جست‌وجوی استاد و پژوهشگر

• Computer Vision
• Computational Imaging
• Non-Line-of-Sight Imaging
• +۷ مورد دیگر

Suren Jayasuriya is a highly active faculty-level researcher in computer vision and computational imaging, with 79 refereed publications (2014-2025) in leading venues such as CVPR, ICCV, ECCV, NeurIPS, IEEE TPAMI and ACM TOG. His work integrates physics-based models with modern machine learning to tackle problems like non-line-of-sight imaging, atmospheric turbulence removal, neural 3D reconstruction, and speech enhancement, while also advancing STEM education through AI. Education & Affiliation: No explicit institutional details are contained in the supplied DBLP extract; however, the sustained publication record and extensive student mentoring indicate a tenured or tenure-track professorship within an engineering or computing department. Research Interests: Jayasuriya’s interests sit at the intersection of computer vision, computational photography, and physics-based machine learning . He develops algorithms that exploit optical and acoustic phenomena for tasks such as seeing around corners, correcting atmospheric distortion, and reconstructing 3D scenes from sparse sonar or radar data. Additional threads include energy-efficient tracking, robust speech processing, and AI-supported pedagogical innovation. Publication Trends: Across the 15 most recent works (2022-2025) his papers exhibit a clear thematic arc: neural representations for multimodal fusion (camera-sonar, radar-vision), unsupervised video restoration under atmospheric turbulence, attention-driven non-line-of-sight tracking, and evaluation of large multimodal models for perceptual reasoning. These contributions simultaneously advance core vision methodologies and demonstrate interdisciplinary applications spanning robotics, environmental monitoring, underwater perception, and education. Students & Mentoring: Jayasuriya has advised an active cohort of graduate researchers who appear repeatedly as co-authors, including Sreenithy Chandran, Ripon Kumar Saha, Albert W. Reed, Joshua D. Rego, Dehao Qin, Jianwei Zhang, Odrika Iqbal, Sameeksha Katoch, Md. Farhan Tasnim Oshim, and Shenbagaraj Kannapiran, among others. Scientific Awards: No awards are listed in the supplied extract; the awards field is left empty. Labs & Teams: While specific laboratory names are not disclosed, the collaborative scope—encompassing hardware-software co-design, field deployments, and educational outreach—suggests he leads or co-leads a research group with access to specialized imaging and robotics facilities.

• Machine Learning
• Deep Learning
• Neural Networks
• +۷ مورد دیگر

Sung-Bae Cho is a prolific researcher in computer science with a publication record spanning over three decades from 1990 to 2025, demonstrating sustained academic productivity and research leadership. Their work primarily focuses on machine learning, neural networks, and their applications across diverse domains including cybersecurity, healthcare, and intelligent systems. Cho's research interests center around advanced machine learning techniques including deep learning architectures, Bayesian networks, and context-aware systems. Their work shows a consistent evolution from traditional neural networks to modern deep learning approaches, with recent publications emphasizing graph neural networks, federated learning, and anomaly detection systems. The research demonstrates strong methodological rigor with applications in practical domains such as traffic prediction, medical diagnosis, and security systems. The publication pattern reveals significant research productivity with multiple high-impact papers annually in reputable venues including IEEE Access, Neurocomputing, and Expert Systems with Applications. Recent work shows particular emphasis on addressing contemporary challenges in machine learning including continual learning, few-shot learning, and privacy-preserving approaches in federated settings. The research demonstrates both theoretical contributions and practical implementations across various application domains. Cho has cultivated an extensive collaborative network with numerous co-authors including Kyung-Joong Kim, Satchidananda Dehuri, Jin-Hyuk Hong, and Seok-Jun Bu, suggesting leadership in research groups and projects. The collaborative pattern indicates supervision of junior researchers and students, though specific advisee relationships aren't explicitly documented in the publication metadata. The researcher maintains active contributions to laboratory and team-based research, with recent publications indicating involvement in projects related to healthcare AI, cybersecurity systems, and intelligent transportation. Current research directions appear focused on addressing limitations in deep learning including catastrophic forgetting, data scarcity, and privacy concerns through novel architectural and training approaches.

