AI and Process Automation for Sustainable Entertainment and Media

Informazioni relative al progetto

EMERALD

ID dell’accordo di sovvenzione: 101119800

DOI

10.3030/101119800

Progetto chiuso

Data della firma CE 23 Maggio 2023

Data di avvio 1 Ottobre 2023

Data di completamento 31 Marzo 2026

Finanziato da

• Digital, Industry and Space

Costo totale

€ 2 689 186,25

Contributo UE

€ 2 191 223,75

Coordinato da

UNIVERSIDAD POMPEU FABRA
Spain

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Documents, reports (5)

Plan for Dissemination, Communication and Exploitation

Plan for lifetime of project and subsequently of results, with links to the white papers, web resources and publications

Tools for digitising physical talent and objects

Report detailing tools for digitising physical talent and objects and extracting PBR data for post-production

Low-level feature extraction from compressed video

Report on tools for using low level features extracted from compressed domain sources in partner workflows

Evaluation Plan

Methods and metrics to evaluate algorithms, datasets and prototypes (a) under partner laboratory conditions and (b) field trials and demonstrations

Tool for colour grading assistance in postproduction

Report on the development in written and audiovisual form

Data sets, microdata, etc (2)

Interim dataset for video matting algorithms training

Interim dataset for video matting algorithms training (80 preliminary captures and processed videos)

Natural history dataset

Natural history dataset using BBC production material to better represent the material BBC tools address

Demonstrators, pilots, prototypes (1)

Player classification and action spotting

Algorithms and tools for efficient for player classification and action spotting

Data Management Plan (1)

Data Management Plan

Datasets, papers and open-source planning via Open Science guidelines

Websites, patent fillings, videos etc. (1)

Project Website and social media channels

Website and social media channels with PU deliverables and information, links to demo materials and data repositories

Other (1)

Algorithms for head- and body-pose estimation

End-to-end DL algorithms for head- and body-pose estimation with structural constraints

Pubblicazioni

Conference proceedings (12)

An Empirical Study of Reducing AV1 Decoder Complexity and Energy Consumption via Encoder Parameter Tuning

Autori: Vibhoothi Vibhoothi, Julien Zouein, Shanker Shreejith, Jean-Baptiste Kempf, Anil Kokaram
Pubblicato in: 2025 Picture Coding Symposium (PCS), 2026
Editore: IEEE
DOI: 10.1109/PCS65673.2025.11417575

NLML-HPE: Head Pose Estimation with Limited Data via Manifold Learning

Autori: Mahdi Ghafourian, Federico M. Sukno
Pubblicato in: 2025 IEEE International Joint Conference on Biometrics (IJCB), 2026
Editore: IEEE
DOI: 10.1109/IJCB65343.2025.11411574

Unravelling the Power of Single-Pass Look-Ahead in Modern Codecs for Optimized Transcoding Deployment

Autori: Vibhoothi, Julien Zouein, François Pitié, Anil Kokaram
Editore: Proceedings of the 2024 NAB Broadcast Engineering and Information Technology (BEIT) Conference
DOI: 10.48550/ARXIV.2404.05321

ReTiDe: Real-Time Denoising for Energy-Efficient Motion Picture Processing with FPGAs

Autori: Changhong Li, Clément Bled, Rosa Fernandez, Shreejith Shanker
Pubblicato in: Proceedings of the 22nd ACM SIGGRAPH European Conference on Visual Media Production, 2026
Editore: ACM
DOI: 10.1145/3756863.3769710

LiteVPNet: A Lightweight Network for Video Encoding Control in Quality-Critical Applications

Autori: Vibhoothi Vibhoothi, François Pitié, Anil Kokaram
Pubblicato in: 2025 Picture Coding Symposium (PCS), 2026
Editore: IEEE
DOI: 10.1109/PCS65673.2025.11417531

Towards Consistent Automatic Colour Grading: A Scene-Aware Neural Network for Illuminant Estimation

Autori: Bold-Erdene Ganbaatar, François Pitié
Pubblicato in: Proceedings of the 22nd ACM SIGGRAPH European Conference on Visual Media Production, 2026
Editore: ACM
DOI: 10.1145/3756863.3769704

Demystifying the use of Compression in Virtual Production

Autori: Anil Kokaram, Vibhoothi Vibhoothi, Julien Zouein, François Pitié, Christopher Nash, James Bentley, Philip Coulam-Jones
Pubblicato in: SMPTE Media Technology Summit 2024, 2024
Editore: SMPTE
DOI: 10.48550/arXiv.2411.00547

Multi Task Denoiser Training for Solving Linear Inverse Problems

Autori: Clément Bled, François Pitié
Pubblicato in: Proceedings of the 22nd ACM SIGGRAPH European Conference on Visual Media Production, 2026
Editore: ACM
DOI: 10.1145/3756863.3769703

Two Weakly Supervised Approaches for Role Classification of Soccer Players

Autori: Alejandro Cartas, Coloma Ballester, Gloria Haro
Pubblicato in: Proceedings of the 7th ACM International Workshop on Multimedia Content Analysis in Sports, 2024
Editore: ACM
DOI: 10.1145/3689061.3689072

AV1 Motion Vector Fidelity and Application for Efficient Optical Flow

Autori: Julien Zouein, Vibhoothi Vibhoothi, Anil Kokaram
Pubblicato in: 2025 Picture Coding Symposium (PCS), 2026
Editore: IEEE
DOI: 10.1109/PCS65673.2025.11417638

SoccerHigh: A Benchmark Dataset for Automatic Soccer Video Summarization

Autori: Artur Díaz-Juan, Coloma Ballester, Gloria Haro
Pubblicato in: Proceedings of the 8th International ACM Workshop on Multimedia Content Analysis in Sports, 2026
Editore: ACM
DOI: 10.1145/3728423.3759410

Leveraging AV1 Motion Vectors for Fast and Dense Feature Matching

Autori: Julien Zouein, Hossein Javidnia, François Pitié, Anil Kokaram
Pubblicato in: 2025 IEEE 4th International Conference on Intelligent Reality (ICIR), 2026
Editore: IEEE
DOI: 10.1109/ICIR68135.2025.11361611

Peer reviewed articles (1)

Using Single-Pass Look-Ahead in Modern Codecs for Optimized Transcoding Deployment

Autori: Vibhoothi Vibhoothi, Julien Zouein, François Pitié, Anil Kokaram
Pubblicato in: SMPTE Motion Imaging Journal, Numero 133, 2025, ISSN 1545-0279
Editore: Society of Motion Picture and Television Engineers (SMPTE)
DOI: 10.5594/JMI.2024/WSSG3140