جست‌وجوی استاد و پژوهشگر

Romain Raveauxمشاهده پروفایل

دانشیار

• Image Analysis
• Machine Learning
• Structural Pattern Recognition
• +۵ مورد دیگر

Romain Raveaux is an Associate Professor at the LIFAT Computer Science Laboratory, University of Tours, affiliated with Polytech Tours. His research focuses on Image Analysis, Machine Learning, Structural Pattern Recognition, Graph Matching, Graph Neural Networks, Discrete Optimization, Reinforcement Learning, and Transfer Learning . Email: romain.raveaux@gmail.com , romain.raveaux@laposte.net Address: 64 av. Jean Portalis, Tours, France, 37200 Phone: +33 (0)2 47 36 14 27 Research Interests Graph Matching and Neural Networks Discrete Optimization for Pattern Recognition Transfer Learning in Graph-Based Models Historical Document Analysis Scientific Trends His recent work bridges Graph Neural Networks with Mixed-Integer Programming , focusing on Image Semantic Segmentation and Graph Cycle Detection . Earlier studies emphasize Genetic Algorithms for graph classification and Graph Edit Distance optimization in pattern recognition.

• Signal Processing
• Bayesian Statistics
• Deep Learning
• +۴ مورد دیگر

Lars Hammarstrand is an Associate Professor at Chalmers University of Technology specializing in the Signal Processing research group. His work integrates model-based Bayesian statistics with deep machine learning for applications in visual localization, sensor fusion, and autonomous systems, with emphasis on robustness in real-world environments. His research focuses on bridging Bayesian inference and deep learning to solve challenges in autonomous vehicle perception. Key areas include visual localization under appearance changes, radar-camera sensor fusion, and out-of-distribution detection for safety-critical systems. Recent work explores neural radiance fields for radar, semi-supervised learning for mapping, and probabilistic hierarchical classification to address real-world uncertainties in autonomous driving. Analysis of his 2020-2025 publications reveals a trajectory toward unifying geometric and semantic understanding in autonomous systems. His work demonstrates increasing integration of neural radiance fields with traditional filtering techniques, while advancing open-set recognition capabilities. Notable contributions include road geometry estimation frameworks, extended object tracking with PHD filters, and methods to mitigate data leakage in localization benchmarks. No scientific awards were mentioned in the provided materials. Hammarstrand has contributed to academic supervision methodology through his publication on improving master's thesis supervision efficiency, though specific student names are not listed. The provided information contains no details about research grants or funding sources. He operates within Chalmers University's Signal Processing research group, which develops advanced algorithms for automotive perception systems, focusing on sensor fusion techniques that combine radar, camera, and motion data for robust environmental understanding in autonomous vehicles.

• artificial intelligence
• image analysis
• deep learning
• +۸ مورد دیگر

Natasa Sladoje is a Professor in Computerized Image Analysis at the Department of Information Technology, Uppsala University. She is affiliated with the Vi3 and Image Analysis research group and leads the MIDA research group. Her work spans artificial intelligence, biomedical image analysis, deep learning, and algorithm development, with applications in medical imaging and life sciences. Her research focuses on developing advanced image analysis methods, particularly using machine and deep learning, to enable automated analysis of image data in science and everyday life. Key areas include medical image analysis, image registration, segmentation, pattern recognition, and discrete geometry. She applies these techniques to critical domains such as oral cancer detection, cytology, and multimodal imaging. The recent publications highlight a strong trend in AI-driven medical diagnostics, particularly in cancer detection using whole slide images, self-supervised learning for sparse instance detection, and contrastive learning for multimodal image registration. Her work also emphasizes reproducibility and benchmarking in bioimage analysis through frameworks like BIAFLOWS and public datasets like HISTOBREAST. She has no listed scientific awards in the provided text. Natasa Sladoje supervises research within the MIDA group and collaborates extensively on projects involving bioimage analysis, deep learning, and medical applications. While specific grant details are not mentioned, her leadership in collaborative frameworks and publication output suggests active involvement in funded research initiatives. She leads the MIDA (Medical Image Analysis) research group, which focuses on developing and applying novel image analysis tools for biomedical applications, particularly in cancer diagnostics and multimodal imaging.

