Maggie Zhu (Fengqing Maggie Zhu) is an Assistant Professor at Purdue University's Department of Electrical and Computer Engineering, College of Engineering. She holds a Ph.D. in Electrical and Computer Engineering from Purdue (2011) and has focused on image processing, video compression, computer vision, and computational photography since joining the faculty in 2015. Ph.D. in Electrical and Computer Engineering (2011) Assistant Professor at Purdue (2015–present) Staff Researcher at Huawei Technologies (2012) Her research bridges machine learning with practical applications in image compression , 3D reconstruction , and nutrition analysis , particularly through wearable technologies and edge-cloud systems. Recent work includes class-incremental learning for 3D perception and low-rank adaptation for efficient vision models. Scientific awards include: Huawei Certification of Recognition (2012) NIH mHealth Summer Institute Participant (2011) Charles C. Chappelle Graduate Fellowship Motorola Foundation Fellowship She has contributed to food portion estimation using monocular imaging , neural video compression , and domain adaptation methods, with publications spanning learned compression techniques and healthcare applications. Recent grants focus on technology-enabled dietary assessment and collaborative computing frameworks.
Qiang Qiu is an Associate Professor in the Department of Electrical and Computer Engineering at Purdue University's College of Engineering. He actively contributes to the Vertically Integrated Projects (VIP) program, fostering interdisciplinary collaboration between faculty, students, and projects. His research spans machine learning, computer vision, robotics, and generative AI, with particular emphasis on diffusion models, transformer fine-tuning, and graph neural networks. Key themes include improving model generalizability through orthogonal low-rank embeddings, developing efficient parameter-tuning strategies, and advancing visuotactile manipulation in robotics. Recent publications reveal trends in attention control for text-to-image alignment, posterior sampling for diverse image generation, and federated learning security. His work addresses gradient conflicts in machine unlearning and explores multimodal sensing for robotic manipulation.
Prof. Dr. Behçet Uğur Töreyin is a full Professor at the Informatics Institute of Istanbul Technical University, where he also serves as Head of Department since 2023. He leads the Signal Processing for Computational Intelligence (SP4CING) research group, focusing on advanced signal and image processing techniques for intelligent systems. His work spans interdisciplinary applications in bioimaging, environmental monitoring, surveillance, and remote sensing. PhD in Electrical and Electronics Engineering, İhsan Doğramacı Bilkent University (2009) MS in Electrical and Electronics Engineering, İhsan Doğramacı Bilkent University (2003) BS in Electrical and Electronics Engineering, Middle East Technical University (2001) His research interests include signal processing, image processing, machine learning, pattern recognition, deep learning, computer vision, and compressed domain analysis. He has pioneered work in flame detection, video understanding in compressed domains, and efficient neural architectures. His recent publications emphasize green AI, model efficiency, and privacy-preserving techniques. The analysis of his 15 most recent articles (2022–2024) reveals a strong focus on compressed domain processing, efficient deep learning models (e.g., HaLViT), biomedical imaging, and environmental applications. He frequently employs transformer models, CNNs, and hybrid architectures for tasks such as Raman spectroscopy quantification, smoking detection in video, and server fault diagnosis using thermal imaging. Scientist of the Year, SCIENCE HEROES ASSOCIATION (2017) Entrepreneurial and Innovative Graduation Design Project (BTP) Competition, ITU (2016) 2241 Industrial Undergraduate Thesis Competition, TÜBİTAK (2016) Golden Youth, İş Bank (1997) Prof. Töreyin has supervised several students, including Mr. Berk Arıcan, whose M.S. thesis won the best thesis award in computer science at ASELSAN Akademi in 2023. He has led numerous research projects funded by TÜBİTAK and other agencies, including work on quantum machine learning for carbon credit trading and lip-sync error detection in live broadcasts. He actively mentors students and promotes innovation in computational intelligence. He leads the SP4CING research group at ITU, which focuses on designing signal processing techniques for computational intelligence. The group's work integrates deep learning, compressed domain analysis, and multi-modal sensing for real-world applications in healthcare, environment, and industry.
