Find Academic Supervisors

• Image and Video Processing
• Light Field Coding
• Multimedia Signal Processing
• +6 more

Caroline Conti is an Assistant Professor in the Department of Information Science and Technology (ISTA) at ISCTE – University Institute of Lisbon, and an Associate Researcher at the Institute of Telecommunications - IUL, where she is part of the Multimedia Signal Processing Group. She holds a PhD in Information Science and Technology from Iscte (2017), a specialization from Instituto Superior Técnico (2013), and a Bachelor’s in Electrical Engineering from the University of São Paulo (2010). Her research focuses on image and video processing , particularly in light field coding , 3D holoscopic video , and immersive visual technologies . She is a pioneer in light field research in Portugal and has contributed extensively to scalable and robust coding frameworks. Her recent publications emphasize deep learning-based segmentation, disparity estimation, and adaptive over-segmentation for 4D light fields, published in top journals like IEEE Transactions on Image Processing and Signal Processing: Image Communication . IBM Scientific Prize (2017) Scientific Awards ISCTE-IUL (2016, 2014) Best Poster Award at COST Interaction 2014 She has supervised multiple PhD and Master’s students in areas such as deep learning for light field inpainting and saliency detection. She has led and participated in European and national research projects, including the European 3D-ConTourNet and FCT-funded LIMESA. She is actively involved in the academic community as a Guest Editor for Signal Processing: Image Communication and as an Area Chair for IEEE ICIP 2025. She is a founding member and secretary of the Portuguese Chapter of the IEEE Signal Processing Society.

• Artificial Intelligence
• Machine Learning
• Computer Science
• +3 more

Ivan Radosavljevic is a researcher at Singidunum University's Department of Postgraduate Studies, actively contributing to the fields of Artificial Intelligence, Machine Learning, and Software Engineering. His work spans diverse applications including environmental monitoring, educational technology, medical diagnostics, and geospatial systems. Research interests focus on AI-driven solutions for air quality assessment, synthetic dataset generation for semantic segmentation, real estate price prediction from internet ads, and medical imaging analysis. He has developed software tools for remote rendering monitoring, automated grading, and eye-tracking-based code interaction studies. His publications demonstrate expertise in integrating fuzzy logic with GIS for environmental applications, creating innovative educational technologies, and applying machine learning to healthcare diagnostics. Ivan collaborates with colleagues across multiple domains while maintaining a strong focus on practical implementations of artificial intelligence.

Charles MarkhamView profile

Associate Professor

• Computer Science
• Biomedical Engineering
• Machine Vision
• +5 more

Dr. Charles Markham is an Associate Professor in the Department of Computer Science at Maynooth University's Faculty of Science & Engineering. He graduated with a degree in Applied Physics from Dublin City University and earned his PhD in element specific imaging in computerised tomography. His research spans novel imaging systems, biomedical instrumentation, and human-computer interaction with a strong focus on brain-computer interfaces and motion capture technologies. Research Affiliations: Hamilton Institute, ALL Institute Teaching: Robotics, Computer Graphics, Advanced Computer Architecture Professor Markham's research interests center on novel imaging technologies including coded aperture imaging and wide-baseline stereo systems, motion capture and wearable computing with applications in rehabilitation, and mobile machine vision for driving simulation and augmented reality. His work with the Mathematics and Statistics Ecology group demonstrates interdisciplinary interests in ecological modelling . His publication record shows consistent contributions to brain-computer interfaces (2007-2011), driver behavior analysis (2014-2021), motion capture systems (2006-2009), and optical imaging techniques (2001-2008). The research spans multiple disciplines including neuroscience, biomedical engineering, and ecological mathematics. He has supervised several graduate students including D. Kelly (2009 thesis on sign language recognition) and J. Foody (2007 thesis on motion capture biofeedback systems). His collaborations extend across institutions with partnerships at TU Dublin and University College Dublin.

• Computer Vision
• Machine Learning
• Artificial Intelligence
• +5 more

Cem Eteke is a doctoral candidate at the Chair of Media Technology within the Munich Institute of Robotics and Machine Intelligence (MIRMI) at the Technical University of Munich (TUM). His research focuses on semantic image and video synthesis, with an emphasis on explainable generative models, diffusion models, and their applications to semantic communication systems. Education: B.Sc. in Computer Engineering and Electrical & Electronics Engineering (2017), M.Sc. in same field (2019) from Koc University, Istanbul. Professional Experience: Former Data Scientist and AI Engineer, with brief research on high-dimensional non-convex optimization algorithms. Research Trends: His recent publications (2022-2025) highlight advancements in real-time semantic communication, diffusion models for video synthesis, and neural rendering techniques for indoor scene segmentation. Key themes include lossy coding strategies, spatially adaptive conditioning, and temporally consistent generative modeling. Projects: Involved in research initiatives like the Centre for Tactile Internet with Human-in-the-Loop (CeTI) , 5G Testbed Bayern , and KMU-Innovativ: KIMaps , focusing on haptic communication, indoor navigation, and semantic scene understanding.