Erchan Aptoulaمشاهده پروفایل

استاد

• Digital Image Analysis
• Computer Vision
• Remote Sensing
• +۳ مورد دیگر

Erchan Aptoula is a Professor of Computer Science at Sabanci University's Faculty of Engineering and Natural Sciences in Istanbul, Türkiye. He is affiliated with the Computer Vision and Pattern Analysis Laboratory (VPALab) and actively conducts research in digital image analysis, computer vision, and deep learning with a focus on remote sensing and (bio)medical data. University: Sabanci University School: Faculty of Engineering and Natural Sciences Academic Rank: Professor Email: erchan.aptoula@sabanciuniv.edu His research interests span domain generalization for remote sensing, explainable AI, medical image analysis, and precision agriculture applications. Recent work includes advancements in open-set domain generalization for hyperspectral classification, pollen classification with novel datasets, and domain adaptation techniques for SAR flood segmentation. Scientific contributions include 15+ recent publications addressing domain generalization, semantic segmentation, and uncertainty quantification in remote sensing and medical imaging. Awards include 2nd place at IEEE SIU'25 student paper awards. Projects involve international collaborations with institutions in Tunisia, Finland, and the UK, focusing on medical image understanding, crowd counting, and Ottoman document analysis.

• Applied Analysis
• Numerical Analysis
• Data Science
• +۶ مورد دیگر

Leon Bungert is a Professor of Mathematics of Machine Learning at the University of Würzburg, working in applied analysis and numerics with a particular focus on data science and machine learning. His research investigates PDEs and variational models on graphs, adversarial robustness of machine learning, variational regularization, and nonlinear optimization. Dr. Bungert serves as a guest editor for the European Journal of Applied Mathematics, an associate editor for Advances in Continuous and Discrete Models: Theory and Applications, and is a member of the program committee at SSVM 2025. He is also an ELLIS member and actively organizes conferences and workshops, including "MIA'25" at IHP in Paris (January 13-15, 2025), "Synergies of Machine Learning and Numerics" in Osaka (March 11-13, 2025), and "Mathematical Analysis of Adversarial Machine Learning" in Oaxaca (August 17-22, 2025). Research Interests Dr. Bungert's primary research areas include: PDEs on graphs Adversarial robustness in machine learning Inverse problems Optimization Variational problems in L-infinity Nonlinear eigenvalue problems Image reconstruction with structural priors His work bridges theoretical mathematics with practical applications in machine learning, particularly focusing on the mathematical foundations of deep learning and developing robust algorithms that can withstand adversarial attacks. He has made significant contributions to understanding the connections between partial differential equations and machine learning algorithms. Research Trends Analysis of Dr. Bungert's recent publications reveals a strong focus on the intersection of machine learning and mathematical analysis. A key theme is the application of variational methods and partial differential equations to machine learning problems, particularly in understanding and improving the robustness of neural networks against adversarial examples. His work on Lipschitz learning on graphs has established important theoretical foundations for graph-based semi-supervised learning. Additionally, his research on the infinity Laplacian and p-Laplacian equations provides deep insights into the mathematical structure of machine learning algorithms. The development of Bregman learning frameworks for sparse neural networks represents a significant contribution to efficient deep learning model training. Professional Activities Dr. Bungert is actively involved in the academic community through editorial roles and conference organization. His current professional activities include: Guest editor for the European Journal of Applied Mathematics Associate editor for Advances in Continuous and Discrete Models: Theory and Applications Member of the program committee at SSVM 2025 ELLIS member Co-organizer of multiple international conferences and workshops Technical Contributions Dr. Bungert has developed several open-source software packages that implement his theoretical contributions, including: Code for convergence rates of Lipschitz learning on graphs A Bregman training framework for sparse neural networks CLIP: Cheap Lipschitz Training of Neural Networks Nonlinear Power Method for Proximal Operators and Neural Networks Robust Image Reconstruction with Misaligned Structural Information These implementations are primarily in Python and MATLAB, demonstrating his commitment to making theoretical advances accessible for practical applications.