Keith Stein is a Professor of Physics in the Department of Physics & Engineering at Bethel University, within the College of Arts and Sciences. He has been a faculty member since 2001 and is deeply involved in research and student collaboration. His work bridges computational and experimental fluid dynamics, with applications in aerospace and engineering systems. Education: B.A. in Physics, Bethel College, 1987 M.S. in Aerospace Engineering and Mechanics, University of Minnesota, 1989 Ph.D. in Aerospace Engineering and Mechanics, University of Minnesota, 1999 Dr. Stein's research focuses on fluid-structure interactions, particularly in parachute systems, and he utilizes advanced optical and high-speed video imaging to study compressible flows, shock waves, and thermal convection. His work has involved collaborations with the U.S. Army, Rice University’s T*AFSM group, and the University of Minnesota on projects such as the Mars Science Laboratory parachute simulations. He emphasizes student-faculty research partnerships, providing hands-on experience in cutting-edge experimental and computational techniques. His scholarly contributions have been recognized through awards and service. Notably, he received the Department of the Army Research and Development Award and the Bethel Excellence in Scholarship Award . He has also served on the advisory board of the International Journal for Numerical Methods in Fluids . Dr. Stein is actively engaged in mentoring and research leadership. While specific students and publications are not listed, his long-standing involvement in collaborative research suggests a strong advising role. His work continues to contribute to both academic and applied aerospace engineering challenges. He has been affiliated with the Team for Advanced Flow Simulation and Modeling (T*AFSM) at Rice University and has collaborated with the University of Minnesota Department of Aerospace Engineering and Mechanics , particularly on NASA-related parachute dynamics projects.
André Zaccarin is a Professor in the Department of Electrical and Computer Engineering at the College of Engineering, Université Laval, where he has been a faculty member since 1991. He holds a Ph.D. in Electrical Engineering from Princeton University and has maintained a strong research presence in image and video processing, computer vision, and coding algorithms. Ph.D. in Electrical Engineering, Princeton University (1991) M.A., Princeton University (1988) M.Sc. in Electrical Engineering, Université Laval (1987) B.Sc.A. in Electrical Engineering, Université Laval (1985) His research focuses on the study and development of advanced coding algorithms for still images and video sequences. Key areas include dense motion field estimation, model-based coding, 3D motion models, segmentation-based coding, and fast coding algorithms. He also investigates image segmentation, analysis and modeling, with applications in medical imaging and motion estimation for computer vision. Hyperspectral image processing is another significant area of interest. With 61 available publications, his scholarly output reflects sustained contributions in signal and image processing, particularly in compression and computer vision. The body of work shows consistent engagement with algorithmic innovation, motion analysis, and practical implementations in imaging systems. While specific scientific awards are not listed in the provided text, his long-standing academic career and industrial research role suggest recognition within the field. André Zaccarin has supervised multiple student projects, though specific names are not provided. He was also affiliated with Intel Corp. as a Senior Staff Researcher at the Microprocessor Research Labs from 2000 to 2001, indicating industry collaboration. He served as an Invited Researcher at Princeton University during summer 1992. He is affiliated with the Computer Vision and Systems Laboratory at Université Laval, where his research group conducts work in vision systems and image processing technologies.
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.
Oscar Jose Pellicer Valero is a researcher at the Universitat de València, affiliated with the School of Engineering and the Department of Electronic Engineering. He is a member of the Intelligent Data Analysis Laboratory (IDAL) and the Image Processing Laboratory (IPL), both part of the ERI research institute. He completed his PhD in 2022 with a thesis on biomechanical modeling and machine learning for medical image registration in prostate cancer therapy. His research spans artificial intelligence applied to both biomedical and environmental challenges. Key areas include post-COVID syndrome analysis, medical image processing, digital twins of Earth, and extreme climate event modeling. He develops AI-driven tools for data analysis, such as the AIDE and XAIDA4Detection toolboxes, contributing to both healthcare and environmental science. His recent publications (2023–2025) show a strong trend in applying deep learning and AI to understand complex systems—ranging from human health (e.g., long-COVID symptoms, fibromyalgia, renal function) to Earth system science (e.g., fog nowcasting, compound droughts). The interdisciplinary nature of his work bridges medicine, engineering, and climate science. Oscar has not yet received any explicitly mentioned scientific awards. However, his high publication output and involvement in multicenter studies (e.g., LONG-COVID-EXP) indicate active research leadership. He has not supervised any students listed in the data, but his role as a postdoctoral researcher suggests future advising responsibilities. He is involved in software development for scientific applications and contributes to open data and tool dissemination. His work is increasingly focused on explainable AI and digital twins, reflecting emerging trends in trustworthy and human-centered AI systems.
