Find Academic Supervisors

Xin FuView profile

Professor

• Computer Architecture
• Machine Learning
• Energy-Efficient Computing
• +2 more

Dr. Xin Fu is a Professor in Electrical and Computer Engineering at the University of Houston's Cullen College of Engineering, holding a PhD from the University of Florida. His research spans computer architecture, energy-efficient systems, machine learning acceleration, and hardware reliability, with applications in edge computing and quantum systems. Awarded the NSF CAREER Award and named Miller Scholar, he leads innovations in heterogeneous computing architectures. Research focuses on optimizing hardware-software co-design for AI workloads, with current projects in federated learning optimization, quantum computing reliability, and neural network acceleration. Recent publications demonstrate cross-cutting work in mobile AI deployment, adversarial defense mechanisms, and quantum error correction. Honors include: NSF Faculty Early CAREER Award (2014) Four-time recipient of competitive NSF research grants Miller Scholar recognition for teaching and research excellence

Rui DaiView profile

Associate Professor

• Wireless Sensor Networks
• Multimedia Communications
• Video Analytics
• +2 more

Dr. Rui Dai is an Associate Professor in the Department of Computer Science at the University of Cincinnati's College of Engineering and Applied Science. Her research focuses on wireless sensor networks, multimedia communications, and video analytics for healthcare and surveillance applications. She directs multiple NSF and NIST-funded projects on perceptual-quality-aware video systems. Research interests include quality-of-experience optimization for video analytics, compressed domain feature extraction, and edge computing frameworks for intelligent surveillance. Recent work develops deep feature compression techniques, multi-camera fall detection systems, and quality-aware video distribution strategies for 5G networks. Publications demonstrate consistent innovation in video processing for resource-constrained environments, with applications spanning healthcare monitoring, public safety networks, and embedded vision systems. Current projects investigate metaverse communication challenges for 6G networks and PHP vulnerability detection through hybrid static-fuzzing analysis.

Andrew MaidenView profile

Professor

• Computational Optics
• Ptychography
• Coherent Diffractive Imaging
• +5 more

Professor Andrew Maiden is a faculty member at the University of Sheffield's School of Electrical and Electronic Engineering, specializing in Computational Imaging. He leads the Semiconductor Materials and Devices Research Group. His research focuses on advancing optical systems through computational methods like ptychography, which enhances microscopy and imaging precision. With a PhD from Durham University (2005) and an MEng from the University of Birmingham (2001), Maiden's career includes pioneering work with Professor John Rodenburg on ptychography and a brief industry stint commercializing microscopy technologies. He teaches Digital Signal Processing (DSP) to third-year students and advises researchers such as Cao S (PhD graduate). Research interests include Coherent Diffractive Imaging (CDI), electron microscopy phase imaging, and inverse problem solutions. His work bridges computational algorithms with practical applications in optics and materials science. Maiden has contributed to over 50 peer-reviewed publications and holds patents on ptychography-related imaging techniques. His lab focuses on developing high-resolution imaging tools without traditional lenses, emphasizing low-dose radiation and high-throughput bio-imaging. Teaching and mentorship play key roles in his academic contributions, shaping future engineers in signal processing and computational methods. Collaborations span academia and industry, reflecting his dual focus on innovation and real-world application.

Ahmet TekalpView profile

Professor

• Digital Image Processing
• Video Compression
• Motion-Compensated Video Filtering
• +5 more

Ahmet Tekalp is a Professor in the Department of Electrical and Computer Engineering at Koc University's College of Engineering since 2001. He holds dual citizenship in Turkey and the USA, with prior academic roles at the University of Rochester (1986-2005) and research positions at Eastman Kodak (1984-1987) and Rensselaer Polytechnic Institute (1981-1984). He chairs the Electronics and Informatics Group at TUBITAK since 2004 as a part-time position. B.S. (1980) in Electrical Engineering & Mathematics, Bogaziçi University M.S. (1982) and Ph.D. (1984) in Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute His research focuses on digital image and video processing, including video compression, motion-compensated filtering for high-resolution applications, video segmentation, object tracking, content-based video analysis, multi-camera surveillance processing, and digital content protection. He has led numerous European and U.S. grants, including FP7 STREP projects and NSF awards, emphasizing applications in sensor networks, visual databases, and medical imaging. His scholarly work spans diverse areas such as superresolution reconstruction, head gesture animation, 3DTV streaming, and reversible data hiding. He has played pivotal roles in editorial boards, including serving as Editor-in-Chief of Signal Processing: Image Communication, and has contributed to major standards bodies like ISO MPEG and ANSI NCITS. Member, Turkish Academy of Sciences (TUBA) Fellow, IEEE Fulbright Senior Scholarship (1999) TUBITAK Science Award (2004) IEEE Signal Processing Society Distinguished Lecturer (1998) He has led multiple international research collaborations and projects, including European FP6/FP7 networks and NATO programs, with substantial grant funding from NSF, NYSTAR, and industry partners like Eastman Kodak, Xerox, and Siemens.

