4D Video Scene Understanding in the Wild Contrastive Language-Image Pretraining (CLIP) for Video Analytics Egocentric Vision - Making Sense of the First-Person Perspective Human Vision Image Segmentation Multimodal Behaviour Understanding and Generation for Human-Robot Interaction Self-supervised Learning Statistical Models of Shape and Appearance Stereo Vision & Feature Matching Structured Generative models for Computer Vision Uncertainty and Evaluation in Vision Video Understanding
Session Topic: Image Segmentation
Professor Xianghua Xie is currently leading a research team on Computer Vision and Machine Learning (http://csvision.swan.ac.uk) in the Department of Computer Science, Swansea University. He was a recipient of an RCUK Academic Fellowship (tenure-track research focused lectureship) between September 2007 and March 2012. He was appointed as a Senior Lecturer from October 2012, then an Associate Professor in April 2013, and a full Professor from March 2019. Prior to his position at Swansea, He was a Research Associate at the Computer Vision Group, Department of Computer Science, University of Bristol, where he completed both his PhD (2006) and MSc (2002) degrees.
Professor Xie has strong research interests in the areas of Pattern Recognition and Machine Intelligence and their applications to real-world problems. He has been an investigator on several research projects funded by external bodies, such as EPSRC, Leverhulme, NISCHR, and WORD. Among his research works, those of significant importance include detecting abnormal patterns in complex visual and medical data, assisted diagnosis using automated image analysis, fully automated volumetric image segmentation, registration, and motion analysis, machine understanding of human action, efficient deep learning, and deep learning on irregular domains. By 2020, he has published over 150 fully refereed research publications and (co-)edited several conference proceedings. He is an associate editor of IET Computer Vision and an editorial member of a number of other international journals and has chaired and co-chaired several international conferences, e.g. BMVC2015 and BMVC2019.
Session Topic: Egocentric Vision - Making Sense of the First-Person Perspective
Dr Michael Wray is a lecturer/Assistant Professor of Computer Vision at the School of Computer Science at the University of Bristol. Dr Wray's research interests are in multi-modal video understanding, particularly for egocentric videos — focusing on how both vision and language can be tied together towards tasks such as cross-modal retrieval, grounding and captioning. Dr Wray is part of MaVi and ViLab.
Session Topic: Statistical Models of Shape and Appearance
After completing a degree in Maths and Physics at Exeter University, and a PhD in Civil Engineering (studying a storm sewer overflow) at Sheffield City Polytechnic, Prof. Tim Cootes joined the University of Manchester in 1991.
Prof. Tim Cootes began as an RA, working with Prof Chris Taylor on modelling industrial components.
Prof. Tim Cootes was awarded an SERC Postgraduate fellowship in 1993, and an EPSRC Advanced Fellowship in 1995.
Prof. Tim Cootes became a Lecturer in ISBE in June 2001, and was promoted to Senior Lecturer in October 2002.
Prof. Tim Cootes became a Reader in Computer Vision in August 2005, and was appointed as a Professorial Research Fellow in August 2006.
Prof. Cootes research has concentrated on constructing statistical models of the shape and appearance of objects in images, and in developing algorithms to match such models to new images. We have applied these models to many problems in the industrial and medical domains, and to the interpretation of facial images.
Session Topic: Self-supervised Learning
Dr Oisin Mac Aodha is an Lecturer (aka Assistant Professor) in Machine Learning in the School of Informatics at the University of Edinburgh (UoE). Dr Oisin Mac Aodha is also a Turing Fellow and ELLIS Scholar. His current research interests are in the areas of computer vision and machine learning, with an specific emphasis on 3D understanding, human-in-the-loop methods, and computational challenges in biodiversity monitoring.
From 2016-2019 Dr Oisin Mac Aodha was fortunate to be a postdoc in Prof. Pietro Perona's Computational Vision Lab at Caltech working with the Visipedia team. Previous to Caltech, Dr Oisin Mac Aodha spent three great years (2013-2016) as a postdoc in the Department of Computer Science at University College London (UCL) with Prof. Gabriel Brostow and Prof. Kate Jones. There Dr Oisin Mac Aodha worked on interactive machine learning, where our goal was to design algorithms to enable non-programming scientists to semi-automatically explore events of interest in vast quantities of audio and visual data.
Dr Oisin Mac Aodha did both MSc (with Dr. Simon Prince) and PhD (with Prof. Gabriel Brostow) at UCL and have an undergraduate degree in electronic engineering from the University of Galway in Ireland. Before his PhD, Dr Oisin Mac Aodha was a research assistant for one year in Prof. Marc Pollefeys' group at ETH Zurich.
Session Topic: Stereo Vision & Feature Matching
Krystian Mikolajczyk did his undergraduate study at the University of Science and Technology (AGH) in Krakow, Poland. He completed his PhD degree at the Institute National Polytechnique de Grenoble, France. He then worked as a research assistant in INRIA, University of Oxford and Technical University of Darmstadt (Germany), before joining the University of Surrey as a Lecturer, and Imperial College London as a Reader in 2015. His main area of expertise is in image and video recognition, in particular in problems related to matching, representation and learning. He participated in a number of EU and UK projects in the area of image and video analysis. He publishes in computer vision, pattern recognition and machine learning forums. He has served in various roles at major international conferences co-chairing British Machine Vision Conference 2012, 2017 and IEEE International Conference on Advanced Video and Signal-Based Surveillance 2013. In 2014 he received Longuet-Higgins Prize awarded by the Technical Committee on Pattern Analysis and Machine Intelligence of the IEEE Computer Society.
