{"id":1674,"date":"2020-10-29T11:40:06","date_gmt":"2020-10-29T11:40:06","guid":{"rendered":"https:\/\/recpad2020.uevora.pt\/?page_id=1674"},"modified":"2020-10-29T11:46:02","modified_gmt":"2020-10-29T11:46:02","slug":"invited-speaker","status":"publish","type":"page","link":"https:\/\/recpad2020.uevora.pt\/index.php\/invited-speaker\/","title":{"rendered":"Invited Speaker"},"content":{"rendered":"\n
\"\"<\/figure>\n\n\n\n

Hubert P. H. Shum – Durham University
http:\/\/hubertshum.com<\/span><\/a><\/p>\n\n\n\n

Title<\/strong><\/h4>\n\n\n\n

Machine Learning for Human Data Modelling and Analysis<\/p>\n\n\n\n

Abstract<\/strong><\/h4>\n\n\n\n

Taking advantage of the recent advancement in machine learning and the availability of big data, computers have become smarter than ever in understanding complicated data. In this talk, I will focus on the modelling and analysis of human data, which can be represented in formats such as images, video, 3D movement and surfaces. Such data is core to a wide spectrum of research fields including computer vision (e.g. action recognition, pose estimation, 3D reconstruction), computer graphics (e.g. character animation, crowd simulations) and biomedical engineering (e.g. diseases diagnosis, motion analysis). Modelling human data effectively is a challenging problem as it is high dimensional in nature and diverse in representations. I will talk about how machine learning techniques can be used to take on the challenge to come up with novel models that enable robust applications. In particular, I will discuss how state-of-the-art deep learning provides a powerful framework for large-scale human data modelling and analysis. Finally, I will share some insights into future research opportunities and interesting research directions in this area.<\/p>\n\n\n\n

Biography<\/strong><\/h4>\n\n\n\n

Dr Hubert P. H. Shum is an Associate Professor in Computer Science at Durham University. Before this, he worked as the Director of Research\/Associate Professor\/Senior Lecturer at Northumbria University, a Postdoctoral Researcher at RIKEN Japan, and a Research Assistant at the City University of Hong Kong. He received his PhD degree from the University of Edinburgh, his Master and Bachelor degrees from the City University of Hong Kong. He led funded research projects as the Principal Investigator awarded by EPSRC, the Ministry of Defence (DASA) and the Royal Society. This facilitated him to develop his research team and to collaborate with international researchers from the UK, China, France, Japan and India. To engage the academic and industry networks, he led his team hosting important conferences such as BMVC and ACM SIGGRAPH Conference on MIG. Contributing to the research community, he has served as an Associate Editor for Computer Graphics Forum, a Guest Editor for International Journal of Computer Vision, and a Program Committee member in 15 conferences such as CVPR, Eurographics, Pacific Graphics. He has published over 100 research papers in the fields of computer graphics, computer vision, motion analysis and machine learning, particularly focusing on the modelling of human-related data. More information can be found on http:\/\/hubertshum.com<\/a><\/p>\n\r\n