Recent 12 Older Addressing the cold start problem in recommender systems Βι¶ΉΤΌΕΔ iPlayer has a constant stream of new users and content. How can we make recommendations when there isn't enough information about either? Blog post on 14 Jul 2023 We need to talk about recommendations: helping curators and data scientists work better together Communication is key to enabling curators and data scientists to work towards the same goals - but often recommendation systems are understood in very different ways. Blog post on 17 May 2023 AI-assisted journalism: our open-source quote extraction system We are releasing an open-source quote extraction and attribution system called Citron. Blog post on 19 Apr 2023 Social TV and the future of data The future of social TV is fun, smart and safe - launching next-generation social TV in collaboration with Tim Berners Lee's team. Blog post on 26 Oct 2022 A new dataset to improve TV production using artificial intelligence and machine learning A TV shoot designed to be edited by a machine learning program or artificial intelligence. Our open-source dataset is for AI production and intelligent cinematography researchers. Blog post on 17 May 2022 Using artificial intelligence to automatically segment media content Media consumption continues to evolve, with rising interest in short-form content - and segments or clips of Βι¶ΉΤΌΕΔ programmes are an excellent source. Blog post on 4 Apr 2022 Releasing the largest British Sign Language dataset for research A new dataset of British Sign Language footage to help academic researchers interested in automated sign language recognition has just been released. Blog post on 19 Nov 2021 Sustainable futures: Designing a secure carbon calculator Investigating the potential of a personal data-driven climate impact calculator that puts users' privacy first. Blog post on 26 Oct 2021 Personal data stores: building and trialling trusted data services Sir Tim Berners-Lee, wants to reconfigure the web so users own and control their data. We are investigating how to give young people the chance to do just that. Blog post on 29 Sep 2021 Ethics of recommendation systems in public service media We are collaborating with the Ada Lovelace Institute to explore the ethical implications of recommendation systems in public service media. Blog post on 5 Aug 2021 Creating automatic video summaries with text queries Can we auto summarise a video to help producers and editors work efficiently? Blog post on 1 Jul 2021 Putting audience data at the heart of the Βι¶ΉΤΌΕΔ What could we do if carefully protected audience data 'pods' were a part of the Βι¶ΉΤΌΕΔ's services and systems? Blog post on 11 Sep 2020 Βι¶ΉΤΌΕΔ R&D Showcase 2020 Personal. Efficient. Sustainable. Discover how Βι¶ΉΤΌΕΔ R&D is helping to build a better Βι¶ΉΤΌΕΔ in these 3 interactive experiences. Blog post on 7 Sep 2020 Interpreting Convolutional Neural Networks for Video Coding Using machine learning for the improvement of video compression. Blog post on 2 Jun 2020 Creating A Personalised Documentary: What The Audience Told Us Following some user testing, people gave us feedback on what they enjoyed and whether they would watch a new format like this. Blog post on 23 Jan 2020 Recent 12 Older