TU Wien

Consortium Member

The Institute of Visual Computing and Human-Centered Technology is one of four institutes in the faculty of Informatics at TU Wien. The institute investigates the design and development of key technologies in the areas of computer vision, computer graphics, visualization, augmented/mixed/virtual reality, and human-computer interaction. Topics include visual methods in the computational sciences (computer graphics and computer vision) including modelling, image analysis and synthesis, photorealistic rendering, real-time rendering, visualization of large data sets, processing of sensor data as well as the recognition of contained patterns and structures. Further topics are socio-technical systems, mobile and ubiquitous technologies, people-centered design and evaluation, as well as ethics and responsible research and innovation.
The Computer Vision Lab (CVL) is devoted to both basic and applied research in the field of Computer Vision, which comprehends the natural world through images, image sequences, and films and reconstructs its properties, such as shape, illumination, and color distributions. The theoretical backbones at CVL are: Image Processing, Feature Extraction and Object Recognition, Document Analysis, 3-D Computer Vision, Motion Detection and Tracking, Multi-Spectral Imaging (MSI), and Machine Learning (Neural Networks, Adaptive Methods, Deep Learning, etc.) which are employed in applied research in areas such as Cultural Heritage Applications, Ambient Assisted Living (AAL), Medical Imaging, Micro-Array Image Analysis (e.g. in Biotechnology), Image Sequence Analysis, Surveillance, Image Compression and others.
The Institute of Information Systems Engineering, also at the faculty of Informatics, provides foundational and advanced techniques, algorithms, design and engineering approaches to model complete lifecycles of data-intensive and distributed information systems.
The Data and Text analytics group at the Research Unit E-Commerce performs research and creates solutions in the Business-2-Business (B2B) and Business-2-Consumer (B2C) domains, in Data Intelligence and in High Performance Computing (HPC) Systems. Topics include process modeling, semantic web research, ontology engineering, information integration, network analysis, text mining. Further topics are online analytics, data mining, and machine learning as well as recommender systems and information retrieval.

Role in the Project

TUW is work package leader and responsible for developing and implementing techniques for automated media analysis. The objective is the extraction of meaningful content-based information from audio-visual and textual materials. This includes text analysis by creating links between words and concepts (texts) and patterns detection in multiple modalities (film, video, image, audio recordings).

Team Members

David Banyasz

Master student, researcher and developer (automated text analysis)


TU Wien

Christian Breiteneder

Senior Advisor


TU Wien

Allan Hanbury

TUW-TA team leader, supervisor (automated text analysis)


TU Wien

Daniel Helm

Researcher and developer (automated image analysis)


TU Wien

Sebastian Hofstätter

PhD student, researcher and developer (automated text analysis)


TU Wien

Fabian Jogl

Master student, researcher and developer (automated image analysis)


TU Wien

Martin Kampel

Supervisor (automated image analysis)


TU Wien

Anna Marakasova

PhD student, researcher and developer (automated text analysis) (until January 2022)


TU Wien

Pia Pachinger

Ph.D. student, researcher, and developer (automated text analysis)


TU Wien

Robert Sablatnig

Work Package Leader, member of the Management Board, TUW-CVL team leader (automated image analysis), main contact and representative of TU Wien


TU Wien

Mete Sertkan

PhD student, researcher and developer (automated text analysis)


TU Wien

Josef Weber

Master student, researcher and developer (automated text analysis)


TU Wien

Article Author

Video Shot Analysis for Digital Curation and Preservation of Historical Films

Daniel Helm, Martin Kampel, Video Shot Analysis for Digital Curation and Preservation of Historical Films, in: Proceedings of the 17th Eurographics Workshop on Graphics and Cultural Heritage (November 2019), 25-28.

Shot Boundary Detection for Automatic Video Analysis of Historical Films

Daniel Helm, Martin Kampel, Shot Boundary Detection for Automatic Video Analysis of Historical Films, in: Marco Cristani, Andrea Prati, Oswald Lanz, Stefano Messelodi, Nicu Sebe (eds.), New Trends in Image Analysis and Processing – ICIAP 2019. Lecture Notes in Computer Science, vol. 11808 (Cham: Springer, 2019), 137-147.

Overscan Detection in Digitized Analog Films by Precise Sprocket Hole Segmentation

Daniel Helm, Martin Kampel, Overscan Detection in Digitized Analog Films by Precise Sprocket Hole Segmentation, in: George Bebis et al. (eds.), Advances in Visual Computing. ISVC 2020. Lecture Notes in Computer Science, vol. 12509 (Cham: Springer, 2020), 148-159.

Frame Border Detection for Digitized Historical Footage

Daniel Helm, Bernhard Pointner, Martin Kampel, Frame Border Detection for Digitized Historical Footage, in: Proceedings of the Joint Austrian Computer Vision and Robotics Workshop (August 2020), 114-115.

Graph-based Shot Type Classification in Large Historical Film Archives

Daniel Helm, Florian Kleber, Martin Kampel, Graph-based Shot Type Classification in Large Historical Film Archives, in: Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, vol. 4 (February 2022), 991-998.