Feras Dayoubمشاهده پروفایل

مدرس ارشد

• Robotics
• Computer Vision
• Machine Learning
• +۲ مورد دیگر

Dr. Feras Dayoub is a Senior Lecturer and Chief Investigator at the QUT Centre for Robotics (QCR) , where he co-leads the Visual Learning and Understanding program. He previously served as Chief Investigator at the ARC Centre of Excellence for Robotic Vision (2016-2020) and holds a PhD in Robotics and Computer Vision from the University of Lincoln. Research Focus: Deploying computer vision and machine learning for real-world mobile robotics applications, including autonomous weed control (CRC-P), vision-enabled underwater robots for reef protection (COTSbot/RangerBot), and UAV-based infrastructure inspection. Teaching: Coordinates advanced robotics topics (EGB439) and teaches microprocessor systems (CAB202). His recent publications focus on uncertainty quantification in robotic vision, open-set recognition, and performance monitoring of deployed models. His work has been recognized with multiple awards from the Australian Centre for Robotic Vision and a Google Impact Challenge popular vote award. 2023: Hyperdimensional Feature Fusion for Out-of-Distribution Detection 2023: Class Distribution Shift Prediction for Domain Adaptation 2022: Uncertainty for Open-Set Error Identification 2022: FSNet for Semantic Segmentation Failure Detection Awards include: 2020: ACRV Best-Profile Raising Event 2019: QUT STEM Camp Certificate of Appreciation 2016: Google Impact Challenge People's Choice Award 2015: QUT Vice Chancellor's Performance Award As supervisor, he guides projects on robotic object detection, cross-view localization, and continues to advance visual learning methodologies for real-world autonomous systems.

• Computer Vision
• Robotics
• 3D Reconstruction
• +۵ مورد دیگر

Thomas Läbe is a Researcher in the Department of Photogrammetry at the University of Bonn's Institute of Geodesy and Geoinformation. His roles include technical associate and software developer, with a focus on advancing robotics, computer vision, and agricultural automation. He holds a diploma in computer science (Dipl.-Inform. (FH)) from Cologne University of Applied Sciences (1994). His research spans image processing, bundle adjustment, visual odometry, and camera calibration, with notable contributions to SLAM (Simultaneous Localization and Mapping) for autonomous systems. Education: 1994: Dipl.-Inform. (FH) in Computer Science, Cologne University of Applied Sciences Research Interests: Focuses on integrating vision-based technologies into robotics for precision agriculture, 3D reconstruction, and robust localization in dynamic environments. His work addresses challenges in sensor calibration, panoptic segmentation, and semantic mapping for autonomous systems operating in agricultural and urban settings. Publications Trends: Recent work emphasizes agricultural robotics, including fruit completion, plant phenotyping, and robust localization under changing conditions. Key themes include LiDAR-based localization, semantic occupancy prediction, and end-to-end learning for 3D representations. Awards: 2001 Hansa Luftbild Price (Best PFG paper award, shared) Technical Contributions: Developed software frameworks for bundle adjustment, multi-camera systems, and obstacle detection. Collaborated on projects like the Phenoliner field phenotyping platform and UAV-based environmental monitoring systems. Labs/Teams: Active in the Photogrammetry professorship group, contributing to the PRBonn (Perception, Robotics & Bonn) robotics initiatives, with open-source tools like OverlapNet and PAg-NeRF for 3D perception.