Fangneng ZhanView profile

Research Fellow

• Computer Science
• Artificial Intelligence
• Neural Rendering
• +7 more

Currently a Research Fellow at Harvard University & MIT , Fangneng Zhan specializes in Neural Rendering and Generative AI . His research focuses on developing evolutive rendering frameworks, 3D-aware generative models, and multimodal synthesis techniques. Previously, he was a postdoctoral researcher at the Max Planck Institute for Informatics under Prof. Christian Theobalt. He earned his Ph.D. in Computer Science & Engineering from Nanyang Technological University, Singapore and a Bachelor's in Communication Engineering from the University of Electronic Science and Technology of China . His work spans 3D reconstruction, robotics applications , and lighting estimation , with significant contributions to SIGGRAPH , NeurIPS , and CVPR conferences. Recent research highlights include evolutive gauge transformations for neural fields, generalizable 3D style transfer via Gaussian splatting, and multimodal synthesis frameworks leveraging pre-trained models like CLIP and Stable Diffusion. He has co-authored Top50 Popular Paper in TPAMI 2023 and organized workshops at CVPR 2024 on generative models. Scientific Awards: Top50 Popular Paper, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2023 Collaborative Network: Mentored students at institutions like Harvard, NTU, and ETH Zurich. His projects include datasets for lighting estimation and real-time scene text detection systems.

Blaž ZupanView profile

Professor

• Artificial Intelligence
• Machine Learning
• Explainable AI
• +4 more

Blaž Zupan is a Full Professor at the University of Ljubljana, also affiliated with Baylor College of Medicine in Houston, teaching artificial intelligence and machine learning. He leads a fifteen-member bioinformatics laboratory and has authored over one hundred publications with more than ten thousand citations, reflecting significant impact in computational sciences. His research centers on explainable AI, machine learning, and data visualization, with deep applications in bioinformatics. He pioneered the Orange data mining suite—a visual programming tool for accessible analytics—and bioinformatics platforms like dictyExpress for gene expression analysis and GenePath for genetic network discovery, emphasizing user-friendly interfaces and real-world usability. Analysis of his recent publications reveals a trajectory from foundational AI (e.g., concept hierarchies in 1999) to contemporary bioinformatics, with current work focusing on single-cell genomics, batch-effect correction, and democratizing AI through visual programming. His tools bridge computational methods and biological discovery, particularly in systems biology and genomics. Zupan’s accolades include the Zois Award (2010), two University of Ljubljana Golden Plaques (2011, 2019), a Fulbright Scholarship (2013), and six student-voted Best Teacher Awards (2008–2017). He was named among the Top 100 Most Influential Innovators of Central and Eastern Europe (2016) by Res Publica, Financial Times, and Google. He secures substantial research funding, currently leading projects like KATARINA (computer science education for all), DALI4US (data literacy for primary schools), DANIO-ReCODE (genomics of regeneration), and L2-60154 (explainable AI for gene expression). Past projects span AI systems (2009–2020), drug discovery, and systems biology, demonstrating sustained interdisciplinary impact. As head of the Bioinformatics Laboratory, he fosters collaboration between computer science and biology, developing open-source tools that empower researchers globally. His consulting for industry and public organizations extends his influence into data-driven decision support and AI training.

