no code implementations • 29 Apr 2024 • Zacharias Chrysidis, Stefanos-Iordanis Papadopoulos, Symeon Papadopoulos, Panagiotis C. Petrantonakis
EVVER-Net can be used to filter evidence collected from the Web, thus enhancing the robustness of end-to-end AFC systems.
1 code implementation • 16 Nov 2023 • Stefanos-Iordanis Papadopoulos, Christos Koutlis, Symeon Papadopoulos, Panagiotis C. Petrantonakis
Online misinformation is often multimodal in nature, i. e., it is caused by misleading associations between texts and accompanying images.
2 code implementations • 27 Apr 2023 • Stefanos-Iordanis Papadopoulos, Christos Koutlis, Symeon Papadopoulos, Panagiotis C. Petrantonakis
Multimedia content has become ubiquitous on social media platforms, leading to the rise of multimodal misinformation (MM) and the urgent need for effective strategies to detect and prevent its spread.
1 code implementation • 2 Mar 2023 • Stefanos-Iordanis Papadopoulos, Christos Koutlis, Symeon Papadopoulos, Panagiotis C. Petrantonakis
To address this, we perform a comparative study on existing and new Synthetic Misinformers that involves (1) out-of-context (OOC) image-caption pairs, (2) cross-modal named entity inconsistency (NEI) as well as (3) hybrid approaches and we evaluate them against real-world misinformation; using the COSMOS benchmark.
no code implementations • 14 Dec 2022 • Stefanos-Iordanis Papadopoulos, Christos Koutlis, Anastasios Papazoglou-Chalikias, Symeon Papadopoulos, Spiros Nikolopoulos
To this end, we develop a computer vision pipeline fine tuned on fashion imagery in order to extract relevant visual features along with the category and attributes of the garment.
1 code implementation • 27 Jul 2022 • Stefanos-Iordanis Papadopoulos, Christos Koutlis, Symeon Papadopoulos, Ioannis Kompatsiaris
For fashion outfits to be considered aesthetically pleasing, the garments that constitute them need to be compatible in terms of visual aspects, such as style, category and color.