Converging broadcast and user generated content for interactive ultra-high definition services

Informations projet

COGNITUS

N° de convention de subvention: 687605

DOI

10.3030/687605

Projet clôturé

Date de signature de la CE 12 Novembre 2015

Date de début 1 Janvier 2016

Date de fin 31 Decembre 2018

Financé au titre de

• INDUSTRIAL LEADERSHIP - Leadership in enabling and industrial technologies - Information and Communication Technologies (ICT)

Coût total

€ 4 068 691,25

Contribution de l’UE

€ 3 643 018,26

Coordonné par

BRITISH BROADCASTING CORPORATION
United Kingdom

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Livrables

Documents, reports (16)

COGNITUS deployment and user evaluation report

Evaluation of the platform performed with a closed group of end users and in accordance to the defined use cases will be documented in this deliverable. All WP6 tasks contribute to this deliverable.

Report on user requirements and analysis (Final version)

Based on D1.1 this deliverable will report final results of Tasks 1.2 and 1.3. As the market evolves throughout the project duration, this deliverable will provide an updated version of the market analysis and of the new technologies relevant for COGNITUS.

Architecture and integration specification

Based on the work carried out in Task 5.1 this deliverable will include description of the COGNITUS system architecture, its components, as well as the intercommunication and interoperability procedures facilitating components' integration into the system. Additionally, various other aspects will be covered, such as definition of the relationships, dependencies, and interactions between the system and its environment, system’s functional elements, information management, context management and services.

Report on the quality assessment metrics for COGNITUS system

This deliverable reports work carried out in Task 1.5. Both quality of service and quality of experience will be addressed. Appropriate metrics will be selected and used for both professional and user generated content.

Report on formative expert evaluation results

The purpose of this deliverable is to report work done under T5.4 which includes the results of the formative evaluation of the developed prototypes and applications, focusing on the conformance of the designed technologies to the elaborated user requirements and scenarios, especially in terms of usability and functionality.

Report on dissemination and outreach (first version)

Activities from Task 8.4 are reported in this deliverable together with a plan for next dissemination and outreach steps.

Report on system integration

This deliverable is related to Task 5.3 that unifies the outcomes of other activities to produce the final COGNITUS prototype. Related development and findings will be documented in this deliverable. The report will also include evaluations of technical testing.

Report on COGNITUS graphical user interface designs

This deliverable is related to Task 1.4 and it will provide a comprehensive report on the design of the graphical user interfaces in COGNITUS for different purposes. The designs should reflect the specified user interaction flow and the user requirements collected in Task 1.2 will be taken into consideration in the designs.

Evaluation strategy and planning

This deliverable describes the process / strategy, the time-plan and the data collection approaches for evaluating the application demonstrators. It reports initial work carried out in Task 6.3.

Report on dissemination and outreach (final version)

This report will provide an update on dissemination and outreach activities with respect to D8.1.

Report on metadata structuring analysis and interoperability

Related to Task 2.3, this report describes in full details the defined metadata structure with the full specification of a hierarchy and fields for data coming in different modalities and formats. The specified structure will be followed in all technical modules to facilitate interoperability of the data flow.

User rewards and rights protection

This deliverable is related to Task 2.1. It includes the definition of policy, terms and conditions for user generated content acquisition, as well as the description of a detailed reward scheme to support an easy, friendly and safe submission of the user generated content.

Use case scenario specifications

The purpose of this deliverable is to report the work done under Task 1.1. It will include the definition and the development of a range of scenarios that will demonstrate the potential of the COGNITUS technology and all its innovative features. A user-centred design principle will be employed, in order to collect and report end-user requirements, in accordance to the related market trends and the relevant stakeholders.

Use case deployment and field trials

This deliverable will describe different development stages and the final stage of the deployment process of the two applications and the corresponding results. All WP6 tasks contribute to this deliverable.