Edward V. DiBellaView profile

Professor

• Advanced MRI Imaging
• Positron Emission Tomography
• Image Processing
• +5 more

Edward V. DiBella, PhD, is a Professor in the Department of Radiology & Imaging Sciences at the University of Utah School of Medicine, where he serves as director of the Utah Center for Advanced Imaging Research (UCAIR). He holds adjunct faculty appointments in Bioengineering and is affiliated with the Center for Arrhythmia Research and Management (CARMA) and the Experimental Therapeutics Program in the Huntsman Cancer Institute. Dr. DiBella leads the Cardiovascular MRI Group, focusing on developing advanced imaging techniques for cardiac applications. Dr. DiBella's educational background includes a Master's degree from the University of Vermont and a PhD from the Georgia Institute of Technology, followed by postdoctoral training at the University of Utah Department of Radiology. His research spans over two decades of contributions to medical imaging science. His primary research interests center on improving MRI acquisition, reconstruction, and post-processing techniques, with particular emphasis on cardiac, cancer, and stroke applications. Dr. DiBella's work addresses fundamental challenges in medical imaging including motion artifacts, image reconstruction from undersampled data, quantitative perfusion analysis, and advanced techniques for cardiac imaging. His group has pioneered radial simultaneous multi-slice (SMS) approaches for myocardial perfusion MRI that enable whole-heart coverage without gating. Analysis of Dr. DiBella's recent publications reveals a strong focus on deep learning applications in MRI reconstruction, quantitative myocardial perfusion techniques, and advanced diffusion imaging for stroke recovery prediction. His work demonstrates a consistent trajectory toward more efficient, accurate, and clinically applicable imaging methods that address real-world challenges in cardiac MRI. Dr. DiBella has mentored numerous graduate students and postdoctoral researchers who have gone on to successful careers in academia and industry. His laboratory maintains active collaborations with cardiology, electrophysiology, and bioengineering departments, reflecting the interdisciplinary nature of modern medical imaging research. Current projects in Dr. DiBella's Cardiovascular MRI Group include Deep Learning for Radial SMS Reconstruction, Diffusion imaging for predicting stroke recovery, Quantitative myocardial perfusion, and Radial SMS for myocardial perfusion MRI. The group's work is particularly relevant to heart failure, coronary artery disease, and atrial fibrillation diagnosis and management, addressing the fact that heart disease remains the leading cause of death worldwide.

Detlev MarpeView profile

Researcher

• Video Coding
• Image Compression
• Signal Processing
• +3 more

Detlev Marpe is a leading researcher at the Fraunhofer Heinrich Hertz Institute (HHI), serving as Head of the Video Coding & Analytics Department and Head of the Image & Video Coding Group. His work focuses on advancing video compression standards, including HEVC (H.265) and its extensions. He has contributed significantly to tools like entropy coding, transform coding, and scalable video coding. His research emphasizes efficient compression techniques, such as adaptive context models and wavelet-based methods, with applications in multimedia communication and low-delay video encoding. Affiliations: Fraunhofer Institute for Telecommunications HHI, Berlin, Germany Roles: Department Head, Research Group Leader, and Adjunct Lecturer at TU Berlin (2013/14) Research Interests: Video coding standards (HEVC, H.264/AVC), entropy coding (CABAC), wavelet-based compression, scalable video coding (SVC), multiview video coding (MVC), and rate-distortion optimization. His work bridges theoretical advancements with practical implementations, addressing challenges in compression efficiency, scalability, and real-time applications. Publications & Awards: Over 200 publications in top-tier journals and conferences, including IEEE Transactions and SPIE. Notable awards include the Chester Sall Best Paper Award and multiple Best Paper Awards from IEEE journals. His contributions to video coding standards have been adopted in global specifications like MPEG and ITU-T. Grants & Labs: Involved in major research projects on HEVC extensions, 3D video coding, and low-delay applications. Collaborates with industry partners and academic institutions globally. His team at HHI develops reference software and test models for emerging standards.

