جستجوی استاد راهنمای دانشگاهی

• Multimedia Signal Processing
• Image and Video Coding
• Event-Based Imaging
• +۸ مورد دیگر

Catarina Brites is an Assistant Professor in the Department of Information Science and Technology at ISCTE - Instituto Universitário de Lisboa and an Integrated Researcher at the Institute of Telecommunications - IUL, where she contributes to the Multimedia Signal Processing Group (MSP-Lx). She holds a PhD in Electrical and Computer Engineering from Instituto Superior Técnico (IST), University of Lisbon. PhD, Electrical and Computer Engineering, Instituto Superior Técnico (IST), 2011 M.Sc., Electrical and Computer Engineering, Instituto Superior Técnico (IST), 2005 B.Sc., Electrical and Computer Engineering, Instituto Superior Técnico (IST), 2003 Her research focuses on multimedia signal processing , particularly 2D/3D visual data coding , event-based imaging , plenoptic imaging (light fields and point clouds) , machine learning for image coding , and visual quality assessment . She has authored over 70 scientific publications with more than 3,890 citations (Google Scholar) and an h-index of 30. Her recent publications highlight a consistent focus on point cloud quality assessment , event-based vision coding , and deep learning applications in image and video compression . Trends include the development of novel metrics for 3D visual data and the application of neural networks to lossless and efficient coding paradigms. Best Paper Award Finalist at 2021 IEEE International Workshop on Multimedia Signal Processing Best Paper Honorable Mention Award at 2019 IEEE International Conference on Multimedia and Expo Top 8% Reviewer at 2018 IEEE International Conference on Multimedia and Expo Top 10% Paper Award at 2017 IEEE International Workshop on Multimedia Signal Processing Best Reviewer Award at 2012 IEEE Visual Communications and Image Processing Catarina Brites has co-supervised several M.Sc. theses at IST in areas including image/video coding and deep learning-based coding. She has been actively involved in multiple national and European R&D projects, serving as Co-Principal Investigator in the DARING project and Technical Coordinator in the EVASION project. She has also contributed as an Associate Editor for IEEE journals and served on technical and organizing committees for major conferences including IEEE ICIP, ICME, VCIP, and ACIVS. She is a key member of the Multimedia Signal Processing Group (MSP-Lx) at the Institute of Telecommunications, where she leads research in next-generation visual data representation and compression. She is also involved in the Technical Commission CT-120 - Image, Audio and Multimedia Information Coding, contributing to national standardization efforts.

Hee Sup Shinمشاهده پروفایل

استادیار

• Robotics
• Flexible and stretchable electronics
• Haptics
• +۳ مورد دیگر

Hee Sup Shin is an Assistant Professor in the School of Science and Engineering at the University of Missouri-Kansas City (UMKC). He holds a Ph.D. in Mechanical Engineering from Carnegie Mellon University (2021), an M.S. from the same institution (2015), and a B.S. from Korea University (2013). His research focuses on wearable robotics, flexible electronics, haptic systems, and biomedical devices. He leads the MiroLaboratory (https://mirolaboratory.github.io/), developing innovative technologies for healthcare monitoring and human-robot interaction. Shin's work integrates soft materials, advanced sensors, and wireless systems to create next-generation biomedical devices and robotic interfaces. Recent projects include skin-integrated wearables for sleep and respiratory monitoring, implantable bioelectronic systems, and modular sensor skins for UAVs. His research bridges mechanical engineering, materials science, and clinical applications, emphasizing practical biomedical solutions and aerospace engineering advancements. Key contributions include programmable thermal haptic interfaces for VR, soft airflow sensors for unmanned vehicles, and mechanoacoustic systems for pediatric health monitoring. His lab emphasizes translational research with applications in rehabilitation, aerospace, and wearable diagnostics. No scientific awards are explicitly listed, but his prolific publication record reflects strong academic engagement.