Quality assessment, quantification and enhancement of UGC quality for creating UHD content

Research and software development results from Tasks 3.2 and 3.3 will be reported in this deliverable. It will include the experiments and analysis of both initial UGC and the final, composite UHD video. The deliverable will also include a description of integration of expert viewer requirements.

Report on user requirements and analysis (first version)

This deliverable will include work done under Tasks 1.2 and 1.3. It will include the user requirement analysis related to existing solutions, analysis of the conditions at the participating user partner organisations, and a report on a wide range of technologies relevant to COGNITUS, to guarantee that developments meet clear user and market needs.

Open Research Data Pilot (2)

COGNITUS data management plan (first version)

COGNITUS Data Management Plan (DMP) will comply with the EC DMP template. Since DMP is expected to mature during the project, more developed versions of the plan will be included as an additional deliverable at a later stage. Related Task is 7.4.

COGNITUS data management plan (updated version)

This report is an updated version of the initial DMP from D7.2 delivered to support the data management life cycle for all data that will be collected, processed or generated by the project.

Publications

Conference proceedings (38)

An efficient video super-resolution approach based on sparse representation

Auteurs: Farzad Toutounchi, Valia Guerra Ones, Ebroul Izquierdo
Publié dans: 2017 IEEE 19th International Workshop on Multimedia Signal Processing (MMSP), 2017, Page(s) 1-6, ISBN 978-1-5090-3649-3
Éditeur: IEEE
DOI: 10.1109/MMSP.2017.8122217

Complexity-Driven Rate-Control for Parallel HEVC Coding

Auteurs: Carter, Juliette; Blasi, Saverio; Mrak, Marta
Publié dans: Visual Communications and Image Processing 2017 (IEEE VCIP 2017), Numéro 10-13 December 2017, 2017
Éditeur: IEEE
DOI: 10.5281/zenodo.1040286

Fair Treatment and Informed Choice for Contributors of User-Generated Video

Auteurs: Evans, Michael; Kerlin, Lianne; Jones, Rhianne
Publié dans: ACM TVX 2017, Numéro 14-16 June 2017, 2017
Éditeur: ACM
DOI: 10.5281/zenodo.1039879

Rewarding Contributions in a User-Generated Video Online Community

Auteurs: Ntoa, Stavroula; Margetis, George; Stephanidis, Constantine
Publié dans: ACM TVX 2017, Numéro 14-16 June 2017, 2017
Éditeur: ACM
DOI: 10.5281/zenodo.834200

Professional Use of User-Generated Video - Views of Producers and Contributors

Auteurs: Kerlin, Lianne; Evans, Michael; Jones, Rhianne
Publié dans: ACM TVX 2017, Numéro 14-16 June 2017, 2017
Éditeur: ACM
DOI: 10.5281/zenodo.1040270

Maximum component elimination in mixing of user generated audio recordings

Auteurs: Nikolaos Stefanakis, Athanasios Mouchtaris
Publié dans: 2017 IEEE 19th International Workshop on Multimedia Signal Processing (MMSP), 2017, Page(s) 1-6, ISBN 978-1-5090-3649-3
Éditeur: IEEE
DOI: 10.1109/MMSP.2017.8122279

A subjective evaluation on mixtures of crowdsourced audio recordings

Auteurs: Nikolaos Stefanakis, Menelaos Viskadouros, Athanasios Mouchtaris
Publié dans: 2017 25th European Signal Processing Conference (EUSIPCO), Numéro 28/08/2017, 2017, Page(s) 1819-1823, ISBN 978-0-9928626-7-1
Éditeur: IEEE
DOI: 10.23919/EUSIPCO.2017.8081523

Synchronization Ambiguity in Audio Content Generated by Users Attending the Same Public Event

Auteurs: Nikolaos Stefanakis; Athanasios Mouchtaris
Publié dans: ACM TVX 2017, Numéro 14-16 June 2017, 2017
Éditeur: ACM
DOI: 10.5281/zenodo.437157

