vision-based robotics .

Martin BråtelundView profile

Researcher

• Mathematics
• Computer Vision
• Algebraic Geometry
• +2 more

Martin Bråtelund is a Doctoral Research Fellow at the Department of Mathematics, University of Oslo. His research focuses on critical configurations in projective geometry, with applications in computer vision and algebraic geometry. He holds a formal affiliation with the Faculty of Mathematics and Natural Sciences. Research Interests: Martin explores interdisciplinary areas bridging mathematics and computer science, particularly in understanding geometric configurations under projective transformations. His work involves algebraic methods to analyze critical scenarios in multi-view geometry, with implications for 3D reconstruction and computer vision algorithms. Key Trends in Publications: His recent articles investigate foundational problems in projective geometry, such as critical configurations for multiple views and compatibility of fundamental matrices. These studies contribute to both theoretical mathematics and applied computational methods in geometric modeling.

Hengshuang ZhaoView profile

Assistant Professor

• Computer Vision
• Scene Understanding
• Multimodal Learning
• +3 more

Dr. Hengshuang Zhao is an Assistant Professor at the Department of Computer Science, University of Hong Kong. He holds a PhD from The Chinese University of Hong Kong and completed postdoctoral research at MIT CSAIL and the University of Oxford. His research focuses on computer vision, machine learning, and AI, emphasizing visual scene understanding, generative modeling, autonomous driving, and embodied AI. He leads a lab actively recruiting PhD students and researchers. Education: PhD in Computer Science, Chinese University of Hong Kong (2017) Bachelor's Degree, Huazhong University of Science and Technology Affiliations: Member of Hong Kong Robotics Institute Organizer of CVPR/ICML workshops on point clouds and embodied AI His research interests include: Scene Understanding (e.g., semantic segmentation, 3D reconstruction), Multimodal Learning (vision-language models), and Generative Modeling (image/video synthesis). Recent work includes Depth Anything (CVPR 2024 Best Demo), Point Transformer V3 (CVPR 2024), and DriveGPT4 series for autonomous driving. He has been recognized with awards including the Excellent Young Scientists Fund (2024), AI 2000 Influential Scholar in CV (2022-2024), and organized multiple top-tier conferences' workshops and tutorials.

• Computer Vision
• Machine Learning
• Healthcare AI
• +7 more

Jianbo Jiao is an Associate Professor in Computer Vision and Machine Learning at the School of Computer Science, University of Birmingham, where he leads the MIx (Machine Intelligence + x) research group. Previously, he was a Postdoctoral Researcher in the Biomedical Image Analysis (BioMedIA) group and Visual Geometry Group (VGG) at the University of Oxford, working on the SeeBiByte and VisualAI projects. MSc from Peking University (2015) PhD in Computer Science from City University of Hong Kong (2018), supported by Hong Kong PhD Fellowship Scheme Visiting scholar at Beckman Institute, University of Illinois at Urbana-Champaign (2017-2018) Dr. Jiao's research focuses on Computer Vision, Machine Learning, Healthcare AI, and AI for Science. His work primarily investigates learning representations in open-world scenarios by exploring auxiliary information from multiple modalities (image/video, speech/audio, text/NLP, depth/stereo, gaze/saliency, motion) and reducing dependency on supervision through self-supervised, weakly-supervised, and semi-supervised learning approaches. His group has made significant contributions to multimodal learning, medical image analysis, and 3D vision. His recent publications demonstrate strong trends in multimodal learning, medical AI applications, and 3D computer vision. The research spans fundamental computer vision tasks like segmentation and scene understanding while addressing practical challenges in healthcare and scientific domains. Notably, there's significant focus on making vision systems more robust to distribution shifts and requiring less labeled data. Amazon Research Award recipient (2024) Royal Society Short Industry Fellow Best Paper Award at MICAD 2024 Best Paper Award at MICCAI 2024 ASMUS Workshop Best Presentation (Runner-Up) Award at MICCAI 2024 ASMUS Workshop Best Paper Award at ECCV 2022 Medical Computer Vision Workshop Multiple Outstanding Reviewer Awards from top conferences Dr. Jiao serves as Associate Editor for The Transactions on Machine Learning Research (TMLR) and IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), and has been actively contributing to the community as Area Chair for NeurIPS, ICML, ICLR, and ACM MM. His MIx group has secured multiple research grants including the Amazon Research Award for the PCo3D project on Physically Plausible Controllable 3D Generative Models. Current PhD students include Isaac Akintaro, Hao Ai, and Kangning Zhang. The MIx group maintains active collaborations with industry partners including Amazon and Meta, and has developed notable datasets such as 360+x for panoptic multi-modal scene understanding and DyMVHumans for dynamic human modeling. Their research bridges fundamental computer vision with practical applications in healthcare, physics, chemistry, and other scientific domains.

• Reinforcement Learning
• Artificial Intelligence
• Computer Vision
• +6 more

C. H. T. Child is an Associate Professor in the Department of Computer Science at City, University of London, with a distinguished research career spanning over two decades. The academic maintains an active research profile with publications extending through 2025, demonstrating continued scholarly contributions across multiple domains of computer science and artificial intelligence. Child's primary research interests center around Reinforcement Learning , Artificial Intelligence , and Computer Vision , with specialized expertise in non-Euclidean geometry applications for gaming environments, medical informatics, and human-computer interaction. The research portfolio reveals a consistent trajectory from foundational work in reinforcement learning algorithms to applied research in game AI, medical informatics, and scene representation learning. A notable research thread involves the application of non-Euclidean geometry to create novel gaming experiences, while another significant strand focuses on developing advanced AI systems for non-player characters with personality modeling capabilities. Analysis of the most recent publications (2019-2025) shows an evolution toward more sophisticated deep learning architectures applied to complex problems in medical informatics and scene representation. The work has increasingly incorporated transformer networks, attention mechanisms, and advanced feature extraction techniques, reflecting broader trends in the field while maintaining the researcher's distinctive focus on reinforcement learning fundamentals. The publication record demonstrates successful translation of theoretical AI concepts into practical applications across gaming, healthcare, and computer vision domains. Child has supervised multiple doctoral students and research collaborators, with several co-authors appearing consistently across publications as first authors on significant works. The research has been supported through university resources and likely external funding, though specific grant details are not provided in the available materials. The academic maintains an active presence in both theoretical and applied research communities, with publications spanning top conferences and journals in computer science and AI. The researcher leads work in the Extreme AI Personality Engine project and contributes to computer vision research with applications in hand pose estimation and medical imaging. These research streams are well-integrated, with reinforcement learning principles providing a unifying theoretical framework across diverse application domains.