Find Academic Supervisors

Minglun GongView profile

Professor

• Visual Computing
• Computer Graphics
• Computer Vision
• +6 more

Dr. Minglun Gong is a Professor and Director of the School of Computer Science at the University of Guelph (since 2019). Previously, he served as Professor and Head of the Department of Computer Science at Memorial University of Newfoundland. He holds a Ph.D. from the University of Alberta (2003), M.Sc. from Tsinghua University (1997), and B.Engr. from Harbin Engineering University (1994). His research focuses on visual computing, including computer graphics, computer vision, visualization, image processing, and pattern recognition. He has authored over 150 referred papers and holds patents in the field. He is an Associate Editor for Pattern Recognition and IEEE Signal Processing Letters , and has received awards such as the Izaak Walton Killam Memorial Award and multiple best paper awards. Dr. Gong has advised numerous students, including Ph.D./M.Sc. candidates and visiting scholars. His lab's recent work includes UAV path planning for urban reconstruction, image stylization techniques, and 3D human pose estimation. He actively participates in academic service, including editorial roles, conference program committees, and administrative roles at multiple institutions. His teaching spans courses in image processing, computational photography, and technical communication. He is also involved in administrative committees, such as Graduate Studies and Promotion at Memorial University. Key research contributions include advancements in transparent object modeling, underwater 3D reconstruction, and image-to-image translation. His work emphasizes practical applications in fields like medical imaging, autonomous systems, and environmental modeling.

• Computer Vision
• Robotics
• Medical Imaging
• +4 more

Yuhao Chen is a Research Assistant Professor at the University of Waterloo, specializing in cutting-edge research at the intersection of computer vision, robotics, and healthcare. His work focuses on 3D reconstruction, food tracking, medical imaging, and AI-driven solutions for nutrition analysis and sports analytics. He has contributed to benchmark datasets like NutritionVerse, MetaGraspNet, and FoodVerse, advancing applications in robotic grasping, dietary intake estimation, and human-object interaction analysis. Research interests include egocentric video analysis, real-time 3D reconstruction, zero-shot learning, and multi-task learning. His projects often integrate Gaussian splatting, photometric SLAM, and diffusion models to solve complex problems in food tracking, medical image segmentation, and sports player motion analysis. Recent work highlights include FoodTrack for dietary monitoring and RepViT-MedSAM for medical image segmentation. Yuhao Chen’s innovations span robotics, healthcare, and AI, with a focus on practical applications such as automated nutrition assessment, robotic bin picking, and athlete performance analysis. His research emphasizes scalable frameworks and physically informed 3D reconstruction methods to address real-world challenges in health, sports, and automation.

• Numerical analysis
• Scientific computing
• Partial differential equations
• +3 more

Kirill Serkh is an Assistant Professor in the Department of Mathematics at the University of Toronto, with a cross-appointment to the Department of Computer Science. His research focuses on advanced numerical methods for solving complex mathematical problems. Key Research Areas: Numerical analysis, Scientific computing, Partial differential equations, Numerical linear algebra, Quadrature and approximation theory, Special functions His recent work explores high-order numerical schemes for PDEs on non-smooth domains, adaptive methods for oscillatory integrals, and efficient evaluation of Newtonian potentials. He has contributed to the development of hybrid boundary integral methods and spectral techniques for challenging computational problems. While no specific scientific awards are mentioned in the provided text, his publications demonstrate expertise in computational mathematics and interdisciplinary applications in fluid dynamics, wave propagation, and machine learning. His methodological innovations span both theoretical and applied domains.