Dr. Binod Bhattarai is a Lecturer (equivalent to Assistant Professor in the US) in the School of Natural and Computing Sciences at the University of Aberdeen, UK. He is also an Honorary Lecturer at University College London and a Co-founder and Adjunct Research Scientist at NAAMII, Nepal. Dr. Bhattarai heads the Multimodal Learning Lab, a cross-border initiative between the University of Aberdeen and NAAMII, Nepal. His educational background includes a PhD in Computer Science from Universite de Caen, France, and previous work experience as a Senior Research Fellow at University College London, a Postdoctoral Research Associate at Imperial College London, and a Data Scientist at Telenor Group, Norway. Dr. Bhattarai's research focuses on developing robust and interpretable machine learning algorithms that can reason across complex, heterogeneous data. His work spans multiple domains including surgical videos, medical imaging, and low-resource languages, with applications in healthcare, energy, and global agriculture. He follows a core philosophy of building AI that is not only powerful but also trustworthy and explainable, with a belief that true intelligence lies in the ability to seamlessly integrate diverse data sources. His publications demonstrate strong trends in multimodal learning, particularly in medical applications. A significant portion of his recent work focuses on gastrointestinal image analysis, out-of-distribution detection in medical contexts, and federated learning approaches for healthcare data. His research often bridges computer vision, natural language processing, and medical imaging to create practical AI solutions for healthcare challenges. Best Paper Award Finalist, MIUA 2025 Runner-up, ARCADE Challenge, MICCAI 2023 Google Cloud Research Innovator, 2022 Outstanding Reviewer Award, BMVC, 2021 Winner FetReg Endoscopic Vision Challenge at MICCAI 2021 Outstanding Reviewer Award, BMVC, 2019 Best Student Paper Award of Image, Video and Multidimensional Signal Processing, ICASSP, 2016 Best Paper Award Runner up, ACM ICVGIP, 2016 DAAD Postdoc Net-AI-Fellow, 2020 (top 22 out of 192) Dr. Bhattarai actively mentors PhD students and research assistants through the Multimodal Learning Lab. Current PhD students include Jardin Ruari (Assessing AI algorithms for Capsule Endoscopy) and Krit Duangprom (Surgical Tool and Hand Pose Estimation). His lab has successfully guided numerous researchers who have gone on to PhD programs at prestigious institutions including MILA, Dartmouth College, University of Utah, and RIT. He has secured multiple research grants including a Co-PI role for "Non-constrast CT Head Image Analysis" funded by The Ronald Sutton Academic Trust (30.8K GBP, 2024-27), and a PI role for "Frontiers Seed Funding" by the Royal Academy of Engineering (20K GBP, 2023-2024). The Multimodal Learning Lab, which Dr. Bhattarai heads, is a cross-border initiative between the University of Aberdeen and NAAMII, Nepal. The lab focuses on developing robust and interpretable machine learning algorithms that can reason across complex, heterogeneous data. Current research projects include explainable anomaly detection in GI endoscopy, surgical vision world models, multimodal federated learning, surgical data science, and synthetic data generation. The lab operates with a global research pipeline that fosters talent and innovation across borders.
