George Retsinas — accepted AI-conference papers

2026

Registration-Free Learnable Multi-View Capture of Faces in Dense Semantic Correspondence

Panagiotis P. Filntisis, George Retsinas, Radek Danecek, Vanessa Sklyarova, Petros Maragos, Timo Bolkart

CVPR 2026

Recent frameworks like ToFu and TEMPEH provide an automated alternative to classical registration pipelines by predicting 3D meshes in dense semantic correspondence directly from calibrated multi-view images. However, these learning-based methods rely on the slow, manual registration pipelines they

Cited by 0 Source ↗code ↗Scholar ↗

2025

Category-Level 6D Object Pose Estimation in Agricultural Settings Using a Lattice-Deformation Framework and Diffusion-Augmented Synthetic Data

Marios Glytsos, Panagiotis Paraskevas Filntisis, George Retsinas, Petros Maragos

IROS 2025

Accurate 6D object pose estimation is essential for robotic grasping and manipulation, particularly in agriculture, where fruits and vegetables exhibit high intra-class variability in shape, size, and texture. The vast majority of existing methods rely on instance-specific CAD models or require dept

Cited by 1 Source ↗code ↗Scholar ↗

2025

Instance-Level Composed Image Retrieval

Bill Psomas, George Retsinas, Nikos Efthymiadis, Panagiotis Filntisis, Yannis Avrithis, Petros Maragos +2

NeurIPS 2025poster

The progress of composed image retrieval (CIR), a popular research direction in image retrieval, where a combined visual and textual query is used, is held back by the absence of high-quality training and evaluation data. We introduce a new evaluation dataset, i-CIR, which, unlike existing datasets,…

Cited by 0 Source ↗Scholar ↗

2025

Proactive Tactile Exploration for Object-Agnostic Shape Reconstruction from Minimal Visual Priors

Paris Oikonomou, George Retsinas, Petros Maragos, Costas S. Tzafestas

ICRA 2025

The perception of an object's surface is important for robotic applications enabling robust object manipulation. The level of accuracy in such a representation affects the outcome of the action planning, especially during tasks that require physical contact, e.g. grasping. In this paper, we propose

Cited by 2 Source ↗Scholar ↗

2025

Towards Open-Ended Robotic Exploration Using Vision-Inspired Similarity and Foundation Models

Panagiotis Paraskevas Filntisis, Efthymios Tsaprazlis, Paraskevas Oikonomou, Francesco Mattioli, Vieri Giuliano Santucci, George Retsinas +1

ICRA 2025

In the domain of robotics, achieving Lifelong Open-ended Learning Autonomy (LOLA) represents a significant milestone, especially in contexts where autonomous agents must adapt to unforeseen environmental variations and evolving objectives. This paper introduces VISOR (VisionSimilarity for Open-ended

Cited by 0 Source ↗Scholar ↗

2024

3D Facial Expressions through Analysis-by-Neural-Synthesis

George Retsinas, Panagiotis P. Filntisis, Radek Danecek, Victoria F. Abrevaya, Anastasios Roussos, Timo Bolkart +1

CVPR 2024poster

While existing methods for 3D face reconstruction from in-the-wild images excel at recovering the overall face shape they commonly miss subtle extreme asymmetric or rarely observed expressions. We improve upon these methods with SMIRK (Spatial Modeling for Image-based Reconstruction of Kinesics) whi…

Cited by 23 Source ↗PDF ↗code ↗Scholar ↗

2024

Augmenting Transformer Autoencoders with Phenotype Classification for Robust Detection of Psychotic Relapses

Niki Efthymiou, George Retsinas, Panagiotis Paraskevas Filntisis, Petros Maragos

ICASSP 2024accepted

Recently, deep autoencoder architectures have received attention for the problem of unsupervised anomaly detection. Detecting psychotic relapses in mental health patients is a crucial challenge, often framed as anomaly detection, given the limited availability of data during relapsing states. In thi…

