European Commission logo
español español
CORDIS - Resultados de investigaciones de la UE
CORDIS

Repurposing and enriching images for immersive storytelling through smart digital tools

Resultado final

Final set of contextual data generation and annotation tools

This deliverable will consist the final prototype of the contextual data generation and annotation tools.

Second set of 3D and semantic depth reconstruction and rendering tools

This deliverable will consist of the second prototype versions of the 3D and semantic depth reconstruction tools, as well as rendering tools with 3D effects.

Final set of 3D and semantic depth reconstruction and rendering tools

This deliverable will consist of the final prototype versions of the 3D and semantic depth reconstruction tools, as well as rendering tools with 3D effects.

First set of 3D and semantic depth reconstruction and rendering tools

This deliverable will consist of the first prototype versions of the 3D and semantic depth reconstruction tools, as well as rendering tools with 3D effects.

FotoInMotion use case applications v2

This deliverable will include the implementation of the 2nd version of the customization of the aforementioned FotoInMotion platform (see D4.3) to be applied in the three use cases. Live documents and repositories will be also available, describing the platform functionalities in regards to the specific use case requirements.

Second set of contextual data generation and annotation tools

This deliverable will consist of the second prototype versions of the contextual data generation and annotation tools.

FotoInMotion use case applications v1

This deliverable will include the implementation of the 1st version of the customization of the aforementioned FotoInMotion platform (see D4.2) to be applied in the three use cases. Live documents and repositories will be also available, describing the platform’s functionalities in regards to the initial use cases specific requirements.

FotoInMotion platform and APIs

This deliverable will include (i) a prototype platform based on a user-friendly, highly intuitive and visual web solution and (ii) live documents and repositories that will continuously reflect the latest state of the system implementation, describing its main functionalities and capabilities with frequent releases.

First set of contextual data generation and annotation tools

This deliverable will consist of the first prototype versions of the contextual data generation and annotation tools.

Final FotoInMotion platform and applications

This deliverable will include the final version of the FotoInMotion platform and the three use case applications.

FotoInMotion use cases and requirements v1

This deliverable will specify the user requirements for the three FotoInMotion use cases, and the requirements for the overall FotoInMotion platform.

2D image editing requirements and mechanisms

This deliverable will contain the analysis of the requirements in terms of 2D image processing, SoA of existing reusable options and design specifications, as well as API code and documentation

Overall system architecture

This deliverable will document the complete system architecture of the platform and supporting APIs. Live documents and repositories will be available to continuously reflect the latest state of the system architecture.

Specifications for 3D effects

Mock-up content and specification document for 3D effects.

Communication and dissemination plan

This report will include all details regarding the Communication and Dissemination Plan and activities for the whole project.

FotoInMotion use cases and requirements v2

This deliverable will provide an update of D1.2 based on the initial feedback collected during the first cycles of pilot testing

Communication and dissemination report v1

This deliverable will include the 1st version of the evaluation reporting the outcomes of the Communication and Dissemination activities.

Functional specification of contextual data generation and annotation tools and digital event framework definition

This deliverable will provide the description of the functionality to be included in the tools to be developed in the first three tasks of this WP, meeting the user requirements elicited in WP1. It will also provide the definition of the digital event framework and of the interfaces exposed to gather the obtained contextual data and to enable sharing and re-use of this rich data related to the picture taken

Final pilots report

A final version of a consolidated evaluation report.

Pilots report v1

A first version of the three pilot evaluation results

Innovation report on creative industries v1

This deliverable will analyse existing products and services, an analysis of their main limitations, as well as a discussion of the innovation opportunities for FotoInMotion.

Communication and dissemination report v2

This deliverable will include the final version of the evaluation and reporting of the outcomes of the Communication and Dissemination activities carried out in D6.4, as a follow-up of D6.5

Innovation report on creative industries v2

This deliverable will provide an update of D1.1 taking into account the developments that took place during the first project year

Pilots report v2

A second version of the three pilot evaluation results.

Pilot plan

This plan will focus on specifying the setup of the initial system for pre-pilot testing, as well as a first round for small-scale testing of the system targeting mostly end users within the consortium.

Data management plan v1

This deliverable will document the data management plan of the project, in accordance with H2020 data management requirements.

Data management plan v2

This deliverable will document the updated data management plan.

FotoInMotion website online

This deliverable includes the website of FotoInMotion and a report describing its functionalities and content.

Publicaciones

Semantic Storytelling Automation: A Context-Aware and Metadata-Driven Approach.

Autores: Viana P., Carvalho P., Andrade M.T., Jonker P. P., Papanikolaou V., Teixeira I.N., Vilaça L., Pinto J.P., Costa T.
Publicado en: Proceedings of the 28th ACM International Conference on Multimedia, 2020
Editor: ACM International Conference on Multimedia
DOI: 10.1145/3394171.3416528

Creating automatic storytelling videos from still images: a semantically-aware approach.

Autores: Viana P. , Carvalho P. , Andrade M.T., Teixeira I.N., Jonker P. , Vilaça L. , Pinto J.P., Costa T
Publicado en: 25th International Conference on Pattern Recognition, 2021
Editor: 25th International Conference on Pattern Recognition

Inferring Contextual Data from Real-WorldPhotography.

Autores: Costa T., Andrade M.T, Viana P.
Publicado en: Advances in Intelligent Systems and Computing, 2020
Editor: Advances in Intelligent Systems and Computing

From a Still Image to a Semantically Aware Video: A Context and Metadata-driven Automatic Media Production Framework.

Autores: Viana P., Carvalho P. , Andrade M.T., Teixeira I.N., Jonker P. , Vilaça L. , Pinto J.P., Costa T.
Publicado en: The 17th ACM SIGGRAPH European Conference on Visual Media Production, 2020, ISSN 0000-0000
Editor: 17th ACM SIGGRAPH European Conference

FiM’s DE - the communication package for the creative pipeline

Autores: H. Castro, M. T. Andrade, P. Viana
Publicado en: Multimedia Tools and Applications, 2021, ISSN 1380-7501
Editor: Kluwer Academic Publishers
DOI: 10.1007/s11042-020-10282-0

Efficient CIEDE2000-based Color Similarity Decision for Computer Vision

Autores: Americo Pereira, Pedro Carvalho, Gil Coelho, Luis Corte-Real
Publicado en: IEEE Transactions on Circuits and Systems for Video Technology, 2019, Página(s) 1-1, ISSN 1051-8215
Editor: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tcsvt.2019.2914969

Improving Audiovisual Content Annotation Through a Semi-automated Process Based on Deep Learning

Autores: Luís Vilaça, Paula Viana, Pedro Carvalho, Teresa Andrade
Publicado en: Proceedings of the Tenth International Conference on Soft Computing and Pattern Recognition (SoCPaR 2018), Edición 942, 2020, Página(s) 66-75, ISBN 978-3-030-17064-6
Editor: Springer International Publishing
DOI: 10.1007/978-3-030-17065-3_7

Buscando datos de OpenAIRE...

Se ha producido un error en la búsqueda de datos de OpenAIRE

No hay resultados disponibles