Felix HeideView profile

Professor

• Computational Imaging
• Computer Vision
• Optics
• +6 more

Felix Heide is a Professor of Computer Science at Princeton University , where he leads the Princeton Computational Imaging Lab . He also serves as Head of AI at Torc Robotics , focusing on full autonomy stacks for self-driving trucks. His research sits at the intersection of optics , machine learning , and computer vision , addressing imaging challenges in harsh environments like dense fog, ultra-low/high illumination, and scattering media. Ph.D. in Computer Science from the University of British Columbia Postdoctoral research at Stanford University His work on computational imaging spans physics-based vision, non-line-of-sight imaging , end-to-end camera design , and robust sensor fusion . He has pioneered techniques for inverse neural rendering , nanophotonic optics , and light-speed AI through optical computing. His recent papers in Nature Machine Intelligence , Science Advances , and top conferences ( SIGGRAPH , CVPR , ICCV ) focus on: Adverse weather imaging (fog, snow, rain) Multi-sensor fusion (LiDAR, radar, gated cameras) Light transport through scattering media Optical metasurfaces and diffractive optics End-to-end optimization of imaging pipelines Event-based vision and polarization cues He has received prestigious awards including the SIGGRAPH Significant New Researcher Award , Sloan Research Fellowship , and Packard Fellowship . His lab's open-source code and datasets enable real-world applications in autonomous driving, microscopy, and augmented reality.

Kebin PengView profile

Assistant Professor

• Computer Vision
• 3D Computer Vision
• Depth Estimation
• +7 more

Dr. Kebin Peng is an Assistant Professor in the Department of Computer Science at East Carolina University's College of Engineering and Technology. He joined ECU in 2024 after working as a Senior Software Engineer at MathWorks (2023-2024) and completing his Ph.D. at the University of Texas at San Antonio (2019-2023). Dr. Peng's research focuses on Computer Vision and Machine Learning, with particular expertise in 3D Computer Vision, Depth Estimation, Point Cloud Detection/Segmentation, and 3D Reconstruction. His work often explores unsupervised learning approaches to solve complex vision problems. He teaches graduate and undergraduate courses including Artificial Intelligence, Software Engineering, and Principles of Programming Languages. His publication record shows consistent contributions to top computer vision venues, with recent papers on monocular depth estimation in dynamic scenes, multi-view 3D reconstruction using transformers, and code clone analysis in VR software. Dr. Peng actively contributes to the research community as a reviewer for major conferences including NeurIPS, CVPR, ICCV, and AAAI. Dr. Peng serves on program committees for multiple prestigious conferences and journals, demonstrating his growing recognition in the computer vision and AI research community. His professional service includes reviewing for Neural Information Processing Systems (NeurIPS) 2024, AAAI Conference on Artificial Intelligence 2024, and multiple CVPR conferences. With his blend of academic research experience from UT San Antonio and industry experience at MathWorks and Samsung Research America, Dr. Peng brings a practical perspective to his teaching and research, connecting theoretical concepts with real-world applications in computer vision and artificial intelligence.

Alessandro LiviView profile

Lecturer

• Neuroscience
• Decision Making
• Brain Imaging
• +4 more

Alessandro Livi, PhD is an Instructor in Neuroscience at Washington University in St. Louis School of Medicine, affiliated with the Padoa-Schioppa Lab. His research focuses on neural mechanisms underlying economic decision making, particularly studying the lateral orbital area in the mouse brain using 2-photon calcium imaging and GRIN lens technology. Dr. Livi's educational background includes: PhD in Neuroscience from the University of Parma (Italy), 2019 MS in Neuroscience from the University of Bologna (Italy), 2014 BS in Psychology from the University of Urbino (Italy), 2012 His research spans multiple domains of neuroscience with particular emphasis on decision making processes, neural representation of economic values, and action cost processing. Dr. Livi employs advanced techniques including 2-photon calcium imaging, electrophysiology, and behavioral neuroscience approaches to investigate how neural circuits represent value and guide economic choices. His work bridges cognitive neuroscience with economic theory, examining neural computations of subjective values during choice processes. Analysis of Dr. Livi's publication record reveals a strong focus on neural mechanisms of decision making, particularly in the orbitofrontal cortex, with significant contributions to understanding mirror neuron systems and action observation networks. His research spans both primate and rodent models, investigating how the brain represents decision variables, action costs, and economic values through advanced neural recording techniques. Dr. Livi has established a robust research profile with 29 publications and over 700 citations according to ResearchGate. His technical expertise includes: 2-photon calcium imaging Electrophysiology Neural data analysis Behavioral neuroscience paradigms Computational modeling of neural data

