Search Results

< Back ​ Prof. Matthew Purver Queen Mary University of London ​ Supervisor ​ ​ Matthew Purver is Professor of Computational Linguistics, and leader of QMUL’s Computational Linguistics Laboratory. His research has covered many aspects of natural language processing (NLP), with a £4m grant portfolio including projects on fundamental techniques like cross-lingual processing and incremental language understanding, and applications to news media, social media analysis and mental health diagnosis. His work has been covered by the Guardian, Telegraph, Independent, LA Times, NBC and Scientific American, among others. He is also a senior researcher at the Jožef Stefan Institute, Slovenia, and in 2011 he co-founded the company Chatterbox Labs Ltd. He is interested in supervising students with a background in NLP, linguistics or machine learning and an interest in analysis or generation of natural language. Research themes: Language in Games Game AI Computational Creativity ​ m.purver@qmul.ac.uk Email Mastodon https://www.eecs.qmul.ac.uk/~mpurver/ Other links Website LinkedIn https://twitter.com/mpurver Twitter Github ​ ​ Themes Creative Computing Game AI - Previous Next

< Back ​ Peter York University of York ​ iGGi Alum ​ ​ PhD student working in analytics and machine learning for esports broadcast and understanding. In particular working with Weavr on various projects related to broadcast and learning tools for Dota 2. Please note: Updating of profile text in progress ​ Email Mastodon https://pete-york.github.io Other links Website LinkedIn https://twitter.com/PeteTeeWeet Twitter Github ​ Featured Publication(s): Data-Driven Audience Experiences in Esports Metagaming and metagames in Esports DAX: Data-Driven Audience Experiences in Esports A generalized framework for self-play training Themes Esports Game AI - Previous Next

< Back ​ Dr Anne Hsu Queen Mary University of London ​ Supervisor ​ ​ Anne Hsu’s research includes machine learning, artificial agents, natural language processing and learning, human decision making, interaction design, and well-being technology. Her interests include developing interactive systems that use machine learning and understanding of human psychology to improve human behaviour. She is particularly interested in supervising students with a machine learning, design, HCI, or behavioural sciences background on the following topics: understanding and designing for curiosity in games design for behaviour change motivational/educational games Research themes: Game AI Game Design Games with a Purpose Player Experience Gamification ​ anne.hsu@qmul.ac.uk Email Mastodon Other links Website https://www.linkedin.com/in/anne-showen-hsu LinkedIn Twitter Github ​ ​ Themes Applied Games Design & Development Esports Player Research - Previous Next

< Back ​ Sarah Masters University of York ​ iGGi PG Researcher ​ Available for placement Sarah is an artist, game developer and researcher. They have an MA in Indie Game Development from Falmouth University (Distinction), where they created the city-building card game Eudaimonia. They are an active part of the games community taking part in game jams and setting up their own commercially focused studio. Sarah's work takes a research through design approach making and exploring games as an art form for change, collaborative design, speculative futures including 'ecopunk' and how we design games to meaningfully engage and entertain. Alongside a portfolio of games, their previous work includes running a workshop on Solarpunk vs Grimdark concepts. Their work also explores sustainable design and development practices to create emotional, engaging and meaningful experiences that can be a part of a greener industry and engage in climate change conversation. ​ sarah.masters@york.ac.uk Email https://mastodon.gamedev.place/@sarah https://sarahdotgames.itch.io/ Mastodon https://sarah.games/ Other links Website https://www.linkedin.com/in/sarah-games/ LinkedIn https://twitter.com/sarahdotgames Twitter https://github.com/Impalpably Github ​ Featured Publication(s): Radical Alternate Futurescoping: Solarpunk versus Grimdark Better Dead than a Damsel: Gender Representation and Player Churn Themes Applied Games Design & Development Player Research Eudaimonia: A solarpunk city-building choice and consequence game - Save the world in eight years!: Fatalis - a witchy gardening game: Previous Next

< Back ​ Dr Miles Hansard Queen Mary University of London ​ Supervisor ​ ​ Miles Hansard is a computer vision researcher, working on geometric and statistical methods for 3D scene understanding and rendering. He is also interested in active 3D sensing technologies, including depth cameras, lidar, and millimetre-wave radar. His recent projects include GPU methods for real-time atmospheric effects, commodity radar localization of UAVs, and grasp planning for robotic manipulation. He has also worked on human perceptual processes, including eye-movements, geometric judgements, and binocular stereopsis. Miles Hansard is a Senior Lecturer in computer graphics, and a member of the Vision Group and Centre for Advanced Robotics, at QMUL. He is available to supervise projects in the following areas: Simulation of complex physical effects (e.g. the motion of cloth, fire, and fluids), using machine learning. Physically plausible character animation in complex environments (e.g. slippery terrain), using machine learning. ​ miles.hansard@qmul.ac.uk Email Mastodon https://www.eecs.qmul.ac.uk/~milesh/ Other links Website LinkedIn Twitter Github ​ ​ Themes Design & Development Game AI Game Data Immersive Technology - Previous Next

Novel video narrative from recorded content Theme Creative Computing Project proposed & supervised by Nick Pears To discuss whether this project could become your PhD proposal please email: nick.pears@york.ac.uk < Back ​ Novel video narrative from recorded content Project proposal abstract: In order to stimulate interest and engagement in games, it is important to give players a wide variety of video content that can provide scenario variations each time they engage with the game. However, creating a large volume of diverse video content manually is expensive and time consuming. This project aims to generate novel video narratives from recorded content with minimal human intervention. This requires automatic visual scene understanding that generates auto tagging of scene content and scene actions, either on a frame-by-frame or short clip basis. As well as understanding frame content, action segmentation strategies will be developed and evaluated. This will enable construction of short novel video narratives - for example, from a manually-defined storyline. Deep learning tools and techniques will be employed throughout this project. Supervisor: Nick Pears Based at:

< Back Increasing the Diversity of Deep Generative Models Link ​ Author(s) S Berns Abstract ​ More info TBA ​ Link

< Back The Graph Cut Kernel for Ranked Data Link ​ Author(s) M Conserva, MP Deisenroth, KSS Kumar Abstract ​ More info TBA ​ Link

< Back Unconventional Exchange: Methods for Statistical Analysis of Virtual Goods Link ​ Author(s) OJ Scholten, P Cowling, KA Hawick, JA Walker Abstract ​ More info TBA ​ Link

< Back Navigating the Lines: Towards a Multi-Perspective Approach on Videogame Monetisation Link ​ Author(s) P Declerck, B Dupont, E Grosemans, E Petrovskaya, M Geudens, M Sas, ... Abstract ​ More info TBA ​ Link

< Back Design and implementation of TAG: a tabletop games framework Link ​ Author(s) RD Gaina, M Balla, A Dockhorn, R Montoliu, D Perez-Liebana Abstract ​ More info TBA ​ Link

< Back How Players Learn Team-versus-Team Esports: First Results from A Grounded Theory Study Link ​ Author(s) J Hesketh, CS Deterding, J Gow Abstract ​ More info TBA ​ Link