Jianke ZhuView profile

Professor

• Computer Vision
• Machine Learning
• 3D Reconstruction
• +3 more

Jianke Zhu is a Professor at the College of Computer Science and Technology of Zhejiang University . He obtained his Ph.D. in Computer Science and Engineering from The Chinese University of Hong Kong and conducted postdoctoral research at the BIWI Computer Vision Lab, ETH Zurich . His research focuses on Computer Vision and Machine Learning , with a particular emphasis on 3D scene understanding, LiDAR-based mapping, and neural rendering. Dr. Zhu’s research spans several subfields, including 3D Reconstruction , Semantic Segmentation , Multimodal Learning , and Autonomous Driving . His work integrates Neural Networks , LiDAR Processing , and Uncertainty Quantification to address challenges in real-time and adverse conditions. Selected Recent Trends: 2025 publications highlight his work in Hexagonal Mesh-based Neural Rendering , Instance-aware 3D Scene Understanding , and Efficient Visual Projectors for Multimodal LLMs . Earlier works include Box2Mask for Instance Segmentation (2024) and Token Selection for Point Cloud Learning (2025). Scientific Awards : Senior member of the IEEE Advising and Grants : As a Doctoral Supervisor , he mentors students in advanced topics like LiDAR Odometry and Multi-view Stereo Recovery . His projects have attracted funding for autonomous driving , 3D scene modeling , and neural rendering .

Seunghwa JeongView profile

Professor

• Video Processing
• Virtual Reality
• Machine Learning
• +7 more

Seunghwa Jeong is a Professor in the Department of Contents Software at Sejong University. He holds a Ph.D. (2024) and M.S. (2015) from the Korea Advanced Institute of Science and Technology (KAIST), and a B.S. (2006) from Pusan National University. His professional experience includes serving as CEO at KAI Inc. (2022-2023) and Technical Lead at the same company (2015-2021). His research focuses on two interconnected domains: Immersive Video Processing including VR systems, multi-view environments, and 4D free-viewpoint technologies, and ML-based Video Processing covering video compression, super-resolution, and object detection/segmentation techniques. Recent publications demonstrate a strong focus on real-time video enhancement using deep learning, interactive 360° viewing systems, and consistent object segmentation across multiple viewpoints. His work appears in premier journals including IEEE Transactions on Pattern Analysis and Machine Intelligence and ACM Transactions on Graphics.

Bahram JavidiView profile

Professor

• Real-time multi-dimensional imaging
• Nanotechnology in optical sensing
• Biomedical optics/photonics
• +4 more

Bahram Javidi is a Professor in the Department of Biomedical Engineering at the University of Connecticut. His research focuses on advanced optical imaging technologies, including real-time 3D sensing, visualization, and information processing. He integrates nanotechnology, biomedical photonics, and quantum optics into novel imaging systems for medical and underwater applications. Key Research Areas: 3D integral imaging, digital holography, compressive sensing, optical encryption, and biomedical imaging. Recent Publications: Highlight innovations in underwater signal detection, lensless imaging for disease screening, and adversarial attack defense using optical systems. Technological Impact: Develops portable, low-cost medical diagnostic tools and augmented reality visualization systems. Collaborations: Works with interdisciplinary teams in biomedical engineering, computer science, and optical physics.

Zhewei WangView profile

Visiting Assistant Professor

• Deep Learning
• Machine Learning
• Medical Image Analysis
• +5 more

Zhewei Wang is a Visiting Assistant Professor in Artificial Intelligence at the School of Electrical Engineering and Computer Science (EECS) within the Russ College of Engineering and Technology at Ohio University. He holds a Ph.D. and M.S. in Computer Science and Biomedical Engineering from Ohio University (2020 and 2019, respectively), as well as an M.S. in Electronic Engineering from Wuyi University (2011) and a B.S. in Telecommunications Engineering from the University of Electronic Science and Technology of China. Prior to his current role, he conducted research at Massachusetts General Hospital of Harvard Medical School from 2021 to 2023. His research interests span deep learning, machine learning, medical image analysis, computer vision, natural language processing, reinforcement learning, and graph networks. Notable contributions include work on plasmonic nanoparticles for medical diagnostics, semi-supervised learning for medical imaging, and spiking neural networks for speech enhancement. Recent publications highlight advancements in medical imaging, speech processing, and neural network architectures. Key areas of focus include vessel segmentation in X-ray angiography, MRI conversion techniques, and Alzheimer’s disease staging through metric learning. His interdisciplinary research bridges AI with biomedical applications, emphasizing practical solutions in healthcare and diagnostics. No scientific awards or grants are explicitly listed in the provided information. His academic advising and student mentorship details are not detailed here. He has contributed to collaborative projects at Ohio University and Harvard Medical School, reflecting his commitment to cutting-edge AI research.