Jiju PoovvancheriView profile

Associate Professor

• Computer Graphics
• 3D Vision
• Machine Learning
• +8 more

Dr. Jiju Poovvancheri is an Associate Professor in the Department of Math & Computing Science at Saint Mary’s University, Halifax, Canada. He holds affiliations with the Graphics & Spatial Computing Lab and previously held postdoctoral positions at the University of Victoria and University of Calgary. His research focuses on computer graphics, 3D vision, and machine learning, with applications in virtual/augmented reality, autonomous robotics, urban planning, and bio-mechanical studies. Key research areas include point cloud processing, semantic surface reconstruction, spatial data structures, and geometric deep learning. Education: PhD from Indian Institute of Technology Madras (2011–2014), supervised by Prof. Ramanathan Muthuganapathy. Postdoctoral work at University of Calgary (EYES-HIGH Fellowship, 2015–2017) and University of Victoria (MITACS Elevate Fellowship, 2018). Research & Awards: Winner of MITACS Elevate Fellowship (2018), EYES-HIGH Fellowship (2015–2017), and multiple grants including NSERC DG (2019–2026). His work has been supported by NVIDIA GPU hardware, NSERC, CFI, and industry partners like Modest Tree Media and Caterpillar. Professional Activities: Associate Editor for IEEE Access , Guest Editor for special issues in Remote Sensing and Sensors , and reviewer for top conferences like CVPR, ICCV, and ECCV. Member of ACM SIGGRAPH, Solid Modeling Association, and IEEE Geoscience & Remote Sensing Society. Lab & Collaborations: Leads the Graphics & Spatial Computing Lab, collaborating with institutions globally. Current projects include "Interaction and navigation in virtual spaces" and industry partnerships with Modest Tree Media for real-time object recognition. Advising: Supervised over 20 graduate and undergraduate students, with notable alumni advancing to roles at ReelData AI, Royal Canadian Air Force, and academic institutions like Dalhousie University.

Kangkang YinView profile

Associate Professor

• Computer Animation
• Computer Graphics
• Humanoid Robotics
• +3 more

Kangkang Yin is an Associate Professor in the School of Computing Science at Simon Fraser University (SFU). His research focuses on computer animation, computer graphics, humanoid robotics, machine learning, and multimedia analysis. He teaches courses such as Computer Animation and Scientific Computing, and holds a PhD from the University of British Columbia (2007), MSc from Zhejiang University (2000), and BSc from Zhejiang University (1997). His work bridges robotics and animation through projects like physics-based character controllers, motion diffusion models, and robotic manipulation. Key contributions include the SIMBICON biped locomotion framework and research into emotion-driven dance animation. Recent efforts emphasize reinforcement learning applications in motion synthesis and robust visual navigation for unmanned ground vehicles. Yin's publications span over two decades, addressing challenges in motion control, physics-based simulation, and machine learning applications. His lab contributes to both academic advancements and practical robotics solutions. Current research trends show strong emphasis on combining generative AI with traditional animation techniques, as seen in recent work on auto-regressive motion models (AAMDM) and physics-augmented reinforcement learning (PARC).

Ayesha AliView profile

Professor

• Graphical Markov models
• Pollination networks
• Multivariate statistics
• +7 more

Ayesha Ali is a Professor of Statistics and Director of the Master of Data Science program at the University of Guelph. She holds a PhD in Statistics from the University of Washington (2002) and has expertise in statistical methods for complex high-dimensional systems, including ecological networks, causal inference, and bioinformatics. Her research integrates graphical Markov models, machine learning, and statistical computing to address challenges in plant-pollinator networks, livestock genetics, and disease risk modeling. Education: B.Sc. Honours in Statistics and Actuarial Science, University of Western Ontario (1996) M.Sc. in Statistics, University of Toronto (1998) Ph.D. in Statistics, University of Washington (2002) Research Interests: Graphical Markov models and ecological networks Causal inference and longitudinal data analysis Machine learning and high-dimensional predictive modeling Statistical methods for livestock genetics and animal health Computational statistics and bioinformatics Articles Trends: Her recent work spans interdisciplinary applications, including veterinary oncology biomarker discovery, remote sensing for agricultural suitability, and pipeline development for cross-species transcriptomics. She emphasizes graphical structure exploitation in regression and predictive modeling, with contributions to both theoretical and applied statistical methodologies. Awards: Canadian Journal of Statistics Award (2020) for groundbreaking work on doubly sparse regression NSERC Discovery Grant (2018) NSERC Collaborative Research and Development Grant (2015) Advising & Grants: She has supervised numerous graduate and undergraduate students on projects ranging from plant-pollinator network analysis to bioinformatics. Her grants include NSERC-funded research on milk fatty acid genetics and statistical methods for clustered data. Labs/Teams: Involved in the Bioinformatics program at the University of Guelph, contributing to interdisciplinary research collaborations in ecology and animal science.