Ignacio Arganda Carrerasمشاهده پروفایل

دانشیار

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

Ignacio Arganda Carreras is an Associate Professor at the Universidad del País Vasco/Euskal Herriko Unibertsitatea (UPV/EHU) and an Ikerbasque Research Associate, affiliated with the Donostia International Physics Center (DIPC). His research focuses on biomedical computer vision, with a strong emphasis on deep learning applications in microscopy and medical imaging. Key areas include bioimage analysis pipelines, domain adaptation for cross-modal image segmentation, and AI-driven solutions for healthcare diagnostics. He has contributed extensively to open-source tools like BiaPy, CartoCell, and DL4MicEverywhere, which advance accessibility to deep learning in bioimaging. His work bridges computational methods with biological and medical challenges, addressing issues like 3D object detection, super-resolution imaging, and automated classification in microscopy and clinical settings. Research highlights include developing the MitoEM and Nucmm datasets for mitochondria and neuronal nuclei segmentation, as well as innovative applications in wound healing modeling and aquaculture monitoring. His methodologies emphasize reproducibility, generalization, and mitigation of overfitting in deep learning models.

Lydia Cuiمشاهده پروفایل

مدرس ارشد

• Artificial Intelligence
• Biomedical Image Processing and Analysis
• Machine Learning
• +۶ مورد دیگر

Dr. Lydia Cui is a Senior Lecturer at La Trobe University's Department of Computer Science and Information Technology. She holds a PhD and MPhil from the University of Sydney and a Bachelor's from Harbin Institute of Technology. Her research focuses on AI-driven biomedical image analysis, machine learning, and precision oncology, with emphasis on multi-modality imaging fusion, cancer diagnosis, and graph neural networks. She actively collaborates with industry and hospitals to translate AI technologies into clinical workflows. Dr. Cui leads the Department’s Teaching & Learning and Postgraduate Course Coordination roles. She has received notable awards, including the SNMMI 2015 International Best Paper Award. Her teaching includes Data Mining, Computer Vision, and Image Processing courses. Research interests include segmentation of biomedical images, AI for disease prognosis, and integration of imaging with non-imaging biomarkers. Recent publications span top-tier journals like IEEE Transactions on Medical Imaging and conferences such as MICCAI. She supervises students in AI and biomedical informatics. Funded projects include 'Multi-modality data-driven health monitoring in Industry 4.0' with Rudder Technology.

Jefersson Alex dos Santosمشاهده پروفایل

استادیار

• Remote Sensing Image Processing
• Computer Vision
• Machine Learning
• +۴ مورد دیگر

Jefersson Alex dos Santos is an Assistant Professor (Lecturer) in Computer Vision at the University of Sheffield, UK. Previously, he served as an Associate Professor at Universidade Federal de Minas Gerais (UFMG), Brazil (2013–2022). He holds a PhD in Computer Science from the University of Campinas (Unicamp) and the University of Cergy-Pontoise, France (2013). His research focuses on remote sensing image processing, computer vision, and machine learning, with applications in geospatial data analysis and medical imaging. He is an IEEE Senior Member and serves as an Associate Editor for IEEE Geoscience and Remote Sensing Letters and Co-Chair of the ISPRS Working Group for AI/ML in Geospatial Data. Education: PhD in Computer Science: University of Campinas (Unicamp) & University of Cergy-Pontoise, 2013 Master's in Computer Science: Unicamp, 2009 Bachelor's in Computer Science: University of Mato Grosso do Sul (UEMS), 2006 Research Interests: Remote sensing image processing, computer vision, machine learning, and geospatial data analysis. His work emphasizes interdisciplinary research, including applications in environmental monitoring, medical imaging, and digital forensics. Grants & Awards: CNPq Productivity Research Scholarship (2016–2022) Serrapilheira Institute Research Grant (2021) Labs & Teams: Founder of the Laboratory of Pattern Recognition and Earth Observation (PATREO) at UFMG's Department of Computer Science.