Improving Cold-Start Recommendations with Social-Media Trends and Reputations

Auteurs: João Santos, Filipa Peleja, Flávio Martins, João Magalhães
Publié dans: International Symposium on Intelligent Data Analysis (IDA), 2017, Page(s) 297-309
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-319-68765-0_25

Balanced Search Space Partitioning for Distributed Media Redundant Indexing

Auteurs: Andre Mourão, Joã Magalhaes
Publié dans: Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval - ICMR '17, 2017, Page(s) 142-149, ISBN 9781450347013
Éditeur: ACM Press
DOI: 10.1145/3078971.3078999

Automatic organisation, segmentation, and filtering of user-generated audio content

Auteurs: Goncalo Mordido, Joao Magalhaes, Sofia Cavaco
Publié dans: 2017 IEEE 19th International Workshop on Multimedia Signal Processing (MMSP), 2017, Page(s) 1-6, ISBN 978-1-5090-3649-3
Éditeur: IEEE
DOI: 10.1109/MMSP.2017.8122276

Automatic organisation and quality analysis of user-generated content with audio fingerprinting

Auteurs: Goncalo Mordido, Joao Magalhaes, Sofia Cavaco
Publié dans: 2017 25th European Signal Processing Conference (EUSIPCO), 2017, Page(s) 1814-1818, ISBN 978-0-9928626-7-1
Éditeur: IEEE
DOI: 10.23919/EUSIPCO.2017.8081522

Live Collaborative Social-Media Video Timelines

Auteurs: Rui Queiros, Nuno Correia, João Magalhães
Publié dans: Proceedings of the 15th International Workshop on Content-Based Multimedia Indexing - CBMI '17, 2017, Page(s) 1-5, ISBN 9781450353335
Éditeur: ACM Press
DOI: 10.1145/3095713.3095750

Studying rate control methods for UHDTV delivery using HEVC

Auteurs: Ivan Zupancic, Matteo Naccari, Marta Mrak, Ebroul Izquierdo
Publié dans: 2016 International Symposium ELMAR, 2016, Page(s) 47-50, ISBN 978-953-184-221-1
Éditeur: IEEE
DOI: 10.1109/ELMAR.2016.7731752

Barbara Made the News - Mining the Behavior of Crowds for Time-Aware Learning to Rank

Auteurs: Flavio Martins, João Magalhes, Jamie Callan
Publié dans: Proceedings of the Ninth ACM International Conference on Web Search and Data Mining - WSDM '16, 2016, Page(s) 667-676, ISBN 9781-450337168
Éditeur: ACM Press
DOI: 10.1145/2835776.2835825

A Subjective Evaluation on Mixtures of Crowdsourced Audio Recordings

Auteurs: Stefanakis N.; Viskadouros M.; Mouchtaris, A.
Publié dans: EUSIPCO 2017, Numéro 1, 2017
Éditeur: EURASIP
DOI: 10.5281/zenodo.1159532

Normalization of Partly Overlapping Audio Recordings from the Same Event Based on Relative Signal Powers

Auteurs: Nikolaos Stefanakis, Athanasios Mouchtaris
Publié dans: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018, Page(s) 3141-3145, ISBN 978-1-5386-4658-8
Éditeur: IEEE
DOI: 10.1109/ICASSP.2018.8461919

Feels Like Being There: Viewers Describe the Quality of Experience of Festival Video Using Their Own Words

Auteurs: Michael Evans; Lianne Kerlin; Olivia Larner; Rosie Campbell
Publié dans: ACM CHI 2018, 2018, ISBN 978-1-4503-5621-3
Éditeur: ACM
DOI: 10.5281/zenodo.1466945

An Open Access User Generated Video Dataset from 2016 Edinburgh Festival

Auteurs: F. Toutounchi, E. Izquierdo
Publié dans: 7th Latin American Conference on Networked and Electronic Media (LACNEM 2017), 2017, Page(s) 3 (4 .)-3 (4 .), ISBN 978-1-78561-825-3
Éditeur: Institution of Engineering and Technology
DOI: 10.1049/ic.2017.0028