Luis Torres Urgell is a Professor at the Department of Signal Theory and Communications, Universitat Politècnica de Catalunya (UPC), affiliated with the Higher Technical School of Telecommunication Engineering of Barcelona. His research focuses on multimedia systems, image processing, and signal processing with notable contributions to video compression, audio-visual indexing, and computer vision applications. He has been actively involved in numerous competitive research projects, including initiatives on genomic data compression and multimedia security. His work spans over 410 academic activities, including over 140 conference presentations and 78 scientific documents. Notable contributions include advancements in face recognition algorithms, distributed video coding, and the development of tools for automated video summarization in sports content. Torres has also made significant strides in education through project-based learning in telecommunications and the integration of virtual ethnography in social web platforms. He has been recognized as a Senior Member of IEEE and received institutional recognition from UPC for his research contributions. His research has been supported by grants from the Spanish and Catalan governments, including projects under the RIS3CAT strategy and the National Plan for Scientific Research.
Shuchin Aeron is an Associate Professor in the Department of Electrical and Computer Engineering at Tufts School of Engineering, with joint appointments in the Departments of Computer Science and Mathematics. He holds a Ph.D. from Boston University (2009) and completed postdoctoral research at Schlumberger Doll Research, focusing on borehole acoustic signal processing. His research spans statistical signal processing, machine learning, compressed sensing, and information theory, with applications in geophysics, bioengineering, and imaging. Aeron has authored over 175 publications and holds patents in acoustic signal processing. He received the NSF CAREER Award (2016) and is a Senior Member of the IEEE. Educations: Ph.D., Electrical Engineering, Boston University, 2009 M.S., Electrical Engineering, Boston University, 2004 B.Tech., Indian Institute of Technology, 2002 Research Interests: Statistical signal processing (SSP), inverse problems, compressed sensing, information theory, convex optimization Machine learning applications in geophysical signal processing, imaging, and bioengineering His work emphasizes optimal sampling and recovery of multidimensional signals, with contributions to compressed sensing architectures and generative models for particle physics experiments. He leads NSF-funded projects on data science and domain generalization, and collaborates with industry partners like Schlumberger and Mitsubishi Electric Research Labs. Awards: NSF CAREER Award (2016) Mitsubishi Electric Research Lab Research Gift (2015) Grants and Funding: NSF HDR TRIPODS (2019–2023) AFOSR: Enabling Trusted Human-Like Artificial Teammates (2018–2023) NSF: Optimal Sampling and Recovery for Multilinear Signals (2013–2016) Aeron teaches advanced courses in probabilistic systems analysis, information theory, and machine learning. He directs the Tufts Data Science undergraduate and graduate programs, and serves on editorial boards of journals including Frontiers in Signal Processing and IEEE Transactions on Geoscience and Remote Sensing .
Glenn Van Wallendael is an Associate Professor at Ghent University's Faculty of Engineering and Architecture , affiliated with the Department of Electronics and Information Systems . He leads research in video coding, digital watermarking, and immersive media technologies. Academic Focus: Video compression standards (HEVC, H.266), AI for multimedia, virtual reality Key Collaborations: iMinds, imec, European research consortia Research Interests include: Video compression algorithms (HEVC, SVC, MV-HEVC) Digital watermarking for copyright protection Machine learning applications in image/video analysis Quality of Experience (QoE) in immersive environments Recent Publications (2024-2025) show expertise in: Deepfake detection using vision transformers Medical image landmarking tools Lightweight geometric approximation methods AI-driven video quality assessment Doctoral Mentorship includes supervising: 2021: Hannes Mareen (video forensics) 2020: Vasileios Avramelos (light field coding) 2017: Johan De Praeter (adaptive video encoding)
Yao-Jen Chang is a researcher specializing in computer vision and machine learning, with significant contributions to 3D reconstruction, image registration, and biometric authentication systems. His work often involves collaboration with Tsuhan Chen at Cornell University and explores active learning frameworks, multi-view object recognition, and reinforcement learning applications. Key research areas: 3D modeling, multimedia security, and video processing Collaborations include National Tsing Hua University and Cornell University Research Trends Recent publications focus on: Deep reinforcement learning for image alignment User-interactive 3D reconstruction Biometric key generation for security Multi-view object recognition algorithms