• Type-2 Fuzzy Logic
• Computational Intelligence
• Artificial Intelligence
• +۷ مورد دیگر

Simon Coupland is a Principal Lecturer in the School of Computer Science and Informatics at De Montfort University, within the Faculty of Computing, Engineering and Media. He is an active researcher affiliated with the Centre for Computational Intelligence (CCI), focusing on type-2 fuzzy logic and its applications in AI and decision systems. His educational background includes a PhD in Computer Science and a BSc (Hons) in Computing. PhD in Computer Science BSc (Hons) Computing Simon's research centers on the theoretical and practical aspects of type-2 fuzzy logic, including improving computational performance, assessing extensions to fuzzy systems, and applying these methods to real-world problems such as control and decision-making. His work bridges foundational mathematics with applied AI, particularly in uncertainty modeling and semantic computing. His recent publications reflect a strong trend toward integrating fuzzy logic with neural networks, semantic similarity, and innovative educational practices. The articles span topics in computational intelligence, computer vision, and pedagogical transformation, especially in block teaching models and authentic assessment. Notable scientific awards include: IEEE CIS Pre-college Education Video Competition Joint Winner (2012) IEEE Transactions on Fuzzy Systems Outstanding Paper Award (2009) British Computer Society Machine Intelligence Award (2008) He has contributed to student supervision and curriculum development, particularly in MSc programs related to computing and IT. Simon was a Co-Investigator on the AHRC-funded FuzzyPhoto project (2012–2014), demonstrating his involvement in externally funded research. His teaching includes modules on mobile robotics and advanced topics in fuzzy logic and neural networks. Simon is actively involved in the Centre for Computational Intelligence, where he contributes to research output, student co-creation, and the development of innovative AI-driven educational tools and assessment methods.

• Visualization
• Geometric Modeling
• Topological Analysis
• +۵ مورد دیگر

Joshua A. Levine is an Assistant Professor in the Department of Computer Science at the University of Arizona, where he has been since 2016. Previously, he held positions at Clemson University’s School of Computing (2012–2016) and the University of Utah’s Scientific Computing and Imaging Institute (2009–2012). He earned his Ph.D. in Computer Science from The Ohio State University, along with BS and MS degrees in Computer Engineering and Mathematics from Case Western Reserve University. Education: Ph.D., Computer Science, The Ohio State University (2009) M.S., Computer Science, Case Western Reserve University (2005) B.S., Computer Engineering and Mathematics, Case Western Reserve University (2003) Research Interests: His work focuses on visualization , geometric modeling , topological analysis , and computational topology . He develops tools like the Topology ToolKit for analyzing complex datasets and explores applications in mesh generation, vector fields, and performance analysis. His methods bridge theory with practical systems for scientific and engineering domains. Key Contributions: His publications span top-tier venues like IEEE VIS, SIGGRAPH, and Computer Graphics Forum , emphasizing scalable visualization techniques and algorithms for high-performance computing. Notable work includes Neural Volume Compression and Particle Merging-and-Splitting . Awards: DOE Early Career Research Program (2018) Best Paper Honorable Mention (IEEE VIS SciVis 2017) Multiple Best Paper Awards at visualization and meshing conferences (2010–2017) Labs & Collaborations: Leads visualization research at the University of Arizona, contributing to the Topology ToolKit (TTK), an open-source platform for topological data analysis. Engages in interdisciplinary projects with civil engineering and natural language processing communities.

Michael Wandمشاهده پروفایل

استاد

• Computer Graphics
• Machine Learning
• Geometry Processing
• +۵ مورد دیگر

Michael Wand is a Professor at the Institute of Computer Science , Johannes Gutenberg University Mainz , leading the Visual Computing Group . His research bridges Computer Graphics and Computer Vision , focusing on data-driven methods and structure-aware processing of geometric data. Research Themes Machine learning for geometric data analysis Symmetry and regularity detection in 3D shapes Generative models of visual data Big data in geometry processing Publication Trends : His recent work (2015-2016) explores integrating Markov Random Fields and Convolutional Neural Networks for image synthesis, generative adversarial networks for real-time texture synthesis, and algebraic models for parameterized shape editing. Earlier contributions (2007-2013) focus on point cloud processing , non-rigid shape reconstruction , and interactive editing of complex geometries. Academic Background : Doctoral degree (2004) in Computer Science from University of Tübingen Diploma (2000) in Computer Science from Universität-GH Paderborn

