Search Results

< Back Measuring perceived challenge in digital games: Development & validation of the challenge originating from recent gameplay interaction scale (CORGIS) Link ​ Author(s) A Denisova, P Cairns, C Guckelsberger, D Zendle Abstract ​ More info TBA ​ Link

< Back ​ James Gardner University of York ​ iGGi PG Researcher ​ ​ I am a third-year PhD student at The University of York, specialising in computer vision and machine learning for 3D scene understanding. Supervised by Dr William Smith, my research focuses on neural-based vision and language priors in inverse rendering and scene representation learning. I'm particularly interested in neural fields, generative models, 3D computer vision, differentiable rendering, geometric deep learning, multi-modal models, and 3D scene understanding in general. My research has been recognised with publications at prestigious conferences including NeurIPS and ECCV. Currently, I am working as a research fellow on the ALL.VP project, funded by BridgeAI and Dock10, developing relightable green screen performance capture using deep learning and inverse rendering techniques. This work aims to provide greater creative control to film and TV productions without requiring expensive LED volumes or post-production. I hold an MEng in Electronic Engineering from The University of York, for which I was awarded the IET Prize for outstanding performance and the Malden Owen Award for the best-graduating student on an MEng programme. A description of James' research: My research lies at the intersection of computer vision, machine learning, and 3D scene understanding, with a particular focus on neural-based approaches and the integration of vision and language priors. My work spans a range of topics including neural fields, generative models, differentiable rendering, and geometric deep learning. A key theme in my research is the use of 3D inductive biases for inverse rendering, addressing challenges such as illumination estimation, albedo/geometry disentanglement, and shadow handling in complex outdoor scenes. I've made contributions in creating a rotation-equivariant neural illumination model and spherical neural models for sky visibility estimation in outdoor inverse rendering. Additionally, my work extends to learning rotation-equivariant latent representations of the world from 360-degree videos, aimed at advancing the field of 3D scene understanding and developing models with an understanding of core physical principles such as object permanence. Through my research, I aim to build computer systems capable of deeply comprehending the 3D world, utilising self-supervised, generative, and non-generative approaches to push the boundaries of what's possible in computer vision and scene representation learning. ​ james.gardner@york.ac.uk Email Mastodon Other links Website https://www.linkedin.com/in/jadgardner/ LinkedIn https://twitter.com/JADGardner Twitter https://jadgardner.github.io/ Github ​ ​ Themes Game AI - Previous Next

< Back ​ Dr David Zendle University of York ​ Supervisor ​ ​ David Zendle is an active researcher into the effects of both video games and gambling, and is the author of several key references on the topic of video game monetisation. His most well-known publications deal with the potential effects of loot boxes. His recent work focuses on understanding the diversity of ways that video game play impacts wellbeing, and involves the analysis of large-scale datasets of player behaviour and spending. David is an academic affiliate of the Behavioural Insights Team and holds a research position within the NHS. He is particularly interested in building evidence-based policy in the domain of video game regulation, and has provided oral testimony on video game effects to a variety of government investigations across the globe. David is particularly interested in supervising students with an industry, economics, legal, or behavioural sciences background. He is interested in work on the following topics: The long-term effects of video game play (both positive and negative) Video game monetisation Video game regulation and policy Dark video game design Research themes: Game Analytics Game effects Game policy ​ david.zendle@york.ac.uk Email Mastodon Other links Website LinkedIn https://twitter.com/@davidzendle Twitter Github ​ ​ Themes Game Data Player Research - Previous Next

