Skip to main content

Visual and textual content re-purposing FOR(4) architecture, Design and video virtual reality games

Deliverables

Basic summarization techniques

This deliverable will report the first version of the techniques developed in T5.3 and T5.4 for the production of multilingual summaries. It will also include an evaluation of the performance of the techniques at this stage.

Initial dissemination plan and dissemination/communication material

This deliverable will present the initial dissemination plan of the project and the creation of the project’s communication material (project presentation, communication kit), which will be used as part of other dissemination activities.

Empirical study of textual data related to visual content

Empirical study of textual data related to visual content will study and define the textual data that are related to WP2 movie and painting databases and will use them to acquire meaningful content from them.

Initial visual and textual dataset creation and legal and ethical requirements

This deliverable will describe the creation of the multimedia and multilingual datasets for the use cases. Furthermore, the deliverable will contain a comprehensive description of the legal and ethical requirements. The deliverable will also cooperate and contribute to D3.1 with textual data coming from freely available content from open web resources or proprietary data collections from v4Design data providers accompanying visual content.

Roadmap towards the implementation of the V4Design platform

D6.1 will provide the time-plan for the development of the V4Design platform. It will specify the functionality of the modules that will be developed within V4Design and of the platform as a whole. In addition, it will provide the specifications for the technical infrastructure and a detailed description of the resources needed to achieve the aforementioned functionality.

Initial use case scenarios and user requirements

This deliverable will describe the initial pilot use cases, as well as the user requirements with regard to the four pilot use cases. It will also include a short outline of the evaluation methodology.

Report on standardisation, dissemination and collaboration activities v1

D8.4 will present the first version of the project’s report on the undertaken standardisation, dissemination and collaboration activities.

Use cases, requirements and evaluation plan

This deliverable will describe an update version of the pilot use cases, as well as the user requirements with regard to the four pilot use cases. It will also include a short outline of the evaluation methodology.

Ontology network and reasoning framework

This deliverable will document the semantic models for mapping the V4Design-pertinent conceptualisations on ontology-related constructs. In addition, it will describe the functionality of the first version of semantic integration and reasoning techniques.

Basic version of interior and exterior localization algorithms & tools

Basic version of interior and exterior localization algorithms & tools tested against the SoA on benchmark data with the first iterations of: (a) keyframe extraction, (b) shot detection, (c) object detection, and (d) scene recognition for building and interior object localization.

First iteration of 3D reconstruction and scientific report

First iteration of 3D reconstruction and scientific report describing and showing the SoA methods for image sequence analysis, and 3D sparse and dense reconstruction.

Technical requirements and architecture

This deliverable details the technical requirements that will be taken into account during the implementation of the V4Design platform. In addition, it describes the functionalities that will be supported by the platform. Finally, it outlines the system architecture that will be used for the implementation of the platform prototypes.

Empirical study of visual content

Empirical study of visual content will define the videos and images that will be needed to be used for video analysis and 3D reconstruction.

Basic version of aesthetics concept extraction algorithms & tools

Basic version of aesthetics concept extraction algorithms & tools will be tested against the SoA on benchmark data which will include the first iterations of: (a) aesthetics feature extraction, (b) emotional reaction prediction on art image database.

Basic version of multilingual semantic text analysis

This deliverable will report on the basic version of concept and concept relation techniques addressed in T3.1, T3.2, T3.3 and T3.4, as well as on their preliminary performance evaluation.

Domain specific search and social media crawling tools

This deliverable will describe the creation of the multimedia and textual datasets based on Web and social media crawling, as well as for the collection of art-related and architecture-related content.

Operational prototypes and user interfaces for architecture and VR game design application

This deliverable will document the UI and UX prototypes, which will be designed for the architecture and video game design applications of V4Design.

1st prototype and applications for architecture and video game design platforms

This deliverable will document the first version of the implementation of the frontend applications for the architecture and video game design platforms that will be considered in V4Design, as well as the backend development, which will deal with the personalisation of the applications and their support.

