activity
20092025
most citedFusing Body Posture with Facial Expressions for Joint Recognition of Affect in Child-Robot Interaction

82 citations · 356 across the 60 of their papers we have counts for

collaborators

66 papers

cs.CV2025

GHR-VQA: Graph-guided Hierarchical Relational Reasoning for Video Question Answering

Dionysia Danai Brilli, Dimitrios Mallis, Vassilis Pitsikalis +1

We propose GHR-VQA, Graph-guided Hierarchical Relational Reasoning for Video Question Answering (Video QA), a novel human-centric framework that incorporates scene graphs to captur…

cs.SD2025

A Machine Learning Approach for MIDI to Guitar Tablature Conversion

Maximos Kaliakatsos-Papakostas, Gregoris Bastas, Dimos Makris +3

Guitar tablature transcription consists in deducing the string and the fret number on which each note should be played to reproduce the actual musical part. This assignment should…

cs.LG2025

Diffusion-Based Scenario Tree Generation for Multivariate Time Series Prediction and Multistage Stochastic Optimization

Stelios Zarifis, Ioannis Kordonis, Petros Maragos

Stochastic forecasting is critical for efficient decision-making in uncertain systems, such as energy markets and finance, where estimating the full distribution of future scenario…

cs.CV2025

Multi-task Learning For Joint Action and Gesture Recognition

Konstantinos Spathis, Nikolaos Kardaris, Petros Maragos

In practical applications, computer vision tasks often need to be addressed simultaneously. Multitask learning typically achieves this by jointly training a single deep neural netw…

cs.LG2025

Diffusion-Based Forecasting for Uncertainty-Aware Model Predictive Control

Stelios Zarifis, Ioannis Kordonis, Petros Maragos

We propose Diffusion-Informed Model Predictive Control (D-I MPC), a generic framework for uncertainty-aware prediction and decision-making in partially observable stochastic system…

cs.CV2024

Mushroom Segmentation and 3D Pose Estimation from Point Clouds using Fully Convolutional Geometric Features and Implicit Pose Encoding

George Retsinas, Niki Efthymiou, Petros Maragos

Modern agricultural applications rely more and more on deep learning solutions. However, training well-performing deep networks requires a large amount of annotated data that may n…