< Back ​ Kyle Worrall University of York ​ iGGi PG Researcher ​ Available for post-PhD position Kyle is a composer, programmer and researcher who is designing AI music tools for game composers that don't step on their toes. He is also an IMDb accredited composer, a former business owner, and session musician. Kyle’s PhD research first looked to understand why music generation has not been widely adopted in video games - compared to visual procedural generation - when games as a longer medium have the potential to cause listener fatigue in players through repeated exposure to music. Through interviews with 11 professional composers, Kyle found that concerns are multifaceted and not limited only to: generative output quality being low and concerns for loss of authorship. These interviews have helped to focus his further research into improving the expressive quality of generative music and MIDI mock-ups by developing an assumption free pipeline that only needs the pitch, ontime and duration of MIDI notes to create expressive performances. In listening studies, his algorithm (CFE+P) has been shown to outperform the inexpressive baseline, a randomised baseline modelled after Logic X’s Humanise function, and a score cue informed machine learning model called the Basis Mixer. Now Kyle is working to use a Bidirectional Encoding Representation from Transformers (BERT) model to generate variations of musical layers for existing pieces in a way that does not step on composers toes and could add variety to game music after a set period of time in the game. He plans to later test both the generation and performance algorithms in a game play setting to evaluate quality and repetition, as well as potentially evaluate them with professional composers to prove their co-creative potential. ​ kyle.worrall@york.ac.uk Email Mastodon Other links Website https://www.linkedin.com/in/kyleworrallmusic/ LinkedIn https://twitter.com/kjw_audio Twitter https://github.com/KJWAudio Github Supervisors: Dr Jon Hook Dr Tom Collins Dr Josh Reiss Featured Publication(s): Considerations and Concerns of Professional Game Composers Regarding Artificially Intelligent Music Technology Comparative evaluation in the wild: Systems for the expressive rendering of music Reflection Across AI-based Music Composition The Ethics of Creative AI Themes Creative Computing Game Audio Previous Next

< Back The prevalence of loot boxes in mobile and desktop games Link ​ Author(s) D Zendle, R Meyer, P Cairns, S Waters, N Ballou Abstract ​ More info TBA ​ Link

< Back ​ Steph Carter University of York ​ iGGi PG Researcher ​ Available for placement Steph is a York graduate in psycholinguistics with extensive experience in language teaching. They specialise in second language acquisition, human-computer interaction, and gamification. Their research interests also include accessibility in games, disability representation, and games with a purpose. Additionally, Steph has experience designing games for children and young people, as well as in esport analytics. When not immersed in research, Steph enjoys participating in game jams, creating art and obsessively playing rhythm games. They also love spending time with their two cats, Nano and Pixel. Steph's project explores how game design can improve the way we study people who are learning a second language. While games and gamification have become popular tools in education, especially for learning new languages, traditional research methods often overlook the fun and engaging aspects of games. This can make studies less interesting for participants, leading to higher dropout rates and less reliable results. By incorporating game elements into psycholinguistic studies—research that looks at how we understand and produce language—Steph aims to make these studies more engaging. Using this approach, they investigate how gamified experiments help keep participants interested and whether they provide more accurate data. The findings can then be used to develop better tools for language learning and cognitive research, benefiting both researchers and the game development industry. ​ steph.carter@york.ac.uk Email Mastodon https://linktr.ee/steph_carter Other links Website https://www.linkedin.com/in/steph-carter-742891123/ LinkedIn Twitter Github Supervisor(s): Dr Abi Evans ​ Themes Accessibility Applied Games Design & Development Game Data Player Research - Previous Next

< Back Deep visual instruments: realtime continuous, meaningful human control over deep neural networks for creative expression Link ​ Author(s) M Akten Abstract ​ More info TBA ​ Link

< Back Exploring user motor behaviour in bimanual interactive video games Link ​ Author(s) N Pena-Perez, L Tokarchuk, E Burdet, I Farkhatdinov Abstract ​ More info TBA ​ Link

< Back ​ Stefan Stoican University of Essex ​ iGGi Alum ​ ​ Understanding human crowd behaviour via virtual environments: feedback loop between games & research This project uses computer game experiments to explore decision-making in a virtual evacuation simulation. Can one be “saved by the gaze”? Currently, Stefan is investigating how innate social cognition components such as gaze-cuing might inform one’s egress. Do “Us versus Them” scenarios occur? He is also testing how one’s feelings of social identification with the surrounding crowd might modulate one’s risk-taking. Does hoarding prevent herding? Lastly, the project is looking at how cultural differences might affect egress time, when one insists to save personal possessions. More broadly, Stefan’s research concentrates on two key open questions in human crowd behavioural research. Firstly, how do social groups (that the player observes or is a member of) within the simulated crowd of agents affect both individual decision-making and the emergent behaviour of the crowd? Secondly, both empirical and virtual experiments of human crowds have not fully explored the effect of agent or player interactions with underlying landscape features (e.g. layout, signage, debris, large objects and other obstacles, etc). The outcomes of the experimental studies using real human participants will subsequently be used to develop more realistic decision-making and behavioural response algorithms and hence improve the behaviour of simulated agents in follow-on computer games. Stefan’s academic background may lie in Mathematics and Psychology, but his interdisciplinary mindset has constantly pushed him towards games and Computer Science. For his final Mathematics project, he designed an Android app that gamified teaching statistics. As part of his Psychology Masters degree, he investigated the potential benefits of MOBA games such as League of Legends with regard to visual attention. Currently, his extracurricular projects aim to explore video games’ effects on coping with trauma and on one’s perception of vulnerable groups, via commemorative gaming name choices or via in-game refugee storylines, respectively. Please note: Updating of profile text in progress ​ Email Mastodon Other links Website LinkedIn Twitter Github ​ ​ Themes Game AI - Previous Next