• Video Quality Assessment
• Image Processing
• Machine Learning
• +۳ مورد دیگر

Steve Goering is a researcher at Technische Universität Ilmenau with a focus on video/image quality assessment , machine learning , and human-computer interaction . His work spans QoE modeling , AI-generated content evaluation , and VR/AR applications . Key Contributions: AVT-VQDB-UHD-1 dataset, Frankenstone toolbox, and AVrate Voyager platform. Collaborations: Alexander Raake, Rakesh Rao Ramachandra Rao, Rasmus Merten. Research Trends: Recent articles analyze AI upscaling appeal , 4K/8K HDR perception , and spatial audio in VR . His work integrates deep learning and crowdsourced evaluation . Grants & Tools: Developed open-source platforms for adaptive streaming analysis and immersive media quality assessment. No scientific awards are documented in the provided sources.

• Digital Signal Processing
• FPGA Implementation
• Machine Learning Hardware Acceleration
• +۴ مورد دیگر

Rocco Fazzolari is a Professor at Sapienza University of Rome's School of Engineering, Department of Electrical Engineering and Information Technology. With over 50 publications spanning from 2010 to projected 2025 works, he maintains an active research program focused on digital signal processing, hardware acceleration, and machine learning implementations. His research interests center on FPGA implementation of communication systems, with particular expertise in Residue Number System applications, QAM/PSK demodulation techniques, and reinforcement learning hardware accelerators. His work bridges theoretical signal processing concepts with practical hardware implementations, often targeting communications and control systems applications. Recent publications demonstrate increasing focus on machine learning integration with traditional signal processing techniques. Analysis of his publication trends shows consistent output across multiple venues including IEEE Access, IEEE Transactions on Circuits and Systems, and various conference proceedings. His collaborative pattern reveals a core research group including Gian Carlo Cardarilli, Luca Di Nunzio, and Marco Re, with whom he has co-authored over 45 publications each. He has also organized multiple academic conferences including the International Conference of Yearly Reports on Informatics, Mathematics, and Engineering (ICYRIME) and the Sapienza Yearly Symposium of Technology, Engineering and Mathematics. Research Recognition: Extensive publication record in IEEE journals and major conferences Organizer of multiple international academic conferences Consistent collaborative research output with established research group Fazzolari's work demonstrates strong application focus in communications systems, with recent expansion into machine learning hardware acceleration. His research group appears to maintain stable funding and productivity, with publications showing progression from fundamental digital circuit design to more complex machine learning integrated systems over the past decade.

• Remote Sensing
• Image Processing
• Data Hiding
• +۴ مورد دیگر

Haishan Chen is an active researcher with a prolific publication record spanning from 2008 to 2024 across multiple high-impact journals and conferences. Their work demonstrates expertise at the intersection of remote sensing, image processing, and data security, with significant contributions to environmental monitoring in China and advanced steganographic techniques. Chen's research interests reveal a sophisticated interdisciplinary approach. In remote sensing, they have conducted extensive studies on evapotranspiration patterns, vegetation analysis, and precipitation monitoring across China, utilizing FLUXNET data and satellite observations. Their image processing research has significantly advanced reversible data hiding techniques, particularly with contrast enhancement methods that maintain image quality while embedding information. The integration of machine learning approaches in recent work, such as wavelet scattering networks for infant cry detection, demonstrates adaptability to emerging computational paradigms. Analysis of Chen's publication trends shows a clear evolution from foundational work in image processing and data hiding (2016-2018) toward more complex environmental applications (2020-2024). This trajectory reflects growing expertise in applying computational methods to address climate-related challenges, with increasing sophistication in handling multi-source data and complex environmental variables. Chen maintains a robust collaborative network with prominent Chinese researchers including Jiangqun Ni (6 co-authored papers), Junying Yuan (5 papers), Wien Hong (5 papers), and Tung-Shou Chen (4 papers). These collaborations span multiple institutions and research domains, indicating integration within China's academic research community and cross-disciplinary engagement. The researcher's consistent publication output in reputable venues such as IEEE Geoscience and Remote Sensing Letters, Remote Sensing, and IEEE Access demonstrates recognition within both environmental science and computer science communities. The sustained productivity over 15+ years suggests an established academic position with significant contributions to multiple fields of study.

