ForecasterFlexOBM: A multi-view audio-visual dataset for flexible object-based media production

Davide Berghi*1, Craig Cieciura*1, Farshad Einabadi*1, Maxine Glancy*2,

Oliver Camilleri1, Philip Foster1, Asmar Nadeem1, Faegheh Sardari1, Jinzheng Zhao1,

Marco Volino1, Armin Mustafa1, Philip Jackson1, Adrian Hilton1

1Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, UK

2BBC R&D, London, UK

*Equal contributions.

Dataset Entries

OVERVIEW

This page contains the instructions to download the dataset of the paper "ForecasterFlexOBM: A multi-view audio-visual dataset for flexible object-based media production". Before you download the dataset, you must first accept the licence conditions below.

LICENCE AGREEMENT

The dataset is freely available under the following terms and conditions:

  1. All original images and associated data provided may be used for non-commercial research purposes only.
  2. The source of the dataset must be acknowledged in all publications where they are used. This should be done by referencing all of the following:
  3. The data may not be redistributed.

DOWNLOAD

To access, download and/or use the data you must agree to the terms and conditions outlined in the Licence Agreement above.
If you agree, please compile and submit the form below. Once submitted, we will provide you with the username and password required to access the download page. Make sure to save this credentials for future access.

If you encounter any issues while filling the form or have any questions, please contact davide.berghi@gmail.com, c.cieciura@surrey.ac.uk, or farshad.einabadi@surrey.ac.uk. We will manually send you the credentials to access the download page.









Once you have the username and password:





Acknowledgments

The authors would like to thank Director Gavin Saville, Asst. Director Fiona Rivera; Actors Grace Cookey-Gam, Paul Courtenay Hugh and Lisa Kelly; BSL/English Interpreter Sammi Villabon; BBC’s Mark Lomas, Peter Mills, Jack Reynolds, James Shephard and Emma Young; the Institute of Sound Recording. Research supported by EPSRC BBC Prosperity Partnership AI4ME: Future personalized Object-Based Media Experiences Delivered at Scale Anywhere EP/V038087/1. For the purpose of open access, the authors have applied a Creative Commons Attribution (CC BY) licence to any Author Accepted Manuscript version arising.