An Overview of Recent Video Coding Developments in MPEG and AOMEDIA

Auteurs: Dias, Andre Seixas; Blasi, Saverio; Rivera, Fiona; Izquierdo, Ebroul; Mrak, Marta
Publié dans: IBC Conference 2018, Numéro 1, 2018
Éditeur: IBC
DOI: 10.5281/zenodo.1494930

Enhancing Digital Zoom in Mobile Phone Cameras by Low Complexity Super-Resolution

Auteurs: Toutounchi, Farzad; Izquierdo, Ebroul
Publié dans: IEEE International Conference on Multimedia & Expo Workshops (ICMEW), Numéro 1, 2018
Éditeur: IEEE
DOI: 10.5281/zenodo.1487890

Adaptive Video Encoding for Time-Constrained Compression and Delivery

Auteurs: Dias, André Seixas; Blasi, Saverio; Mrak, Marta; Huang, Shenglan; Izquierdo, Ebroul
Publié dans: European Signal Processing Conference (EUSIPCO), Numéro 1, 2018
Éditeur: IEEE
DOI: 10.5281/zenodo.1494904

Complexity-Constrained Video Encoding and Delivery using Configuration Transfer Matrix

Auteurs: Blasi, Saverio; Dias, André Seixas; Mrak, Marta; Huang, Shenglan; Izquierdo, Ebroul
Publié dans: Picture Coding Symposium (PCS), Numéro 1, 2018
Éditeur: IEEE
DOI: 10.5281/zenodo.1494920

Semi-automatic Video Assessment System

Auteurs: Pedro Martins, Nuno Correia
Publié dans: Proceedings of the 15th International Workshop on Content-Based Multimedia Indexing - CBMI '17, 2017, Page(s) 1-7, ISBN 9781-450353335
Éditeur: ACM Press
DOI: 10.1145/3095713.3095748

Inferring User Gender from User Generated Visual Content on a Deep Semantic Space

Auteurs: David Semedo, João Magalhães, and Flávio Martins
Publié dans: 26th European Signal Processing Conference (EUSIPCO 2018), 2018
Éditeur: IEEE

Temporal Cross-Media Retrieval with Soft-Smoothing

Auteurs: David Semedo and João Magalhães
Publié dans: ACM on Multimedia Conference, 2018
Éditeur: ACM

Ranking News-Quality Multimedia

Auteurs: Gonçalo Marcelino, Ricardo Pinto, João Magalhães
Publié dans: Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval - ICMR '18, 2018, Page(s) 10-18, ISBN 9781450350464
Éditeur: ACM Press
DOI: 10.1145/3206025.3206053

A Vertical PRF Architecture for Microblog Search

Auteurs: Flávio Martins, João Magalhães, Jamie Callan
Publié dans: Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval - ICTIR '18, 2018, Page(s) 107-114, ISBN 9781450356565
Éditeur: ACM Press
DOI: 10.1145/3234944.3234960

Capturing and Reproduction of a Crowded Sound Scene Using a Circular Microphone Array

Auteurs: Stefanakis, N.; Mouchtaris, A.
Publié dans: Signal Processing Conference (EUSIPCO), 2016 24th European, Numéro August 29 – September 2 2016, 2016, Page(s) 1673-1677, ISBN 978-0-9928-6265-7
Éditeur: IEEE
DOI: 10.5281/zenodo.161672

Two-Pass Rate Control for UHDTV Delivery with HEVC

Auteurs: Mrak, Marta; Zupancic, Ivan; Izquierdo, Ebroul; Naccari, Matteo
Publié dans: picture coding symposium 2016 (PCS 2016), Numéro 4-7 December 2016, 2016
Éditeur: IEEE
DOI: 10.5281/zenodo.164863

Automatic Matching and Synchronization of User Generated Videos From a Large Scale Sport Event

