1 code implementation • 1 Apr 2024 • Ioannis Panagiotopoulos, Giorgos Filandrianos, Maria Lymperaiou, Giorgos Stamou
In this paper, we outline our submission for the SemEval-2024 Task 9 competition: 'BRAINTEASER: A Novel Task Defying Common Sense'.
1 code implementation • 1 Apr 2024 • Natalia Grigoriadou, Maria Lymperaiou, Giorgos Filandrianos, Giorgos Stamou
In this paper, we present our team's submissions for SemEval-2024 Task-6 - SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes.
1 code implementation • 13 Mar 2024 • Christos Papadimitriou, Giorgos Filandrianos, Maria Lymperaiou, Giorgos Stamou
Story Visualization (SV) is a challenging generative vision task, that requires both visual quality and consistency between different frames in generated image sequences.
no code implementations • 11 Mar 2024 • Angeliki Dimitriou, Maria Lymperaiou, Giorgos Filandrianos, Konstantinos Thomas, Giorgos Stamou
With a focus on the visual domain, we represent images as scene graphs and obtain their GNN embeddings to bypass solving the NP-hard graph similarity problem for all input pairs, an integral part of the CE computation process.
no code implementations • 17 Feb 2024 • Panagiotis Giadikiaroglou, Maria Lymperaiou, Giorgos Filandrianos, Giorgos Stamou
Exploring the capabilities of Large Language Models (LLMs) in puzzle solving unveils critical insights into their potential and challenges in AI, marking a significant step towards understanding their applicability in complex reasoning tasks.
no code implementations • 21 Jan 2024 • Angeliki Dimitriou, Nikolaos Chaidos, Maria Lymperaiou, Giorgos Stamou
Counterfactuals have been established as a popular explainability technique which leverages a set of minimal edits to alter the prediction of a classifier.
1 code implementation • 21 Oct 2023 • Anastasia Kritharoula, Maria Lymperaiou, Giorgos Stamou
We also study VWSD as a unimodal problem by converting to text-to-text and image-to-image retrieval, as well as question-answering (QA), to fully explore the capabilities of relevant models.
1 code implementation • 3 Oct 2023 • Anastasia Kritharoula, Maria Lymperaiou, Giorgos Stamou
Visual Word Sense Disambiguation (VWSD) is a novel challenging task that lies between linguistic sense disambiguation and fine-grained multimodal retrieval.
no code implementations • 5 Mar 2023 • Theodoti Stoikou, Maria Lymperaiou, Giorgos Stamou
Visual Question Answering (VQA) has been a popular task that combines vision and language, with numerous relevant implementations in literature.
1 code implementation • 4 Mar 2023 • Maria Lymperaiou, Konstantinos Thomas, Giorgos Stamou
Image classification has been one of the most popular tasks in Deep Learning, seeing an abundance of impressive implementations each year.
no code implementations • 4 Mar 2023 • Maria Lymperaiou, Giorgos Stamou
Recent advancements in visiolinguistic (VL) learning have allowed the development of multiple models and techniques that offer several impressive implementations, able to currently resolve a variety of tasks that require the collaboration of vision and language.
no code implementations • 2 Mar 2023 • Maria Lymperaiou, Giorgos Filandrianos, Konstantinos Thomas, Giorgos Stamou
Evaluation of generative models has been an underrepresented field despite the surge of generative architectures.
no code implementations • 9 Jan 2023 • Nikolaos Tsakas, Maria Lymperaiou, Giorgos Filandrianos, Giorgos Stamou
Story Visualization is an advanced task of computed vision that targets sequential image synthesis, where the generated samples need to be realistic, faithful to their conditioning and sequentially consistent.
Ranked #1 on Story Visualization on CLEVR-SV
no code implementations • 19 Nov 2022 • Maria Lymperaiou, Giorgos Stamou
Multimodal learning has been a field of increasing interest, aiming to combine various modalities in a single joint representation.
Conditional Image Generation Factual Visual Question Answering +12
no code implementations • COLING 2022 • Maria Lymperaiou, George Manoliadis, Orfeas Menis Mastromichalakis, Edmund G. Dervakos, Giorgos Stamou
Recent breakthroughs in NLP research, such as the advent of Transformer models have indisputably contributed to major advancements in several tasks.