< Back ​ Peyman Hosseini Queen Mary University of London ​ iGGi PG Researcher ​ Available for placement Peyman is interested in using his computer science knowledge to support society's well-being. Raised in a family where almost everyone’s work is somehow related to mathematics and its applications, he became passionate about algorithms and combinatorics from an early age. This prompted him to pursue an undergraduate degree in computer engineering with a focus on IT and AI. This background led him to start his PhD at IGGI on building more powerful yet efficient Natural Language Processing models for analysing textual data, a rich and abundant source of gaming feedback. A description of Peyman's research: Peyman's research focuses on advancing deep learning architectures for natural language processing and building tools on top of state-of-the-art models. To contribute to the fundamental understanding and practical application of deep learning in natural language processing, focusing on efficiency and effectiveness, he pursues two main objectives: Designing more efficient models that match or surpass state-of-the-art performance with fewer parameters. Systematically analyzing language models to develop solutions that enhance their effectiveness for end-users, such as game studios. His recent accomplishments towards these goals include: 1. Developing novel attention mechanisms: 1.1 Optimized Attention: 25% parameter reduction 1.2 Efficient Attention: 50% parameter reduction 1.3 Super Attention: 25% parameter reduction with significant performance improvements in language and vision tasks 1.4 All mechanisms demonstrate comparable or superior performance to standard attention across various inputs. 2. Designing and training Hummingbird , a proof-of-concept small language model using Efficient Attention, available on HuggingFace. 3. Conducting a study on large language models' limitations in analyzing lengthy reviews for basic NLP tasks. Proposed solutions offer substantial performance improvements while reducing API costs by more than 90%. ​ s.hosseini@qmul.ac.uk Email Mastodon https://peymanhosseini.net/ Other links Website https://www.linkedin.com/in/peyman-hosseini1 LinkedIn https://twitter.com/Peyman_Hs Twitter https://github.com/Speymanhs Github Supervisors: Dr Ignacio Castro Prof. Matthew Purver Featured Publication(s): Brain Drain Optimization (BRADO) Algorithm to Solve Multi-Objective Expert Team Formation Problem in Social Networks You Need to Pay Better Attention: Rethinking the Mathematics of Attention Mechanism Can We Generate Realistic Hands Only Using Convolution? Lon-ea at SemEval-2023 Task 11: A Comparison of Activation Functions for Soft and Hard Label Prediction GRACER: Improving the Accuracy of RACER Classifier Using A Greedy Approach GRACER: Improving the Accuracy of RACER Classifier Using A Greedy Approach Themes Game AI Player Research - Previous Next