Pieter Peersمشاهده پروفایل

دانشیار

• Relighting
• Appearance Modeling
• Neural Rendering
• +۷ مورد دیگر

Pieter Peers is an Associate Professor in the Department of Computer Science at the College of William & Mary. Prior to this, he was a senior researcher at the Graphics Laboratory at the University of Southern California's Institute for Creative Technologies and a Research Assistant Professor at USC's Viterbi School of Engineering. His educational background includes a Ph.D. in Computer Science from K.U.Leuven (Belgium) in 2006 and a BS/MS in the same field from the same institution in 2000. Peers' research focuses on relighting, appearance modeling, and neural rendering—central topics in computer graphics and vision. His work bridges traditional rendering techniques with modern deep learning, particularly in inverse rendering, material modeling, and image-based relighting. He has made significant contributions to subsurface scattering, photometric stereo, and neural rendering systems. His recent publications, including work in SIGGRAPH, CVPR, and ICCV, demonstrate a strong trend toward integrating diffusion models and transformer architectures into appearance modeling and relighting tasks. These works often address real-world challenges such as single-image relighting, material estimation, and lighting control with minimal user input. RenderFormer (SIGGRAPH 2025): Transformer-based neural rendering with global illumination. ScribbleLight (CVPR 2025): Scribble-driven indoor relighting using diffusion models. MatFusion (SIGGRAPH Asia 2023): Diffusion-based SVBRDF capture. He has mentored and collaborated with numerous students and researchers, including Chong Zeng, Jun Myeong Choi, and James Bieron, indicating active involvement in advising and research supervision. While no formal grants or awards are listed, his consistent publication record in top venues suggests sustained research funding and recognition in the graphics community. Peers has led research in advanced rendering systems, including work on compressive light transport sensing, wavelet environment matting, and compact representations of heterogeneous subsurface scattering. His early work at USC and K.U.Leuven laid the foundation for his current research in neural appearance modeling and inverse rendering.

• Database Systems
• Machine Learning
• Graph Theory
• +۳ مورد دیگر

Shuai Ma is a researcher at Beihang University , School of Computer Science and Engineering, China. His work spans database systems , machine learning , and natural language processing , focusing on temporal knowledge graphs, graph neural networks, and privacy-preserving federated learning. He received his PhD from the University of Edinburgh , UK, in 2011. Research interests include graph theory , spatiotemporal data analysis , data mining , and anomaly detection . His recent publications address: 2025 : Technology mapping for ASICs, temporal network motifs, and 3D geometry compression. 2024 : Knowledge graph completion, scene mining for e-commerce, and secure aggregation for federated learning. Article trends reveal expertise in graph neural networks , temporal data processing , and privacy-aware systems . Collaborations with institutions like Concordia University and industry leaders underscore his interdisciplinary impact.

Dan B Goldmanمشاهده پروفایل

دانشیار مدعو

• Computer Graphics
• Computer Vision
• Artificial Intelligence
• +۳ مورد دیگر

Dan B Goldman is an affiliate associate professor at the University of Washington's Computer Science and Engineering department, while serving as a Principal Engineer and AI/ML architect for Lucasfilm & ILM. His career bridges academia and industry, with prior roles at Adobe's Creative Technologies Lab (2007-2015) and Google (2015-2024), where he led computer vision R&D for Project Starline. He is a member of the Visual Effects Society and holds a PhD in Computer Science (2007) from the University of Washington. Research Focus: Computer graphics, computer vision, artificial intelligence, and human-computer interaction Notable Projects: Content-Aware Fill (Photoshop), Project Starline (Google), HyperNeRF (neural radiance fields), and Nerfies (deformable 3D modeling) Academic Legacy: Mentored by David Salesin, with an Erdős-Bacon number of 6 (via Rose Byrne and David Salesin's academic lineage). His work appears in top venues like SIGGRAPH, CVPR, and ECCV, covering topics from neural rendering to 3D reconstruction. Industry Impact: Pioneered technologies used in major films (Star Wars, Jurassic Park) and Adobe Photoshop features. His recent work at Google Labs (2022-2024) focused on generative media, reflecting his dual expertise in creative tools and computational methods.