Nikos Komodakis is a Professor in the Computer Science Department at the University of Crete, Greece, where he develops efficient, scalable and mathematically well-grounded algorithms for analyzing visual data including static natural images, video, and medical image data. His research spans deep learning, computer vision, machine learning, and artificial intelligence with significant contributions to self-supervised learning, few-shot learning, and knowledge distillation techniques. His work demonstrates a strong theoretical foundation combined with practical applications, particularly in medical imaging. Komodakis has published extensively in top-tier computer vision venues including CVPR, ICCV, ECCV, and IEEE Transactions on Image Processing. His recent publications (2022-2025) show a growing emphasis on medical image analysis applications while maintaining strong contributions to fundamental computer vision problems. Notable contributions include novel approaches for unsupervised representation learning that surpass state-of-the-art methods, effective techniques for knowledge distillation (such as the QUEST framework), and innovative frameworks for few-shot visual learning. Komodakis serves on the editorial boards of prestigious journals including the International Journal of Computer Vision, Computer Vision and Image Understanding Journal, and Computational Intelligence Journal. He has been a frequent area chair for major computer vision conferences including CVPR, ICCV, ECCV, and BMVC. Spyros Gidaris received the Ponts Foundation Best Thesis Prize and the University Paris-Est Best Thesis prize under Komodakis' supervision Sergey Zagoruyko received the AFRIF 2018 Thesis Prize for his PhD work supervised by Komodakis His research group has developed influential techniques including Online Bag-of-Visual-Words Generation for Unsupervised Representation Learning, which surpassed previous state-of-the-art methods. The group maintains active GitHub repositories for many of their publications, demonstrating commitment to reproducible research. Current research directions include advancing medical image analysis through deep learning, improving self-supervised learning frameworks, and developing more efficient neural network architectures.
Dr. Lecturer Çağrı KILINÇ is affiliated with Ahievran University, Kırşehir , serving in the Faculty of Engineering and Architecture , Department of Electrical and Electronics Engineering since 2024. Previously, he held full-time research assistant positions at Eskişehir Osmangazi University from 2013 to 2024 and conducted short-term work at Kırşehir Ahi Evran University in 2018 and 2013. Education : PhD in Electrical and Electronics Engineering (2015-2024), MSc in Electrical and Electronics Engineering (2012-2015), BSc in Electrical and Electronics Engineering (2006-2011) from Eskişehir Osmangazi University His research spans Signal Processing , Data Mining , Communication , and Image Processing , focusing on video coding algorithms and educational data analytics. Recent work includes Video Compression techniques leveraging multiple reference frames and Educational Data Mining to model student success factors. He has contributed to international conferences and participated in a TÜBA/TÜBİTAK-funded project (2018-2019) developing unmanned aerial vehicles with advanced payload capabilities. Collaborations include co-authoring with Semih Ergin and Kaya Turgut on melanoma diagnosis applications of feature descriptors.
Ali Cengiz Beğen is a Professor in the Computer Science Department at Ozyegin University in Istanbul. He is also the founder of Networked Media , a technology consulting firm specializing in IP video systems. His career includes technical leadership roles at Comcast and Cisco , where he developed advanced video delivery solutions. Education: PhD in Electrical and Computer Engineering (Georgia Tech, 2006), BSc in Electrical Engineering (Bilkent University, 2001) Research Interests focus on network support for real-time media , including optimized content encoding, low-latency live streaming, and protocol innovation for IP video. His work bridges academic research with industry standards like ISO/IEC JTC1/SC29 (MPEG/JPEG), where he serves as Head of the Turkish National Body . Current projects explore Media-over-QUIC transport , multi-CDN streaming , and reinforcement learning for adaptive streaming. His scientific contributions include 40+ US patents and publications in IEEE Transactions on Multimedia , IETF RFCs, and ACM SIGMM. Awards highlight his impact: Emmy® Award for Technology and Engineering (2020) ACM SIGMM Test of Time Award (2021) SVTA Industry Fellow (2021) ACM Distinguished Member (2020) IEEE Senior Member (2019) Microsoft Bandwidth Estimation Grand Challenge Runner-up (2021) Professional Service includes IEEE Communications Society Distinguished Lecturer (2016-2020) and keynotes at conferences like IEEE ICME and SVTA Webinars . He actively consults for media-tech companies and law firms on video transport standards.