• Neuropsychology
• Epilepsy
• Neuroimaging
• +5 more

Carrie McDonald, Ph.D., is a Professor In Residence in the Department of Radiation Medicine and Applied Science at UC San Diego. She holds affiliations with the UCSD Multimodal Imaging Laboratory, UCSD Epilepsy Center, UCSD Neuropsychological Associates, and the UCSD Translational Brain Tumor Assessment Clinic. Dr. McDonald obtained her B.S. in Psychology from Eckerd College and her Ph.D. in Clinical and Health Psychology from the University of Florida, followed by specialized training in neuropsychology at UCSD and the V.A. San Diego Healthcare System. Her research examines neuropsychological deficits using advanced neuroimaging techniques, with focus areas including: Predicting postoperative cognitive outcomes in epilepsy surgery patients Language/memory reorganization using structural and functional MRI Neurodegeneration in Alzheimer's disease and aging populations with epilepsy Advanced diffusion imaging for brain tumor monitoring She actively leads NIH-funded projects on brain aging in epilepsy (BRACE study) and multi-site neuroimaging initiatives through ENIGMA-Epilepsy. Dr. McDonald's recent publications (2023-2025) demonstrate strong emphasis on artificial intelligence applications in epilepsy diagnostics, neuroplasticity in bilingual patients, radiation-induced cognitive changes, and international classifications of cognitive disorders. Her work integrates machine learning with clinical neuroimaging to develop predictive models for surgical outcomes. Honors include: NINDS K23 Career Development Award Epilepsy Foundation/American Epilepsy Society Fellowship UCSD Fellowship in Biological Psychiatry and Neuroscience She mentors graduate students and postdoctoral researchers in neuroimaging analysis and neuropsychological assessment methods. Current NIH R01 grants support investigations into cognitive resilience, brain network reorganization, and transdiagnostic biomarkers across epilepsy syndromes. Dr. McDonald directs the Lab of Cognitive Imaging, which focuses on developing novel imaging biomarkers for cognitive outcomes in neurological disorders. The lab collaborates extensively with the UCSD Epilepsy Center and international consortia to translate research findings into clinical practice.

Shree K. NayarView profile

Professor

• Computational Imaging
• Computer Vision
• Computer Graphics
• +5 more

Shree K. Nayar is the T. C. Chang Professor of Computer Science in the School of Engineering at Columbia University, where he heads the Columbia Vision Laboratory (CAVE). He served as Department Chair from 2009-2012 and was Director of Research at Snap Inc. from 2018-2024. Nayar received his PhD from Carnegie Mellon University and has been at Columbia since 1991, progressing from Assistant to Full Professor. His educational background includes a PhD in Electrical and Computer Engineering from Carnegie Mellon University (1990), an MS from North Carolina State University (1986), and a BS from Birla Institute of Technology in India (1984). He began his career as a Research Engineer at Taylor Instruments in New Delhi before pursuing graduate studies. Nayar's research spans three interconnected areas: novel computational cameras that capture new forms of visual information, physics-based models for vision and graphics, and algorithms for scene understanding. His work in computational imaging has transformed digital photography, with applications in smartphones, robotics, virtual reality, and human-computer interfaces. His research has produced over 300 publications with nearly 60,000 citations and 80 patents. Analysis of his recent publications reveals a strong focus on computational imaging challenges including low-light vision, depth sensing, mobile interaction, and accessibility technologies. His work consistently bridges theoretical foundations with practical applications, as evidenced by commercial implementations of his assorted pixels technology in smartphone cameras. Elected to National Academy of Engineering (2008), American Academy of Arts and Sciences (2011), National Academy of Inventors (2014), and Indian National Academy of Engineering (2022) Okawa Prize (2023), IEEE PAMI Distinguished Researcher Award (2019) Two-time David Marr Prize winner (1990, 1995) - the highest honor in computer vision Multiple best paper awards at major conferences including SIGGRAPH Asia (2024) and ECCV (2024) National Young Investigator Award (1991), Packard Fellowship (1992) Nayar has supervised numerous PhD and Master's students throughout his career at Columbia. His lab has received continuous funding from NSF, industry partners, and foundations. The Columbia Vision Laboratory (CAVE) is known for its interdisciplinary approach, combining optics, hardware design, and algorithms to solve fundamental vision problems. Nayar's Bigshot Camera project demonstrates his commitment to education, providing hands-on learning experiences for students worldwide. The Columbia Vision Laboratory (CAVE) develops cutting-edge computational imaging and computer vision systems. Under Nayar's leadership, the lab has pioneered technologies including self-powered cameras, high dynamic range imaging systems, and novel computational cameras. The lab maintains strong industry connections, particularly through Nayar's role at Snap Research, and emphasizes translating research into real-world applications that benefit society.