• Neuro-Oncology
• Brain Tumors
• Glioblastoma
• +۴ مورد دیگر

Antonio Omuro, MD, is an Adjunct Professor in the Department of Neurology at Yale School of Medicine and currently serves as Chair of the Department of Neurology and Neurological Sciences at Stanford University. His research focuses on neuro-oncology, particularly clinical trials and therapeutic advancements for brain tumors, including glioblastoma and meningeal neoplasms. Dr. Omuro has held leadership roles, such as former Chief of Neuro-Oncology and Director of the Yale Brain Tumor Center, and completed his MD at the São Paulo School of Medicine (1995) and a Neuro-Oncology fellowship at Memorial Sloan Kettering Cancer Center (2004). His work emphasizes translational research, integrating machine learning and AI into clinical practice for improved diagnostic accuracy and treatment planning. Notable contributions include developing the Yale Glioma Dataset and advancing therapies like PARP inhibitors for recurrent tumors. He has been recognized as a Fellow of the American Academy of Neurology (2022). Dr. Omuro collaborates with researchers globally on projects such as deuterium metabolic imaging, immune profiling in brain tumors, and AI-enhanced radiotherapy planning. His publications highlight advancements in tumor metabolism analysis, clinical trial design, and molecular targeting strategies.

• 3D Reconstruction
• Scene Understanding
• Autonomous Driving
• +۷ مورد دیگر

Stefano Gasperini is a PostDoc Researcher (part-time) at the Technical University of Munich (TUM), affiliated with the Chair of Computer Science Applications in Medicine (CAMP) under Prof. Nassir Navab. He also serves as Co-Founder & CEO of Visualais, a startup focusing on 3D rendering from smartphone images. His primary roles include advancing reliable 3D scene understanding for autonomous driving and medical applications. He holds a PhD (submitted 2023) in Reliable 3D Scene Understanding from TUM, supervised by PD Dr. Federico Tombari, with prior industry experience at BMW and Airbus. Education : PhD in Informatics (2019-2025), TUM Master in Informatics (2017-2019), TUM Bachelor in Computer Engineering (2013-2016), University of Bologna Exchange at UC Santa Cruz (2015-2016) Research Interests : 3D reconstruction, scene understanding, autonomous driving, robustness in computer vision, domain generalization, and medical image analysis. His work bridges theoretical advancements with practical applications in automotive and medical fields, emphasizing reliability under challenging conditions. Publications : Gasperini’s research focuses on robust 3D perception, adversarial augmentation techniques, and domain generalization. Recent work includes pioneering methods like 3D adversarial augmentations for domain adaptation and novel view synthesis using NeRF extensions. Awards : Outstanding Reviewer awards at CVPR 2025, ECCV 2024, ICCV 2023 Deutschlandstipendium scholarships (2017–2019) Summa Cum Laude (2016) and Provost’s Commendations (2015) Advising & Collaboration : Supervises PhD candidates across TUM and industry partners (BMW, Huawei, Mercedes-Benz). Coordinates the reconstruction research group at CAMP and collaborates on projects with AIT, BMW, and academic institutions. Labs & Teams : Active in TUM’s DHM, IFL, and NARVIS labs, focusing on medical imaging, autonomous systems, and surgical data science. Leads the Visualais startup to commercialize 3D reconstruction technologies.

Omri Abendمشاهده پروفایل

دانشیار

• Computational Linguistics
• Natural Language Processing
• Semantic Representation
• +۹ مورد دیگر

Omri Abend is an Associate Professor at The Hebrew University of Jerusalem, affiliated with the School of Computer Science and Engineering and serving as Chair of the Department of Cognitive and Brain Sciences. His research lies at the intersection of Computational Linguistics, Natural Language Processing, and Cognitive Science, with a focus on semantic representation and language acquisition modeling. His primary research interests include: Computational modeling of child language acquisition Semantic representation frameworks, particularly Universal Conceptual Cognitive Annotation (UCCA) Statistical learning and machine translation Unsupervised grammar learning and lexical relation induction Cross-lingual and cross-domain alignment in language models Evaluation methodologies for NLP systems His recent publications demonstrate a strong trend toward analyzing large language models (LLMs), exploring human-like patterns in AI, improving evaluation metrics, and applying NLP to humanitarian domains such as Holocaust testimony analysis. His work combines theoretical linguistic insights with practical machine learning applications. Scientific awards include: Outstanding Paper Award at ACL 2017 Area Chair Award for Best Paper in the Track at ACL 2023 He has supervised and collaborated with numerous researchers and students across projects in semantic parsing, machine translation, and cognitive modeling. His work has been supported by community-wide initiatives such as the MRP shared tasks, which he co-organized. He also leads research on ethical AI, open human feedback, and the computational analysis of historical narratives. Omri Abend leads several research teams focused on: The development and application of the UCCA framework for semantic annotation Cross-lingual and cross-domain knowledge representation in LLMs Computational modeling of language acquisition Evaluation and improvement of NLP systems Application of NLP to digital humanities and historical testimony analysis