• Computer Graphics
• Physics-Based Simulation
• Fluid Dynamics
• +۳ مورد دیگر

Prof. Dr. Jan Bender holds a professorship in Computer Animation at RWTH Aachen University's College of Engineering. As a leading researcher in physics-based simulation methods, his work focuses on developing advanced numerical techniques for fluid dynamics, deformable solids, and multi-physics interactions through Smoothed Particle Hydrodynamics (SPH) and Finite Element Methods (FEM). Key Contributions: Invented PF-FLIP for two-phase flows, developed SymX symbolic framework for energy-based simulations, created STARK unified solver for robotics applications, and introduced implicit boundary handling for SPH Methodologies: Specializes in hybrid Eulerian/Lagrangian approaches, differentiable physics, adaptive discretization, and machine learning integration for simulation acceleration Research Impact: 2023 & 2024 Best Paper Awards in VMV and SCA conferences. His work enables billion-particle fluid simulations and realistic multi-body interactions for robotics, with applications in welding, thermal spraying, and soft robotics. Collaborations: Works extensively with robotics institutes (Gazebo Fluids extension) and materials science departments (TIG welding, thermal spray modeling). Maintains open-source code repositories for simulation frameworks.

• Haptic Communications
• Teleoperation
• Robotics
• +۳ مورد دیگر

Basak Gülecyüz is a Ph.D. researcher at the Chair of Media Technology (Lehrstuhl für Medientechnik) at the Technical University of Munich (TUM), affiliated with the Munich Institute of Robotics and Machine Intelligence (MIRMI). She holds a B.Sc. in Electrical and Electronics Engineering from Middle East Technical University (2016) and an M.Sc. in Communications Engineering from TUM (2019). Research Interests: Haptic communication systems Learning-oriented haptic codecs Teleoperated robot teaching Skill transfer via network-aware teleoperation Vibrotactile signal processing Publications Analysis: Her work focuses on optimizing haptic data transmission for teleoperation under network constraints, developing adaptive sampling strategies, deadband techniques, and perceptual compression algorithms. Key projects include applications in the Tactile Internet and 5G teleoperation systems. Teaching Roles: She served as a MATLAB tutor for Digital Signal Processing in 2022 and supervises student theses on topics like: Network-aware shared control Learning-based human-robot autonomy

• Machine Learning
• Computer Vision
• Haptic Communication
• +۳ مورد دیگر

Furkan Kaynar is a researcher at the Chair of Media Technology, Technical University of Munich, affiliated with the Munich School of Robotics and Machine Intelligence (MSRM) and the Munich Institute of Robotics and Machine Intelligence (MIRMI). He holds a B.Sc. in Electrical and Electronics Engineering (2016) from Bogazici University and an M.Sc. in Electrical Engineering and Information Technology (2019) from TUM. His research focuses on Machine learning for task-oriented robotic grasping Computer vision and interactive segmentation Haptic communication systems Human-robot interfaces for teleassistance Recent work includes few-shot learning methods for grasp area segmentation via remote demonstrations. Project involvement includes Centre for Tactile Internet with Human-in-the-Loop (CeTI) , Teleoperation over 5G , and IEEE P1918.1.1 Haptic Codecs . Collaborative efforts appear in publications at international conferences. Teaching activities include: Organizing the Seminar on Topics in Signal Processing (WS19/20) Conducting tutorials for Image and Video Compression (SS20)

• Computer Vision
• Machine Learning
• Healthcare
• +۵ مورد دیگر

Dr. Jianbo Jiao is an Associate Professor in the School of Computer Science at the University of Birmingham , leading the Machine Intelligence + x (MIx) group . He holds a PhD in Computer Science from City University of Hong Kong (Hong Kong PhD Fellowship Scheme) and an MSc from Peking University. He was a visiting scholar at the University of Illinois at Urbana-Champaign and a postdoctoral researcher in the Biomedical Image Analysis (BioMedIA) group and Visual Geometry Group (VGG) at the University of Oxford. Research Focus: Computer Vision, Machine Learning, Medical Imaging, AI for Science Key Themes: Learning from limited supervision (self-supervised, weakly-supervised), multi-modal data analysis (vision-audio-text-chemical spectra), open-world problems (incremental learning, open-vocabulary segmentation), 3D scene understanding Awards & Recognition: Amazon Research Award (2024) Royal Society Short Industry Fellowship (2023) Best Paper Awards at MICAD 2024 and MICCAI 2024 ASMUS Workshop Outstanding Reviewer Awards from CVPR, ECCV, ICCV, NeurIPS, and MICCAI Fellow of the Higher Education Academy (FHEA) Community Contributions: Area Chair for NeurIPS 2025, ACM MM 2025, and ICLR 2025; Senior Program Committee member for IJCAI 2021; Editorial roles at IEEE T-CSVT, Springer The Visual Computer, and TMLR. Collaborations & Labs: Works with Oxford's BioMedIA and VGG groups, Meta Project Aria, and leads the MIx group at Birmingham, which focuses on open-world AI, 3D modeling, and cross-modal healthcare applications.