• Artificial Intelligence
• Bioinformatics
• Data Mining
• +۳ مورد دیگر

Professor Phoebe Chen is a Professor and Chair of the Department of Computer Science and Information Technology at La Trobe University, Melbourne, Australia since 2010. Previously, she held roles as Associate Professor at Deakin University (2003–2010) and Senior Lecturer at Queensland University of Technology (1999–2003). She earned her BInfTech (First Class Honours) and PhD in Computer Science from the University of Queensland (2000). Her research focuses on interdisciplinary areas including bioinformatics, artificial intelligence, medical image analysis, deep learning, and data mining. Notable projects include the ARC Centre of Excellence in Bioinformatics and drug design using visualization and machine learning. She has secured over 30 research grants totaling ~$8M, including 13 prestigious ARC grants. Professor Chen chairs international conferences like the Asia-Pacific Bioinformatics Conference and ACM MM, and serves on editorial boards such as IEEE Transactions on Neural Networks and Current Bioinformatics. Her work spans topics like cancer recurrence prediction via multi-omics data, medical image analysis using neural networks, and AI-driven solutions for healthcare challenges. She has published over 300 peer-reviewed papers in top journals/conferences (e.g., Nature Machine Intelligence, IEEE Transactions).

ILYAS OZERمشاهده پروفایل

دانشیار

• Machine Learning
• Deep Learning
• Signal Processing
• +۴ مورد دیگر

İlyas Ozer is an Associate Professor in the Department of Computer Engineering at Bandırma Onyedi Eylül University, serving as the Software Department Head. His research focuses on machine learning applications in healthcare, energy systems, and natural language processing. He has authored over 20 peer-reviewed articles and supervised several theses on topics like blockchain-based identity systems and smart transportation. Active in editorial roles for journals like Aintelia Science Notes, he leads projects on medical imaging analysis and food freshness detection using machine learning. His teaching spans courses in data mining, deep learning, and embedded systems.

Tomislav Kartalovمشاهده پروفایل

استادیار

• Image and Video Processing
• Mobile Platform Implementation
• Machine Learning
• +۵ مورد دیگر

Tomislav Kartalov is an Assistant Professor at the Department of Electronics, Faculty of Electrical Engineering and Information Technologies, University of St. Cyril and Methodius in Skopje, Republic of Macedonia. He has held this position since March 2015, following previous roles as a Teaching and Research Assistant from 2002 to 2015 and a brief period in technical maintenance at Macedonian Radio Television. Education includes a Ph.D. in Technical Sciences (2014) with a dissertation on Fusion of Digital Images and Videos for Visual Quality Improvement and Mobile Platform Implementation Possibilities , an M.Sc. in Electrical Engineering (2008) focusing on Visual Quality Enhancement of Digital Television Videos , and a B.Sc. in Electrical Engineering (2002) with a thesis on Software for Switching Power Supply Design (Flyback) . His research interests span image/video processing, mobile platform optimization, machine learning applications in education and healthcare, and sensor networks. Key areas include exposure fusion algorithms for mobile devices, real-time traffic sound detection systems, and multimodal information fusion for intelligent transportation systems. His publications from 2006 to 2023 reflect a strong focus on computational photography, embedded systems, and healthcare technology. Notable contributions include automated exposure fusion techniques for low-resource devices and AI-driven diagnostics using neuroimaging. No scientific awards or grants are explicitly mentioned in the provided texts. Kartalov’s advising history is not listed, but his teaching roles suggest involvement in graduate student mentorship. Laboratory affiliations are not detailed in the text.

• Software Testing Education
• Machine Learning
• Metaheuristic Optimization
• +۹ مورد دیگر

Tamara Živković is a researcher at the Faculty of Informatics and Computing, Singidunum University. She holds a PhD in Software Engineering from the School of Electrical Engineering in Belgrade (2024), with prior Master's and Bachelor's degrees in related fields. Education: PhD, Software Engineering (2012-2024), School of Electrical Engineering, Belgrade Master, Audio and Visual Technologies (2008-2010), School of Electrical Engineering, Belgrade Bachelor, Telecommunications and Information Technology (2001-2007), School of Electrical Engineering, Belgrade Her research focuses on software testing education, metaheuristic optimization for machine learning models, and AI applications in cybersecurity, medical diagnostics, and data analysis. She explores hybrid approaches combining neural networks (LSTM, GRU, CNN) with metaheuristic algorithms (PSO, Firefly, Crayfish) for complex prediction tasks. Recent publications span software defect prediction, phishing detection, Parkinson's disease diagnostics, and sentiment analysis. Her work integrates generative adversarial networks for dataset augmentation and applies attention mechanisms in NLP tasks. She has completed advanced certifications in software product management and agile practices from the University of Alberta, along with ISTQB testing certifications.