• Robotics
• Human-Robot Interaction
• Assistive Robotics
• +۹ مورد دیگر

Guillem Alenyà Ribas is a Researcher and Director of the Perception and Manipulation group at the Institut de Robòtica i Informàtica Industrial (IRI), a joint center of the Spanish National Research Council (CSIC) and the Polytechnic University of Catalonia (UPC), Barcelona. His research focuses on integrating robots into human environments, particularly in assistive robotics and the manipulation of deformable objects such as garments. His research interests span Human-Robot Interaction (HRI) , assistive robotics , explainable AI , robot personalization , deformable object manipulation , and benchmarking . He aims to make robots more transparent, adaptive, and safe in real-world applications. His work combines AI planning, vision, learning from demonstration, and user-centered design to develop systems that can assist in healthcare, domestic, and industrial settings. Recent publications reveal a strong trend in explainability and personalization in HRI, with a focus on frailty assessment in elderly care , real-time explanations , and counterfactual reasoning . His team also advances benchmarking in cloth manipulation , 3D reconstruction of clothed humans , and ontology-based reasoning for robot plans . This reflects a multidisciplinary approach combining robotics, AI, and social sciences. Coordinator of ROB-IN, CLOE-GRAPH, and BURG projects Principal Investigator in SeCuRoPS and DEMETER 5.0 Former coordinator of SIMBIOTS, HuMoUR, and SOCRATES He has supervised numerous PhD students, many of whom have received prestigious awards such as the Georges Giralt PhD Award and the AIHUB.CSIC Prize. His leadership in technology transfer and European projects highlights his role in bridging academic research with real-world applications. He leads the Perception and Manipulation group at IRI, fostering collaboration across disciplines and mentoring a large team of researchers, PhD students, and technical staff. The group actively contributes to open science through standardized datasets and reproducible methodologies.

• Autonomous Driving
• Computer Vision
• Robotics
• +۵ مورد دیگر

Holger Caesar is a tenured Assistant Professor at Delft University of Technology (TU Delft) in the Intelligent Vehicles Lab . He leads research on scalable approaches for autonomous vehicle perception, prediction, and data annotation, with a focus on sensor fusion, domain adaptation, and minimal supervision. His work has been cited over 15,000 times. Education PhD in Computer Vision, University of Edinburgh Prior studies at KIT Karlsruhe, EPF Lausanne, and ETH Zurich Research Interests span autonomous driving perception, weakly supervised learning, novel view synthesis (NeRFs), diffusion models, and collaborative perception. He emphasizes reducing reliance on manual annotations through active learning and partial labeling techniques. Recent Publications include work on 4D Gaussian Splatting, camera-radar fusion, open-set scene graph generation, and safety benchmarking. These reflect trends toward multi-modal perception, robust sensor fusion, and foundation models for scalable autonomous systems. Scientific Awards ELLIS Europe Scholar (2024) TU Delft Cohesion Grant (100k EUR, 2024) Climate Action Grant (30k EUR, 2024) TKI High Tech Systems Grant (502k EUR, 2022) AiNed XS Grant (80k EUR, 2023) Argoverse Scene Flow Challenge Winner (unsupervised track, 2024) Advising & Grants include EU Horizon funding for the MOSAIC project (1 PhD and 1 Postdoc, 2024), EU KDT Cynergie4MIE grant (450k EUR, 2024), and industrial collaborations with Bosch, Motional, and partners across Europe. Labs & Teams include the Intelligent Vehicles Lab at TU Delft and founding roles in Motional's Data Annotation, Autolabeling, and Data Mining teams. He co-organizes workshops at ICCV, CVPR, and NCCV, and leads the ELLIS Delft Unit seminar series.