• Machine Learning
• Representation Learning
• Geometric Deep Learning
• +4 more

Siamak Ravanbakhsh is an Associate Professor at McGill University's School of Computer Science and a Canada CIFAR AI Chair at Mila. His research focuses on machine learning, particularly representation learning with an emphasis on geometry, symmetry, and probabilistic inference. He has held academic positions at the University of British Columbia and was a postdoctoral fellow at Carnegie Mellon University. Education: B.Sc. in Computer Science, Sharif University of Technology M.Sc. and Ph.D. in Computer Science, University of Alberta (supervised by Russ Greiner) Postdoctoral Fellowship at Carnegie Mellon University (with Barnabás Póczos and Jeff Schneider) His research interests span geometric deep learning, equivariant networks, reinforcement learning, and AI for scientific applications. Notable contributions include work on symmetry-aware models, diffusion processes, and equivariant representation learning. Publications highlight advancements in causal abstraction, diffusion-based anomaly detection, and equivariant architectures for crystals and hierarchical structures. His work often bridges theory and application, emphasizing symmetry principles. Advising & Grants: Supervised over 20 graduate students and postdocs, including recent PhD graduates Daniel Levy and Mehran Shakerinava Active in mentoring M.Sc. and internship students He contributes to academic leadership roles at Mila and McGill, fostering interdisciplinary collaborations in AI research.

• Computer Vision
• Computer Graphics
• Geometric Deep Learning
• +1 more

Andrea Tagliasacchi is an Associate Professor and holder of the Visual Computing Research Chair at the School of Computing Science, Simon Fraser University (SFU). His research focuses on Computer Vision, Computer Graphics, Geometric Deep Learning, and 3D Perception. He holds a BSc and MSc from Politecnico di Milano (2005, 2007), a PhD from SFU (2013), and completed a postdoctoral fellowship at EPFL (2015). Education: BSc, Politecnico di Milano, 2005 MSc, Politecnico di Milano, 2007 PhD, Simon Fraser University, 2013 Postdoctoral Fellow, EPFL, 2015 His research interests span advanced topics in geometric deep learning and 3D perception, with applications in computer vision and graphics. He leads or contributes to initiatives like the Tangent Lab and engages in academic-industry collaborations through roles like the Visual Computing Research Chair. Contact him via email for admissions or inquiries. Awards & Affiliations: Visual Computing Research Chair He currently does not teach active courses but remains actively involved in research supervision and academic leadership.

Pierre-Yves LajoieView profile

Assistant Professor

• Robotics
• Computer Vision
• Artificial Intelligence
• +5 more

Pierre-Yves Lajoie is an Assistant Professor in the Department of Computer Engineering and Software Engineering at Polytechnique Montréal, a leading engineering school affiliated with Université de Montréal. His research focuses on robotics and artificial intelligence, with specialization in robotic perception for single and multi-agent systems. He has held research positions at prestigious institutions including the Massachusetts Institute of Technology (2019), Samsung AI Center (2023), and University of Oxford (2024). Education: Ph.D. in Computer Engineering, Polytechnique Montréal Dr. Lajoie's research interests span across robotics, computer vision, and distributed systems. He specializes in developing algorithms for robotic perception in challenging environments, with applications in aerial, underground, indoor, and space robotics. His work focuses on enabling robots to understand their surroundings through visual and sensor data, particularly in collaborative multi-robot scenarios where communication may be limited or unreliable. His primary research center of excellence is the Industry of the Future and Digital Society, with secondary centers in Modeling and Artificial Intelligence and New Frontiers in Information and Communication Technologies. His publication record demonstrates a strong focus on collaborative SLAM (Simultaneous Localization and Mapping) systems, with recent work addressing challenges in planetary exploration, swarm robotics, and pedestrian positioning. His research combines computer vision, machine learning, and distributed systems to create robust solutions for real-world robotic applications, particularly in environments with communication constraints. Scientific Awards: Vanier Canada Scholarship Best Paper Award at IEEE ICC 2024 Dr. Lajoie is actively recruiting graduate students for PhD and Master's programs, with openings for Fall 2025 and Spring 2026. He encourages students to apply for various scholarship opportunities including NSERC, FRQ, and IVADO scholarships at multiple academic levels. His research is supported by collaborations with academic and industrial partners, focusing on applications in space robotics, automated manufacturing, and service robotics. He has supervised research projects in areas such as search and rescue with sparsely connected swarms and distributed risk-aware exploration systems.