• Embedded Systems
• Internet of Things (IoT)
• Deep Learning
• +۷ مورد دیگر

Hemant Ghayvat is an Associate Professor at Linnaeus University's Department of Computer Science and Media Technology, affiliated with the Faculty of Technology. He specializes in Embedded Systems, IoT, and Health Informatics, focusing on Ambient Assisted Living and AI-driven healthcare solutions. His research spans smart home technologies, wearable sensors, and predictive analytics for chronic disease management. Education: Bachelor's in Electronics and Communications (BIST, Bhopal, 2009) Master's in Microelectronics and VLSI (2011) PhD in Smart Home for Ambient Assisted Living (completed in New Zealand) Research Interests: Preventive Healthcare Monitoring Ambient Assisted Living for Elderly AI-Based Decision Making in Medicine Behavioral Pattern Analysis IoT Security and Privacy His work emphasizes fusion of sensor data and AI for real-time health interventions, such as gait rehabilitation for Parkinson's patients and anomaly detection in daily activities. Notable Projects: VCardiac: Framework for contactless heart disease detection via acoustic signals. Mitigating Health Inequalities: System thinking approach for regional healthcare improvement. Teaching: Courses in IoT, Embedded Systems, and Network Security at undergraduate and graduate levels. Labs/Teams: Active in the E-health – Improved Data to and from Patients group at Linnaeus University Centre for Data Intensive Sciences and Applications (DISA).

Saksham Suriمشاهده پروفایل

پژوهشگر

• Computer Vision
• Machine Learning
• Diffusion Models
• +۱۲ مورد دیگر

Saksham Suri is a Researcher at Meta Reality Labs , focusing on efficient foundation models and computer vision . He earned his PhD in Computer Science from the University of Maryland, College Park , advised by Prof. Abhinav Shrivastava . Prior to this, he completed his B.Tech in Computer Science and Engineering at IIIT Delhi , where he worked at the IAB Lab and Precog research group. His research interests center around computer vision and machine learning , particularly in reducing supervision requirements and leveraging synthetic data (e.g., from diffusion models and GANs ) for tasks like object detection , image segmentation , lip synchronization , and video instance segmentation . He has proposed novel architectures and loss functions to enhance recognition through generation, addressing challenges in sparsely annotated object detection , autoregressive generative models , and efficient feature transforms for Vision Transformers . Notable publications include LARP (ICLR 2025, under review), UVIS (CVPR Workshop 2024), Gen2Det (CVPR Workshop 2024), LiFT (ECCV 2024), GRIT (WACV 2024), and Diff2Lip (WACV 2024). These works span topics in video tokenization , synthetic data for detection , lightweight feature transforms , and audio-conditioned lip synchronization . He has collaborated with researchers such as Rama Chellappa , Mayank Vatsa , Richa Singh , C.-C. Jay Kuo , and Larry Davis . His academic contributions include open-source code repositories for projects like LARP , SparseDet , ViT Analysis , and LiFT . He has also served as an Area Chair for CVPR (2018–2021) and contributed to educational resources for courses like CS188 at UC Berkeley.