Session Topic: Uncertainty and Evaluation in Vision
Before moving to Bath Prof. Neill Campbell was a Research Associate in the Virtual Environments and Computer Graphics Group at University College London working with Jan Kautz and Simon Prince on synthesizing and editing photorealistic visual objects funded by the EPSRC.
Previously Prof. Campbell was a Research Associate in the Computer Vision Group of the Machine Intelligence Laboratory, in the Department of Engineering at the University of Cambridge working on the EU Hydrosys Project led by Ed Rosten.
Prof. Neill Campbell completed his PhD, in the Computer Vision Group at the University of Cambridge, under the supervision of Roberto Cipolla and the guidance of George Vogiatzis and Carlos Hernández. Prof. Neill Campbell was funded by a Schiff Foundation Scholarship and Toshiba Research Europe.
Session Topic: 4D Video Scene Understanding in the Wild
Dr. Armin Mustafa is an Associate Professor in Computer Vision and AI, at the Centre for Vision, Speech and Signal Processing, University of Surrey. She also holds a Royal Academy of Engineering Fellowship in ‘4D Vision’. The emergence of machines that interact with their environment has led to an increasing demand for automatic visual understanding of real-world scenes. Her research focuses on AI to better understand complex scenes so that machines can efficiently model and interpret real-world data for a range of socially beneficial applications including autonomous systems, augmented reality and healthcare. She has previously finished her PhD in 'General dynamic scene reconstruction from multi-view videos' in 2016, under Prof. Adrian Hilton and she has previously worked at Samsung Research Institute in Computer Vision.
Session Topic: Human Vision
Dr Ulrik Beierholm is an Associate Professor in the Psychology Department at Durham University, working in Computational Neuroscience. His work crosses the border between neuroscience and computer science, by examining how computational models from machine learning can be used to build models of human perception, decision making, and action.
Session Topic: Structured Generative models for Computer Vision
Dr Paul Henderson is a Lecturer (aka Assistant Professor) in Machine Learning at the University of Glasgow. His research focuses on building machines that understand the visual world with minimal supervision, learning aspects of its structure such as 3D geometry and decomposition into objects. This work draws on techniques from machine learning (particularly deep generative models), computer vision, and computer graphics.
Session Topic: Multimodal Behaviour Understanding and Generation for Human-Robot Interaction
Dr Oya Celiktutan is a Senior Lecturer in Robotics (Associate Professor) at the Department of Engineering, King’s College London, UK, where she leads the Social AI and Robotics Laboratory. Her research interest lies in machine learning to develop socially aware systems capable of autonomously interacting with humans. This includes addressing challenges in multimodal perception, understanding and generating human behaviour, as well as advancing navigation, manipulation, and interaction within the context of human-centric robotics. Her work has been supported by EPSRC, The Royal Society, and the EU Horizon, as well as through industrial collaborations. She received the EPSRC New Investigator Award in 2021 and her team’s research has been recognized with several awards, including the Best Paper Award at IEEE Ro-Man 2022, NVIDIA CCS Best Student Paper Award Runner Up at IEEE FG 2021, First Place Award and Honourable Mention Award at ICCV UDIVA Challenge 2021.
Session Topic: Contrastive Language-Image Pretraining (CLIP) for Video Analytics
Prof. Victor Sanchez is the Head of the Signal and Information Processing (SIP) Lab of The University of Warwick. He received an M.Sc. degree from the University of Alberta, Canada, in 2003, and a Ph.D. degree from The University of British Columbia, Canada, in 2010. From 2011 to 2012, he was with the Video and Image Processing Laboratory, at the University of California at Berkeley, as a Postdoctoral Researcher. In 2012, he was a Visiting Lecturer with the Group on Interactive Coding of Images, Universitat Autònoma de Barcelona. From 2018 to 2019, he was a Visiting Scholar with the School of Electrical and Information Engineering, The University of Sydney, Australia. His research interests include computer vision with applications to multimedia analysis, biometrics, forensics, and security. He has authored several technical articles and book chapters in these areas. His research has been funded by the Newton Fund; the Natural Sciences and Engineering Research Council of Canada; the Canadian Institutes of Health Research; the FP7 and the H2020 Programs of the European Union; the Engineering and Physical Sciences Research Council, U.K; Ford Motor Company, USA, the Defence and Security Accelerator, U.K., and Research England. He is the Chair of the Technical Committee on Computational Forensics under the auspices of the International Association for Pattern Recognition (IAPR). He currently serves as an associate editor of IEEE Signal Processing Letters, IEEE Access, and ACM Computing Surveys.
Session Topic: Video Understanding
Andrew Gilbert is an Associate Professor at the University of Surrey. His academic pursuits are primarily focused on video understanding and Generative Models. His research portfolio comprises over 65 articles published in the leading international vision conferences and journals, and he co-leads the C-CATS research group at Surrey. Dr Gilbert's extensive research work ranges from intelligent creative arts, such as fine-grained style search, movie trailer genre understanding, and 4D performance capture, to enabling computers to perceive and understand their complex and cluttered surroundings using multiple training techniques, including self-supervised and multiple data modes. Previously, his research work encompassed 3D human pose estimation and complex real-world activity recognition, with early work on tracking people on vast surveillance networks. Moreover, Dr. Gilbert is an active British Machine Vision Association (BMVA) Executive Committee member and coordinates the national BMVA technical meetings. These meetings offer a forum for key experts from industry and academia to discuss and identify solutions to current problems in specialist areas of computer vision and machine learning.