< Back ​ Rokas Volkovas Queen Mary University of London ​ iGGi Alum ​ ​ Application of Neuroevolution to General Video Game Playing In the field of artificial intelligence, great advancements in developing AI capable of playing specific games has been made over last few decades. Over the years, the potential of General Game Playing (GGP) AI, was realized, and thus a new area of research was spawned, focusing mainly on turn-based board games. Rapidly expanding, it was just recently extended to include video games and has morphed into General Video Game Playing (GVGP). The studies in this space of AI are highly attractive due to their solution capacity of being highly transferable. As the field is relatively new, there are many different paths to explore. Some effort has already been put into incorporating the established Genetic Algorithm techniques into the area. The goal of the proposed research is to further develop models using the more complex evolutionary algorithms to find generalist solutions to the problems exposed in GVGP. More specifically, the research will aim to discover the appropriate applications and the modifications necessary of approaches such as Competitive Coevolution, circumventing its drawbacks and evolving populations capable of playing multiple games. Furthermore, in addition to other methods it will be concerned with the application of models developing generalist memory on a slower scale evolution (compared to individual in a population) with continuous state perturbations, to find closer to optimum results - adapting networks of individuals to the fitness landscape. In order to reach the goals of the research a number of experiments will be conducted, using a select few video games as a base performance measure. Training the populations evolved will involve tuning the evolutionary operators as well as altering pre-designed system be- haviours to suitably compare the viability of applied procedures. The success of bridging EA with GVPG, along with its advantages and drawbacks in the field will be readily deter- mined, comparing the solutions found to those of other existing approaches. Specifically, the similarity of the behaviour in evolvability using genetic networks searching for solutions and learning theory, via neural networks, has recently been suggested. Evolution is defined to not have any foresight, but models were built showing how it can remember previously discovered solutions, which would imply that natural selection leans towards long term evolvability. Kostas Kouvaris et. al. further establishes the underlying equivalence of the approaches, applying machine learning techniques to improve the generalisation of EA. The generalization allows combining the features from previous experience to find individuals with new feature combinations, better adapted to unseen environments. Were the exploratory learning methods developed in EA to perform no less satisfactorily in the gaming industry environment, given enough sample data from a handful of well defined behaviours, the AI units could be trained to adapt to the new levels they are placed in. In theory, this would then translate to the same amount of effort producing a larger variety of content or, alternatively, producing the same amount of content with less effort, distributing the excess to other areas of development or eliminating it to lower the total production cost. Rokas is an MEng Electronic Engineering graduate from University of Southampton. Initially, pushed away from programming in school due to being taught Pascal, he realized its power in the compulsory C course in University. Applying the knowledge to building games caused the gradual shift from electronics to software development, with the 4th year modules all having the CS tag. During the undergraduate studies Rokas held the UKESF scholarship and did 2 summer internships at Imagination Technologies. Interests in game and software development got him researching neuroevolutionary machine learning for video games. Please note: Updating of profile text in progress ​ Email Mastodon Other links Website LinkedIn Twitter Github ​ Featured Publication(s): Automatic Game Tuning for Strategic Diversity Practical Game Design Tool: State Explorer Extracting learning curves from puzzle games Mek: Mechanics prototyping tool for 2d tile-based turn-based deterministic games Diversity maintenance using a population of repelling random-mutation hill climbers Themes Game AI - Previous Next

< Back ​ Francesca Foffano University of York ​ iGGi PG Researcher ​ Available for placement Francesca's work represents her fascination with how players elaborate and understand complex situations in video games. She likes to use mixed methods (both qualitative and quantitative) to understand high-level player perception in video games using her competencies in HCI (MSc at the University of Trento) and Psychology (BSc at the University of Padua). Prior to joining the PhD, she developed international experience in industry and research. She worked as Research Fellow on AI and ethics for the European project AI4EU at ECLT (Ca' Foscari University of Venice) and on players' perception of adaptive videogames at Reykjavik University. She also was involved as UX Strategist in creative content for MediaMonks headquarter (Amsterdam). A description of Francesca's research: Players will tell you exactly when they got stuck playing a game, but how we define stuck in the first place is still open to discussion. This PhD research aims to identify how and when this happens to help in predicting when players need support. The goal is to smoothen the player experience by reducing the need for external support (such as online guides, walkthroughs, and online forums) that might affect player immersion. The current stage of the research uses in-depth interviews to understand what players have in common, no matter what task they are doing or game they are playing. So why rely on user tests that consider singular test cases instead of understanding where they originate? ​ ff716@york.ac.uk Email Mastodon https://ffoffano.wordpress.com/about/ Other links Website https://www.linkedin.com/in/foffanofrancesca/ LinkedIn https://twitter.com/FrancescaFoffa1 Twitter Github Supervisor: Prof. Paul Cairns Featured Publication(s): A Survey on AI and Ethics: Key factors in building AI trust and awareness across European citizens. When Games Become Inaccessible: A Constructive Grounded Theory on Stuckness in Videogames Artificial intelligence across europe: A study on awareness, attitude and trust When Games Become Inaccessible: A Constructive Grounded Theory on Stuckness in Videogames Investing in AI for social good: an analysis of European national strategies European Strategy on AI: Are we truly fostering social good? Changes of user experience in an adaptive game: a study of an AI manager Themes Player Research - Previous Next