Auteurs: Stefanakis, N.; Chonianakis, S.; Mouchtaris, A
Publié dans: International Conference on Acoustic, Speech and Signal Processing (ICASSP) 2017, Numéro March 2017, 2017
Éditeur: IEEE
DOI: 10.5281/zenodo.268407

The open-source turing codec: towards fast, flexible and parallel HEVC encoding

Auteurs: S.G. Blasi, J. Funnell, M. Naccari, M. Mrak, R. Weerakkody
Publié dans: IBC 2016 Conference, Numéro September 2016, 2016, Page(s) 38 (8 .)-38 (8 .), ISBN 978-1-78561-343-2
Éditeur: Institution of Engineering and Technology
DOI: 10.1049/ibc.2016.0038

Advanced Super-Resolution using Lossless Pooling Convolutional Networks

Auteurs: Toutounchi, Farzad; Izquierdo, Ebroul
Publié dans: Numéro 2, 2019
Éditeur: IEEE

Temporal Cross-Media Retrieval with Soft-Smoothing

Auteurs: David Semedo, Joao Magalhaes
Publié dans: 2018 ACM Multimedia Conference on Multimedia Conference - MM '18, 2018, Page(s) 1038-1046, ISBN 9781-450356657
Éditeur: ACM Press
DOI: 10.1145/3240508.3240665

Inferring User Gender from User Generated Visual Content on a Deep Semantic Space

Auteurs: David Semedo, Joao Magalhaes, Flavio Martins
Publié dans: 2018 26th European Signal Processing Conference (EUSIPCO), 2018, Page(s) 1800-1804, ISBN 978-9-0827-9701-5
Éditeur: IEEE
DOI: 10.23919/eusipco.2018.8553425

Modeling Temporal Evidence from External Collections

Auteurs: Flávio Martins, João Magalhães, Jamie Callan
Publié dans: Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining - WSDM '19, 2019, Page(s) 159-167, ISBN 9781450359405
Éditeur: ACM Press
DOI: 10.1145/3289600.3290966

A Benchmark of Visual Storytelling in Social Media

Auteurs: Gonçalo Marcelino, David Semedo, André Mourão, Saverio Blasi, Marta Mrak, Joao Magalhaes
Publié dans: Proceedings of the 2019 on International Conference on Multimedia Retrieval - ICMR '19, 2019, Page(s) 324-328, ISBN 9781450367653
Éditeur: ACM Press
DOI: 10.1145/3323873.3325047

Estimation of Rate Control Parameters for Video Coding using CNN

Auteurs: Maria Santamaria, Ebroul Izquierdo, Saverio Blasi, Marta Mrak
Publié dans: IEEE International Conference on Visual Communications and Image Processing, 2018
Éditeur: IEEE
DOI: 10.5281/zenodo.2598158

Peer reviewed articles (3)

Balancing search space partitions by sparse coding for distributed redundant media indexing and retrieval

Auteurs: André Mourão, João Magalhães
Publié dans: International Journal of Multimedia Information Retrieval, Numéro 7/1, 2018, Page(s) 57-70, ISSN 2192-6611
Éditeur: Springer
DOI: 10.1007/s13735-017-0140-0

Time-Constrained Video Delivery using Adaptive Coding Parameters

Auteurs: Dias, André Seixas; Huang, Shenglan; Blasi, Saverio; Mrak, Marta; Izquierdo, Ebroul
Publié dans: IEEE Transactions on Circuits and Systems for Video Technology, Numéro 1, 2018, ISSN 1558-2205
Éditeur: IEEE
DOI: 10.5281/zenodo.1494925

Two-Pass Rate Control for Improved Quality of Experience in UHDTV Delivery

Auteurs: Zupancic, Ivan; Naccari, Matteo; Mrak, Marta; Izquierdo, Ebroul
Publié dans: IEEE Journal of Selected Topics in Signal Processing, Numéro 1, 2016, ISSN 1932-4553
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.5281/zenodo.2393245