Dana CobzasView profile

Associate Professor

• Computer Vision
• Medical Imaging
• Image Segmentation
• +7 more

Dana Cobzas is an Associate Professor at the MacEwan University in the Department of Computer Science , with adjunct appointments at the University of Alberta. Her academic journey includes a PhD in Computer Science (University of Alberta, 2004) MSc in Mathematics (Babes-Bolyai University, 1998) BSc in Mathematics (Babes-Bolyai University, 1997) . Her research focuses on imaging and computer vision , particularly mathematical models for medical image processing . Key areas include Medical image segmentation and registration 3D modeling from uncalibrated images Sparse classification for population studies Dynamic vision (tracking and modeling) Medical applications in neuroimaging and oncology . She has developed advanced techniques like deep learning-integrated level set methods and FEM-based segmentation. Scientific recognition includes: NSERC Discovery Grant (2015, 2010) Best Vision Paper at IEEE ICRA 2005 Best Student Paper at Vision Interface 2003 . She is actively involved in teaching and mentoring , with experience supervising senior students’ independent studies and contributing to collaborative projects in robotics and biomedical engineering .

Chengzhou TangView profile

Assistant Professor

• 3D Computer Vision
• Deep Learning
• Robotics
• +3 more

Chengzhou Tang is an Assistant Professor in the Department of Computer Science at the University of Manitoba. His research focuses on 3D computer vision, deep learning, robotics, and embodied artificial intelligence. He leads the Spatial Intelligent System (SPINS) Lab, exploring topics such as 3D object reconstruction, camera localization, and video processing techniques. His work spans applications in robotics, virtual reality, and computational imaging. Dr. Tang's research interests include developing novel algorithms for multi-view diffusion models, deep recurrent optimizers, and subspace methods. He has contributed to advancements in video depth estimation, point cloud processing, and stabilization of 360-degree videos. His recent work emphasizes generative models and embodied AI, addressing challenges in sparse-view 3D reconstruction and scene-agnostic camera localization. His publications reflect a trend toward integrating deep learning with traditional computer vision problems, such as structure-from-motion and SLAM (Simultaneous Localization and Mapping). The SPINS Lab collaborates on projects involving global bundle adjustment networks and initialization-robust monocular SLAM systems. While no awards or grants are explicitly listed, his active publication record indicates sustained research engagement in these areas. Dr. Tang’s academic profile highlights his contributions to foundational techniques in computer vision and their practical applications in robotics and AI systems. His work bridges theoretical advancements with real-world challenges in imaging and spatial intelligence.

Farida CherietView profile

Professor

• Biomedical technology
• Artificial intelligence
• Medical imaging
• +4 more

Dr. Farida Cheriet is a Full Professor in the Department of Computer Engineering and Software Engineering at Polytechnique Montréal . She serves as Director of the 4D Imaging and Vision Laboratory (LIV4D) and holds membership in the Institute of Biomedical Engineering and the Institute for Data Valorization (IVADO) . Her research spans medical imaging , biomedical technology , artificial vision , and 3D movement estimation . Ph.D. (Montreal), DEA (France), Ing. (Algeria) Her work focuses on interpretable AI models for retinal pathology diagnosis, 3D anatomical reconstruction from medical imaging, and automated segmentation of vascular and spinal structures. She leads innovations in deep learning applications for diabetic retinopathy screening, coronary artery analysis , and spine surgery planning . Recent publications highlight her leadership in computer vision for biomedical applications, with 15 featured articles covering ICU readmission prediction, retinal vessel analysis, dental crown design, and spinal ultrasound processing. She received CFI funding (2021) for cutting-edge facilities and collaborates on pan-Canadian ophthalmic image databases (2018). Dr. Cheriet has supervised 28 Ph.D. students and 46 Master's students in biomedical computing, including projects on scoliosis analysis, retinal imaging, and cardiac MRI. Her teaching includes digital communications and computer graphics courses.