HistShot: A Shot Type Dataset based on Historical Documentation during WWII

Daniel Helm, Florian Kleber, Martin Kampel, HistShot: A Shot Type Dataset based on Historical Documentation during WWII, in: Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods, vol. 1 (February 2022), 558-565.

HISTORIAN: A Large-Scale Historical Film Dataset with Cinematographic Annotation

Daniel Helm, Fabian Jogl, Martin Kampel, Historian: A Large-Scale Historical Film Dataset with Cinematographic Annotation, in: 2022 IEEE International Conference on Image Processing (ICIP), (October 2022), 2087-2091.

Participation in Public Deliverables

D1.5 EU Commission Policy Brief: Fostering Media-Literate Cultural Memory

Contributor

D1.6 EU Commission Policy Brief: ECCCH – No Cultural Heritage Cloud Without Audiovisual Media

Contributor

D2.1 Advanced Digitization Tool Kit

Contributor

D3.4 Framework for Tool Kits, Best Practice Models and Future Network Activities

Contributor

D4.1 Controlled Vocabularies Specification

Contributor

D4.4 Translation of Selected Russian Text Documents

Author, Contributor

D8.2 Project Design and Identity Handbook [revised edition]

Contributor

Participation in Events

Pre-Kick-off Meeting

Meeting

Friday, 19.10.2018, 09:15 to Saturday, 20.10.2018, 18:00

Kick-off Meeting

Meeting

Wednesday, 27.02.2019, 09:15 to Friday, 01.03.2019, 20:00

Advanced Digitization

Workshop

Wednesday, 20.03.2019, 09:30 to Friday, 22.03.2019, 16:00

Curation of Engagement Levels

Workshop

Monday, 20.05.2019, 09:00 to Tuesday, 21.05.2019, 17:00

Shot Boundary Detection for Automatic Video Analysis of Historical Films

Presentation

Monday, 09.09.2019

Video Shot Analysis for Digital Curation and Preservation of Historical Films

Presentation

Wednesday, 06.11.2019 to Saturday, 09.11.2019

Vocabularies

Workshop

Thursday, 21.11.2019, 13:45 to Friday, 22.11.2019, 17:00

NonAV Metadata (Citavi)

Mini-Workshop

Wednesday, 27.05.2020, 13:00 to Wednesday, 27.05.2020, 17:00

Overscan Detection in Digitized Analog Films by Precise Sprocket Hole Segmentation

Presentation

Monday, 05.10.2020, 10:30

Text Analysis

Mini-Workshop

Tuesday, 12.01.2021, 09:30 to Tuesday, 12.01.2021, 13:00

Relation Detection

Mini-Workshop

Tuesday, 26.01.2021, 14:00 to Tuesday, 26.01.2021, 17:00

Consortium Meeting

Meeting

Tuesday, 23.02.2021, 15:00 to Wednesday, 24.02.2021, 19:00

Video Analysis in Large Historical Film Collections

Presentation

Monday, 31.05.2021, 15:00 to Monday, 31.05.2021, 17:00

VHH Research Seminar – Session 5: Soviet Filmed Atrocity Images on American Movie Screens, 1942–1945, and Some Partial Answers to the Questions of What, When, Where and By Whom?

Research Seminar

Tuesday, 15.06.2021, 18:00 to Tuesday, 15.06.2021, 20:00

HistShot: A Shot Type Dataset based on Historical Documentation during WWII

Presentation

Thursday, 03.02.2022, 15:00 to Thursday, 03.02.2022, 16:15

Graph-based Shot Type Classification in Large Historical Film Archives

Presentation

Monday, 07.02.2022, 16:45 to Monday, 07.02.2022, 18:30

A Time-Optimized Content Creation Workflow for Remote Teaching

Presentation

Saturday, 05.03.2022, 11:15 to Saturday, 05.03.2022, 12:30

Tracing Visual Evidence of the Holocaust: Challenges of the Digital Curation of Liberation Footage across Archives and Disciplines

Panel

Tuesday, 26.04.2022, 09:00 to Tuesday, 26.04.2022, 10:30

Moving Images from the Archives. Historical Footage of Nazi Crimes in Documentaries

Conference

Sunday, 08.05.2022, 18:00 to Tuesday, 10.05.2022, 17:00

VHH Research Seminar – Session 11: By Filming, by Writing. Photographic Testimonies of the Nazi Camps

Research Seminar

Thursday, 09.06.2022, 16:00 to Thursday, 09.06.2022, 18:00

Migrating Images and Image Migration: How Popular Culture Shapes the Visual History of the Holocaust

Conference

Monday, 12.09.2022, 18:00 to Wednesday, 14.09.2022, 20:00

HISTORIAN: A Large-Scale Historical Film Dataset with Cinematographic Annotation

Presentation

Monday, 17.10.2022, 10:00 to Monday, 17.10.2022, 12:30

Professional Search in Context

Presentation

Wednesday, 02.11.2022, 13:00 to Wednesday, 02.11.2022, 14:00

Holocaust Remembrance Day – Digitales Kuratieren

Presentation

Friday, 27.01.2023, 09:00 to Friday, 27.01.2023, 12:30