V4Design website

This deliverable comprises the design and setup of the project website, which will provide up-to-date information on intermediate and final project results.

Searching for OpenAIRE data...

Publications

Semi-automated Creation of Accurate FE Meshes of Heritage Masonry Walls from Point Cloud Data

Author(s): Maarten Bassier, Gilles Hardy, Leidy Bejarano-Urrego, Anastasios Drougkas, Els Verstrynge, Koen Van Balen, Maarten Vergauwen
Published in: Structural Analysis of Historical Constructions - An Interdisciplinary Approach, Issue 18, 2019, Page(s) 305-314
DOI: 10.1007/978-3-319-99441-3_32

Panoramic Image Application for Cultural Heritage

Author(s): Maarten Bassier, Tijs Deloof, Stan Vincke, Maarten Vergauwen
Published in: Digital Heritage. Progress in Cultural Heritage: Documentation, Preservation, and Protection - 7th International Conference, EuroMed 2018, Nicosia, Cyprus, October 29–November 3, 2018, Proceedings, Part I, Issue 11196, 2018, Page(s) 386-395
DOI: 10.1007/978-3-030-01762-0_33

VERGE in VBS 2018

Author(s): Anastasia Moumtzidou, Stelios Andreadis, Foteini Markatopoulou, Damianos Galanopoulos, Ilias Gialampoukidis, Stefanos Vrochidis, Vasileios Mezaris, Ioannis Kompatsiaris, Ioannis Patras
Published in: MultiMedia Modeling, Issue 10705, 2018, Page(s) 444-450
DOI: 10.1007/978-3-319-73600-6_48

VERGE in VBS 2019

Author(s): Stelios Andreadis, Anastasia Moumtzidou, Damianos Galanopoulos, Foteini Markatopoulou, Konstantinos Apostolidis, Thanassis Mavropoulos, Ilias Gialampoukidis, Stefanos Vrochidis, Vasileios Mezaris, Ioannis Kompatsiaris, Ioannis Patras
Published in: MultiMedia Modeling - 25th International Conference, MMM 2019, Thessaloniki, Greece, January 8–11, 2019, Proceedings, Part II, Issue 11296, 2019, Page(s) 602-608
DOI: 10.1007/978-3-030-05716-9_53

Sentence Packaging in Text Generation from Semantic Graphs as a Community Detection Problem

Author(s): Alexander Shvets, Simon Mille, Leo Wanner
Published in: Proceedings of the 11th International Conference on Natural Language Generation, Issue W18-6542, 2018, Page(s) 350–359

Underspecified Universal Dependency Structures as Inputs for Multilingual Surface Realisation

Author(s): Simon Mille, Anja Belz, Bernd Bohnet, Leo Wanner
Published in: Proceedings of The 11th International Natural Language Generation Conference, 2018, Page(s) pages 199–209

The First Multilingual Surface Realisation Shared Task (SR’18): Overview and Evaluation Results

Author(s): Simon Mille, Anja Belz, Bernd Bohnet, Yvette Graham, Emily Pitler, Leo Wanner
Published in: Proceedings of the First Workshop on Multilingual Surface Realisation, Issue W18-3601v2, 2018, Page(s) 1–12

Activity Recognition from Wearable Cameras

Author(s): Panagiotis Giannakeris, Konstantinos Avgerinakis, Stefanos Vrochidis, Ioannis Kompatsiaris
Published in: 2018 International Conference on Content-Based Multimedia Indexing (CBMI), 2018, Page(s) 1-6
DOI: 10.1109/cbmi.2018.8516553

Fusion of Compound Queries with Multiple Modalities for Known Item Video Search

Author(s): Ilias Gialampoukidis, Anastasia Moumtzidou, Stefanos Vrochidis, Ioannis Kompatsiaris
Published in: 2018 IEEE 13th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP), 2018, Page(s) 1-5
DOI: 10.1109/IVMSPW.2018.8448876