Pavol FederlView profile

Assistant Professor

• Computational Biology
• Computer Graphics
• Biological Modeling
• +4 more

Pavol Federl is an Assistant Professor (Teaching) in the Department of Computer Science at the University of Calgary, Faculty of Science. His research focuses on computational modeling in biological systems, particularly plant growth, fracture mechanics, and interdisciplinary applications of L-systems. He holds a PhD (2002), MSc (1997), and BSc (1995) in Computer Science from the University of Calgary. Research Interests Biological modeling using L-systems Fracture formation in growing materials Computer graphics and interactive simulation environments Plant growth dynamics and pattern formation His work integrates mathematical modeling with computational techniques to study natural phenomena, such as leaf venation patterns and tree bark fracture. Recent research highlights include: Developmental models of multicellular structures Finite element analysis of fracture dynamics Interactive design tools for bonsai tree modeling Grants and Advising No specific grants or advisees are listed in the provided text. His teaching includes courses such as CPSC 457: Principles of Operating Systems. Professional Contributions He has contributed to software development in virtual laboratories and license plate recognition systems, demonstrating expertise in both theoretical and applied computing.

Craig S. KaplanView profile

Professor

• Computer Graphics
• Computational Geometry
• Mathematical Art
• +4 more

Craig S. Kaplan is a Professor at the University of Waterloo's David R. Cheriton School of Computer Science within the Faculty of Mathematics. His research bridges computer science and mathematical art, focusing on computational geometry, geometric pattern design, and algorithmic art. He holds degrees including a Ph.D. and M.Sc. from the University of Washington (2002, 1998) and a B.Math. from the University of Waterloo (1996). His work spans applications of mathematics in art and design, including Islamic geometric patterns, computer graphics, and computational geometry. Notable contributions include developing methods for generating Islamic geometric patterns, exploring aperiodic tilings (including the discovery of an aperiodic monotile in 2023), and creating tools for artistic visualization like RepulsionPak and FlowPak. He also engages with digital art forms such as generative algorithms, stereoscopic 3D rendering, and interactive applications for mindfulness and VR. His publications reflect a focus on geometric algorithms, pattern generation, and interdisciplinary art-science projects. Though no explicit awards are listed, his prolific output and contributions to mathematical art suggest significant recognition in his field. His work often emphasizes computational methods for artistic expression, combining rigorous mathematics with creative outcomes.

Roie LevinView profile

Assistant Professor

• Approximation Algorithms
• Online Algorithms
• Submodular Functions
• +5 more

Roie Levin is an Assistant Professor at Rutgers University's Department of Computer Science. He received his PhD in Algorithms, Combinatorics and Optimization from Carnegie Mellon University in 2022, advised by Anupam Gupta. Prior to that, he worked at the Allen Institute for Artificial Intelligence (2015-2017) and earned dual BSc degrees in Computer Science/Applied Mathematics and Mathematics from Brown University (2015). Before joining Rutgers, he was a Fulbright Postdoctoral Fellow at Tel Aviv University under Niv Buchbinder. Current Role: Assistant Professor in Computer Science Academic Training: PhD (2022) CMU, BSc (2015) Brown University Postdoctoral: Fulbright Fellow at Tel Aviv University Levin's research focuses on approximation algorithms for uncertain environments (online/dynamic/streaming models) and submodular function optimization. His work spans theoretical foundations and practical implementations across distributed systems, geometric constraints, and reinforcement learning paradigms. Teaching includes graduate and undergraduate algorithms courses (CS 344, CS 513) with emphasis on problem-solving techniques, computational complexity, and modern algorithmic trends. His publications showcase expertise in online algorithms, submodular optimization, and approximation theory with applications in clustering, caching, and machine learning. The 2025 articles demonstrate continued exploration of online consistency and contention resolution, while 2023-2024 works focus on submodular optimization under uncertainty and dynamic environments. Earlier publications (2015-2017) cover semantic parsing, geometric approximation, and planar graph optimization. Fulbright Postdoctoral Fellow Levin's research connects theoretical guarantees with practical implementations, bridging classical algorithm design with modern machine learning applications. His recent work explores primal-dual methods in online settings and robust subspace approximation techniques for streaming data environments.