Marco GrangettoView profile

Professor

• Computer Vision
• Image Processing
• Artificial Intelligence
• +5 more

Marco Grangetto serves as Full Professor in the Department of Computer Science at the University of Turin, coordinating research in image processing and computer vision. His expertise spans wavelets, image/video coding, data compression, error resilient video coding, and biomedical image processing, with significant contributions to ISO JPEG2000 standardization and editorial roles in IEEE Transactions on Multimedia. His educational background includes a PhD in Electrical and Communications Engineering (2003) and MSc in Telecommunications Engineering (1999), both from Politecnico di Torino. His research integrates Artificial Intelligence and Deep Learning with medical imaging and fundamental compression theory , producing innovations in neural network pruning, capsule networks, and entropy-based models. Recent work focuses on Covid-19 diagnosis from chest X-rays and efficient 3D scene modeling. His publication trends reveal dual trajectories: applied medical AI (Covid-19 diagnostics, lung cancer segmentation) and theoretical advances (learned compression, contrastive learning, bias mitigation). This bridges clinical validation with information-theoretic foundations, particularly in resource-constrained environments. Scientific recognition includes: Premio Optime by Unione Industriale di Torino (2000) Fulbright Grant for research at UC San Diego (2001) He maintains leadership through IEEE editorial positions, ISO standardization participation, and MPAI membership. His research group develops medical datasets (UniToChest, UniToPatho) while advancing neural network efficiency for clinical deployment. Current projects focus on entropy minimization techniques and unbiased representation learning for healthcare applications.

• Image and Video Processing
• Multimedia Analysis
• Computer Vision
• +5 more

Prof. Tan Yap Peng is a Professor and Chair of the School of Electrical & Electronic Engineering at Nanyang Technological University (NTU), Singapore. He holds the President's Chair in Electrical and Electronic Engineering and serves as Associate Vice President (Lifelong Learning – Postgraduate Programmes by Coursework). His research focuses on multimedia analysis, computer vision, machine learning, and data analytics. He earned his B.S. from National Taiwan University and M.A./Ph.D. from Princeton University. He has led major initiatives including the INFINITUS Infocomm Research Centre and contributed to IEEE technical committees. His over 200 publications span image/video processing, neural network robustness, and cross-modal systems. Awards include IEEE Fellow status. Education: B.S. Electrical Engineering (NTU), M.A./Ph.D. (Princeton) Research interests emphasize interactive digital media, content-based analysis, and AI-driven solutions for visual and signal processing. His work addresses challenges in adversarial attacks, video generation, and low-light image enhancement. He has held editorial roles at IEEE Transactions and EURASIP journals. Conference leadership includes chairs for ICME and ICIP. His contributions bridge academia and industry through collaborative research networks.

Zhiqiang TaoView profile

Assistant Professor

• Machine Learning
• Computer Vision
• Computational Imaging
• +7 more

Zhiqiang Tao is an Assistant Professor in the School of Information at the Golisano College of Computing and Information Sciences, Rochester Institute of Technology (RIT). Prior to RIT, he served as an Assistant Professor at Santa Clara University (2020–2022). He holds a Ph.D. from Northeastern University (ECE Department) and B.E. and M.E. degrees from Tianjin University. Research Focus: His research group develops smart, scalable, and secure machine learning algorithms for healthcare, AI education, computational imaging, and data science. Key areas include large vision-language models (LVLMs), calibrated uncertainties in low-level vision, ranking fairness, and multimodal understanding. Recent works explore LLM fairness, medical question-answering systems, and diffusion models for text-video retrieval. Awards & Honors: RIT GCCIS Emerging Scholar Award (2025) Teaching: IDAI-780: Capstone Project ISTE-780: Data-Driven Knowledge Discovery Advising & Team: Actively seeking motivated graduate/undergraduate students to join his research group. His team has produced impactful work in NeurIPS, CVPR, ECCV, and IEEE TPAMI/TKDE. Labs & Collaboration: Collaborates across disciplines to advance AI applications in healthcare and education, leveraging computational imaging and fair ML principles.