Comprehensive data-driven Risk and Threat Assessment Methods for the Early and Reliable Identification, Validation and Analysis of migration-related risks

Risultati finali

Human rights implications checklist to be used in the planning and development of the CRiTERIA tools

This deliverable presents the first version of the developed methods for online content collection and audiovisual analysis Visual media analysis and annotation Automatic Speech Recognition and results of their preliminary evaluation

System Architecture & Technology Roadmap

THis report outlines the technology roadmap and specifications of the initial prototype interfacing the core platform with the information services of WP5 and WP6

Approaches for automated Explanation, Verification and Validation in Risk Analysis

This report will summarize the approaches for validation and explanation prioritized in T61 and T62

Data and Knowledge Management Plan

Plan that describes the data used in the project as well as the way the project deals with this data and with the knowledge created in the project

First Report on Communication and Dissemination

Report on the communication and dissemination activities performed The activities themselves will be tracked on a continuous basis see T93 and published in a consolidated manner within this deliverable

Dissemination and Communication Plan

Plan for the dissemination and communication activities of the project as well as of individual project partners For communication this will describe the communication strategy and planned actitivies channels timeline and formats Furthermore work on the projects identity a cohesive concept for representing the project to the outside visual identity as well as work on website and online social media presence will be summarized

Report of CRiTERIA Ethical Principles and Practices

This will document the ethical concerns CRiTERIA can come across and the way the partners are dealing with these concerns

CRiTERIA Platform and Dashboard: First Prototype Release

D7.2 delivers an initial prototype including API framework, reflecting feedback from other WPs in terms of design and functionality.

H - Requirement No. 2

Templates of the informed consent forms and information sheets (in language and terms intelligible to the participants) including personal data processing must be submitted as a deliverable.

Pubblicazioni

T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformers

Autori: Mariano V. Ntrougkas, Nikolaos Gkalelis, Vasileios Mezaris
Pubblicato in: IEEE Access, Numero 12, 2024, Pagina/e 76880-76900, ISSN 2169-3536
Editore: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/access.2024.3405788

Unveiling the silent majority: stance detection and characterization of passive users on social media using collaborative filtering and graph convolutional networks

Autori: Zhiwei Zhou, Erick Elejalde
Pubblicato in: EPJ Data Science, Numero 13, 2024, ISSN 2193-1127
Editore: Springer
DOI: 10.1140/epjds/s13688-024-00469-y

ViGAT: Bottom-up event recognition and explanation in video using factorized graph attention network

Autori: Nikolaos Gkalelis; Dimitrios Daskalakis; Vasileios Mezaris
Pubblicato in: IEEE Access, 2022, ISSN 2169-3536
Editore: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.48550/arxiv.2207.09927

The social stratification of internal migration and daily mobility during the COVID-19 pandemic

Autori: Erick Elejalde, Leo Ferres, Victor Navarro, Loreto Bravo, Emilio Zagheni
Pubblicato in: Scientific Reports, Numero 14, 2024, ISSN 2045-2322
Editore: Nature Publishing Group
DOI: 10.1038/s41598-024-63098-5

Bridging Qualitative Data Silos: The Potential of Reusing Codings Through Machine Learning Based Cross-Study Code Linking

Autori: Sergej Wildemann, Claudia Niederée, Erick Elejalde
Pubblicato in: Social Science Computer Review, Numero 42, 2024, Pagina/e 760-776, ISSN 0894-4393
Editore: SAGE Publications
DOI: 10.1177/08944393231215459

Migration Reframed? A multilingual analysis on the stance shift in Europe during the Ukrainian crisis

Autori: Sergej Wildemann, Claudia Niederée, Erick Elejalde
Pubblicato in: Proceedings of the ACM Web Conference 2023, Numero 5, 2023, Pagina/e 2754-2764
Editore: ACM
DOI: 10.1145/3543507.3583442

Masked Feature Modelling for the unsupervised pre-training of a Graph Attention Network block for bottom-up video event recognition

Autori: Dimitrios Daskalakis, Nikolaos Gkalelis, Vasileios Mezaris
Pubblicato in: 2023 IEEE International Symposium on Multimedia (ISM), Numero abs/1807.03748, 2024, Pagina/e 247-250
Editore: IEEE
DOI: 10.1109/ism59092.2023.00047

ITI-CERTH participation in ActEV and AVS Tracks of TRECVID 2022

Autori: Konstantinos Gkountakos; Damianos Galanopoulos; Despoina Touska; Konstantinos Ioannidis; Stefanos Vrochidis; Vasileios Mezaris; Ioannis Kompatsiaris
Pubblicato in: Proc. TRECVID 2022 Workshop, 2022
Editore: NIST
DOI: 10.5281/zenodo.7431865

Are All Combinations Equal? Combining Textual and Visual Features with Multiple Space Learning for Text-Based Video Retrieval

Autori: Damianos Galanopoulos; Vasileios Mezaris
Pubblicato in: Proc. ECCV 2022 Workshops, 2022
Editore: Springer
DOI: 10.1007/978-3-031-25069-9_40

Cross-modal networks and dual softmax operation for MediaEval NewsImages 2022

Autori: Galanopoulos, Damianos; Mezaris, Vasileios
Pubblicato in: Proc. 2022 Multimedia Evaluation Workshop (MediaEval'22), 2023
Editore: CEUR
DOI: 10.5281/zenodo.7669743

Learning Visual Explanations for DCNN-Based Image Classifiers Using an Attention Mechanism

Autori: Gkartzonika, Ioanna; Gkalelis, Nikolaos; Mezaris, Vasileios
Pubblicato in: Proc. ECCV 2022 Workshops, 2022
Editore: Springer
DOI: 10.48550/arXiv.2209.11189

Gated-ViGAT: Efficient Bottom-Up Event Recognition and Explanation Using a New Frame Selection Policy and Gating Mechanism

Autori: Gkalelis, Nikolaos; Daskalakis, Dimitrios; Mezaris, Vasileios
Pubblicato in: Proc. IEEE Int. Symposium on Multimedia (ISM), 2022
Editore: IEEE
DOI: 10.1109/ISM55400.2022.00024

TAME: Attention Mechanism Based Feature Fusion for Generating Explanation Maps of Convolutional Neural Networks

Autori: Ntrougkas, Mariano; Gkalelis, Nikolaos; Mezaris, Vasileios
Pubblicato in: Proc. IEEE Int. Symposium on Multimedia (ISM), 2022
Editore: IEEE
DOI: 10.1109/ISM55400.2022.00014

Risultati finali

Pubblicazioni

Condividi questa pagina

Scarica