Visual and audio analysis of movies video for emotion detection @ Emotional Impact of Movies task MediaEval 2018

Author(s): Elissavet Batziou, Emmanouil Michail, Konstantinos Avgerinakis, Stefanos Vrochidis1, Ioannis Patras, Ioannis Kompatsiaris1
Published in: MediaEval’18, 2018

Exploring Past and Present: VR Reconstruction of the Berlin Gendarmenmarkt

Author(s): Jens Derdaele, Yash Shekhawat, Maarten Vergauwen
Published in: 2018 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct), 2018, Page(s) 287-292
DOI: 10.1109/ismar-adjunct.2018.00088

V4Design for Enhancing Architecture and Video Game Creation

Author(s): Konstantinos Avgerinakis, George Meditskos, Jens Derdaele, Simon Mille, Yash Shekhawat, Luis Fraguada, Eva Lopez, Jolan Wuyts, Anastasios Tellios, Steffen Riegas, Jesper Wachtmeister, Kriszta Doczy, Victor-Jan Vos, Nicolaus Heise, Jens Piesk, Maarten Vergauwen, Leo Wanner, Stefanos Vrochidis, Ioannis Kompatsiaris
Published in: 2018 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct), 2018, Page(s) 305-309
DOI: 10.1109/ismar-adjunct.2018.00091

From TLS Recoding to VR Environment for Documentation of the Governor's Tombs in Dayr al-Barsha, Egypt

Author(s): Roberto de Lima, Maarten Vergauwen
Published in: 2018 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct), 2018, Page(s) 293-298
DOI: 10.1109/ismar-adjunct.2018.00089

A portable grammar-based NLG system for verbalization of structured data

Author(s): Simon Mille, Stamatia Dasiopoulou, Leo Wanner
Published in: Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing - SAC '19, 2019, Page(s) 1054-1056
DOI: 10.1145/3297280.3297571

V4Ann: Representation and Interlinking of Atom-based Annotations of Digital Content




The Digital Tools in the design process of Landscape




Grounded identities: Urban surface conditioning and material technologies




A Multimodal Analytics Platform for Journalists Analyzing Large-Scale, Heterogeneous Multilingual, and Multimedia Content

Author(s): Stefanos Vrochidis, Anastasia Moumtzidou, Ilias Gialampoukidis, Dimitris Liparas, Gerard Casamayor, Leo Wanner, Nicolaus Heise, Tilman Wagner, Andriy Bilous, Emmanuel Jamin, Boyan Simeonov, Vladimir Alexiev, Reinhard Busch, Ioannis Arapakis, Ioannis Kompatsiaris
Published in: Frontiers in Robotics and AI, Issue 5, 2018, ISSN 2296-9144
DOI: 10.3389/frobt.2018.00123

CLUSTERING OF WALL GEOMETRY FROM UNSTRUCTURED POINT CLOUDS

Author(s): M. Bassier, M. Vergauwen
Published in: ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Issue XLII-2/W9, 2019, Page(s) 101-108, ISSN 2194-9034
DOI: 10.5194/isprs-archives-XLII-2-W9-101-2019

Classification of sensor independent point cloud data of building objects using random forests

Author(s): Maarten Bassier, Bjorn Van Genechten, Maarten Vergauwen
Published in: Journal of Building Engineering, Issue 21, 2019, Page(s) 468-477, ISSN 2352-7102
DOI: 10.1016/j.jobe.2018.04.027

An Overview of Innovative Heritage Deliverables Based on Remote Sensing Techniques

Author(s): Maarten Bassier, Stan Vincke, Roberto de Lima Hernandez, Maarten Vergauwen
Published in: Remote Sensing, Issue 10/10, 2018, Page(s) 1607, ISSN 2072-4292
DOI: 10.3390/rs10101607