Bournemouth University’s research team have celebrated their success in an international conference in Beijing, China. Their paper, co-authored by Yinyu Nie, Jian Chang, Ehtzaz Chaudhry, Shihui Guo, Andi Smart (University of Exeter) and Jian Jun Zhang, titled “Semantic modelling of indoor scenes with support inference from a single photograph” was selected as the Best Paper in the 31st International Conference on Computer Animation and Social Agents (CASA 2018) held on May 21-23, 2018 in Beijing, China.
http://casa2018.ios.ac.cn/casa-2018-best-paper-award/

The award winning paper presented an automatic approach for semantic modelling of indoor scenes based on a single photograph. Without using hand-crafted features, the guide indoor scene modelling with feature maps extracted by Fully Convolutional Networks (FCNs). The modelling approach forms part of the development of a preliminary experimentation on modern technologies to enhance visitor experiences using digital innovation, a €7.8m EU funded project (VISTA AR).
The research leading to these results has been co-funded by European Regional Development Funds (ERDF) – VISTA AR project (the Interreg France (Channel) England), the China Scholarship Council and Bournemouth University. For more information about the project (VISTA AR), please visit project website (https://www.vista-ar.eu/)
Best paper award!
Bournemouth University student wins ‘Best Undergraduate Research Paper Award’










BU academic publishes in online newspaper in Nepal
Final day of the ESRC Festival of Social Science
Using Art to enhance Research
Register now to attend the 17th Annual Postgraduate Research Conference – Wednesday 3 December 2025
ECR Funding Open Call: Research Culture & Community Grant – Application Deadline Friday 12 December
MSCA Postdoctoral Fellowships 2025 Call
ERC Advanced Grant 2025 Webinar
Horizon Europe Work Programme 2025 Published
Horizon Europe 2025 Work Programme pre-Published
Update on UKRO services
European research project exploring use of ‘virtual twins’ to better manage metabolic associated fatty liver disease