Saining Xieمشاهده پروفایل

استادیار

• Computer Vision
• Machine Learning
• Visual Intelligence
• +۳ مورد دیگر

Saining Xie is an Assistant Professor of Computer Science at NYU Courant Institute of Mathematical Sciences and affiliated with the NYU Center for Data Science. He leads the CILVR research group and teaches courses including Computer Vision, Machine Learning, and Learning with Large Language and Vision Models at the graduate level. His educational background includes a Ph.D. and M.S. from UC San Diego's CSE Department under Zhuowen Tu's supervision, and a bachelor's degree from Shanghai Jiao Tong University. During his doctoral studies, he interned at NEC Labs, Adobe, Facebook, Google, and DeepMind. Dr. Xie's research focuses on advancing robust visual intelligence through scalable and reliable systems that interpret visual events and develop common sense understanding of the world. His work spans computer vision, machine learning, representation learning, and multimodal systems, with particular emphasis on developing architectures that bridge vision and language understanding. His publications demonstrate significant contributions to vision-language models, diffusion models, convolutional neural networks, and 3D scene understanding, with numerous papers appearing at top conferences including NeurIPS, CVPR, and ICCV, often receiving recognition as oral or spotlight presentations. Oral Presentation at NeurIPS 2024 Oral Presentation at CVPR 2024 Spotlight Presentation at ICLR 2023 Oral Presentation at ICCV 2023 Best Paper Nomination at CVPR 2020 Dr. Xie actively mentors PhD students including Ellis Brown, Fred Lu, Xichen Pan, Peter Tong, and others. He has organized major tutorials at CVPR and ECCV on Visual Recognition for Images, Video, and 3D, and his research has practical applications in visual grounding, multimodal reasoning, and robust AI systems. His lab maintains strong connections with industry research labs including FAIR, where he previously worked as a research scientist.

Francisco Díaz Barrancasمشاهده پروفایل

پژوهشگر

• Computer Science
• Virtual Reality
• Color Science
• +۳ مورد دیگر

Francisco Díaz Barrancas is a PostDoctoral Researcher at the University of Extremadura, Spain, with affiliations to the Centro Universitario de Mérida. His work spans virtual reality systems, color science, and cybersecurity, supported by international collaborations including the ERC project "Color 3.0" at Justus-Liebig University and research stays in Portugal and Italy. PhD in Real-Time Rendering (UEx, 2022) M.Sc. in Computer Technologies Research (UEx, 2018) B.Sc. in Computer Engineering (UEx, 2017) Research focuses on hyperspectral imaging , color constancy , and VR device optimization , with recent work on neural network training in VR and cybersecurity in immersive environments . Publications span JCR-indexed journals and IEEE conferences , emphasizing perceptually-motivated solutions. Best Poster Award at XIV CONFERENZA DEL COLORE (2018) Teaching experience includes courses in Programming Fundamentals and Multimedia Communication at UEx. Internationally active with research stays at Colour Science Laboratory (Portugal), MIPS LAB (Italy), and ICVS Summer School (UK).

Daniel Ritchieمشاهده پروفایل

دانشیار

• Computer Graphics
• Artificial Intelligence
• Machine Learning
• +۵ مورد دیگر

Dr. Daniel Ritchie is an Associate Professor of Computer Science at Brown University , where he co-leads the Brown Visual Computing group. His research integrates Computer Graphics , Artificial Intelligence , and Machine Learning to develop neurosymbolic methods that combine procedural models and deep neural networks for 3D shape and scene creation.