Visar Berishaمشاهده پروفایل

استاد

• Speech and Audio AI
• Healthcare AI
• Machine Learning
• +۳ مورد دیگر

Visar Berisha is a Professor and Associate Dean of Research and Commercialization in the Fulton Schools of Engineering at Arizona State University (ASU), with a joint appointment in the College of Health Solutions. His work bridges engineering and healthcare, focusing on AI-driven analysis of speech and behavior to improve patient outcomes. He leads interdisciplinary research in digital medicine, machine learning, and signal processing. Education: Ph.D. in Electrical Engineering from Arizona State University (2007). Research Interests: Speech and audio AI, healthcare AI, statistical signal processing, and clinical applications. His team develops FDA-registered tools for tracking neurological disorders (e.g., ALS, Parkinson’s) and post-traumatic conditions through speech analysis. Recent Trends in Articles: Focus on clinical speech analytics, predictive modeling for neurological disorders, and machine learning robustness. Key topics include dysarthria progression, migraine classification, and automated semantic relevance for cognitive decline. Awards: 2023-2024 ISCA Distinguished Lecturer Winner of FTC Voice Cloning Challenge (OriginStory) Grants & Partnerships: Funding from NIH, NSF, and industry collaborations. Labs & Teams: Directs research on speech-based biomarkers, clinical AI validation, and neuroimaging analysis. Current students include Vikram C.M., Lingfeng Xu, and others. Alumni hold roles at universities, research institutions, and tech companies.

• Generative AI
• Multimodality
• Computer Vision
• +۴ مورد دیگر

Dr. Quang-Vinh Dang is a Researcher at the University of Hamburg, affiliated with the Cluster of Excellence 'Understanding Written Artefacts' (UWA). He holds a Ph.D. in Artificial Intelligence Convergence and specializes in Generative AI, multimodality, and computer vision. His work focuses on applying AI techniques to analyze historical manuscripts, combining domain expertise with machine learning. Education: Ph.D. in Artificial Intelligence Convergence, Master’s and Bachelor’s degrees in Mechatronics (focusing on control systems and robotics). Research interests include generative AI, computer vision applications in cultural heritage preservation, and cross-disciplinary approaches blending robotics and AI. He has contributed to projects like the Visual Manuscript Analysis Lab and Document Image Binarization competitions. Awards include 3rd place (ICDAR 2019) and Best Paper Award (Korea Computer Congress 2019). His publications span scene text processing, multimodal emotion recognition, and document restoration techniques. Labs/Teams: Member of the Visual Manuscript Analysis Lab within UWA, contributing to similarity measurement of visual patterns in manuscripts.

• Deep Learning
• Medical Imaging
• Computer Vision
• +۳ مورد دیگر

Hong Li is an Adjunct Professor at the University of Guelph, specializing in advanced deep learning techniques applied to medical imaging, computer vision, and edge computing. His research focuses on developing efficient neural network architectures for healthcare applications, sports analytics, and real-time systems. Key research interests include designing compact networks like EdgeSegNet and EdgeSpeechNets for edge devices, developing explainable AI strategies, and applying deep learning to medical imaging for disease detection (e.g., COVID-19 via chest X-rays) and severity assessment. His work bridges theoretical advancements with practical deployment challenges in resource-constrained environments. Publications highlight contributions to semantic segmentation, object tracking in sports (e.g., PuckNet for hockey puck localization), and neural architecture search methodologies. His research emphasizes interdisciplinary applications across healthcare, sports technology, and embedded systems.

Yukang Yanمشاهده پروفایل

استادیار

• Human-Computer Interaction
• Mixed Reality
• Virtual/Augmented Reality
• +۳ مورد دیگر

Yukang Yan is an Assistant Professor in the Department of Computer Science at the University of Rochester, affiliated with the ROCHCI research group. Previously, he was a postdoctoral researcher in the Augmented Perception Lab at Carnegie Mellon University's Human-Computer Interaction Institute. He holds a PhD and Bachelor's degree from Tsinghua University. His research focuses on Human-Computer Interaction (HCI) and Mixed Reality, emphasizing three interconnected threads: computational modeling of user behavior and perception, development of adaptive interfaces for bidirectional human-computer communication, and exploration of behavioral enhancements in Mixed Reality. Key areas include virtual/augmented reality interfaces, gesture-based interaction, and accessibility solutions. His work has been recognized with awards such as the ACM CHI 2020 and 2023 Honorable Mention Awards, the IEEE VR Best Paper Nomination, and an Outstanding Doctoral Thesis award from Tsinghua University. His research bridges theoretical insights with practical applications in AR/VR systems, emphasizing user-centered design and accessibility. Yan's contributions span over 20 peer-reviewed publications at top venues like ACM CHI, ACM UIST, and IEEE VR. His recent projects include HandAvatar (HCI 2023) for non-humanoid avatar interaction and Color-to-Depth Mappings (UIST 2022) for VR depth perception enhancements.