Cited by 0 Source ↗Scholar ↗

2024

DiffusionPen: Towards Controlling the Style of Handwritten Text Generation

Konstantina Nikolaidou*, George Retsinas, Giorgos Sfikas, Marcus Liwicki

ECCV 2024poster

"Handwritten Text Generation (HTG) conditioned on text and style is a challenging task due to the variability of inter-user characteristics and the unlimited combinations of characters that form new words unseen during training. Diffusion Models have recently shown promising results in HTG but still…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2024

Matrix Factorization in Tropical and Mixed Tropical-Linear Algebras

Ioannis Kordonis, Emmanouil Theodosis, George Retsinas, Petros Maragos

ICASSP 2024accepted

Matrix Factorization (MF) has found numerous applications in Machine Learning and Data Mining, including collaborative filtering recommendation systems, dimensionality reduction, data visualization, and community detection. Motivated by the recent successes of tropical algebra and geometry in machin…

Cited by 0 Source ↗Scholar ↗

2023

E-Prevention: The ICASSP-2023 Challenge on Person Identification and Relapse Detection from Continuous Recordings of Biosignals

Athanasia Zlatintsi, Panagiotis Paraskevas Filntisis, Niki Efthymiou, Christos Garoufis, George Retsinas, Thomas Sounapoglou +4

ICASSP 2023accepted

The e-Prevention challenge concerns the analysis and processing of long-term continuous recordings of biosignals recorded from wearable sensors, i.e., accelerometers, gyroscopes and heart rate monitors embedded in smartwatches, as well as sleep information and daily step count, in order to extract h…

Cited by 0 Source ↗Scholar ↗

2023

Newton-Based Trainable Learning Rate

George Retsinas, Giorgos Sfikas, Panagiotis Paraskevas Filntisis, Petros Maragos

ICASSP 2023accepted

Selecting an appropriate learning rate for efficiently training deep neural networks is a difficult process that can be affected by numerous parameters, such as the dataset, the model architecture or even the batch size. In this work, we propose an algorithm for automatically adjusting the learning…

Cited by 0 Source ↗Scholar ↗

2022

Neural Network Approximation based on Hausdorff distance of Tropical Zonotopes

Panagiotis Misiakos, Georgios Smyrnis, George Retsinas, Petros Maragos

ICLR 2022poster

In this work we theoretically contribute to neural network approximation by providing a novel tropical geometrical viewpoint to structured neural network compression. In particular, we show that the approximation error between two neural networks with ReLU activations and one hidden layer depends on…

Cited by 10 Source ↗PDF ↗Scholar ↗

2020

Maxpolynomial Division with Application To Neural Network Simplification

Georgios Smyrnis, Petros Maragos, George Retsinas

ICASSP 2020accepted

In this work, we further the link between neural networks with piecewise linear activations and tropical algebra. To that end, we introduce the process of Maxpolynomial Division, a geometric method which simulates division of polynomials in the max-plus semiring, while highlighting its key propertie…

Cited by 0 Source ↗Scholar ↗

2020

Person Identification Using Deep Convolutional Neural Networks on Short-Term Signals from Wearable Sensors

George Retsinas, Panayiotis Paraskevas Filntisis, Niki Efthymiou, Emmanouil Theodosis, Athanasia Zlatintsi, Petros Maragos

ICASSP 2020accepted

In this work, we explore the discriminating ability of short-term signal patterns (e.g. few minutes long) with respect to the person identification task. We focus on signals recorded by simple wearable devices, such as smart watches, which can measure movements (accelerometer and gyroscope sensors)…

Cited by 0 Source ↗Scholar ↗

2019

An Alternative Deep Feature Approach to Line Level Keyword Spotting

George Retsinas, Georgios Louloudis, Nikolaos Stamatopoulos, Giorgos Sfikas, Basilis Gatos

CVPR 2019poster

Keyword spotting (KWS) is defined as the problem of detecting all instances of a given word, provided by the user either as a query word image (Query-by-Example, QbE) or a query word string (Query-by-String, QbS) in a body of digitized documents. Keyword detection is t…

Cited by 15 PDF ↗Scholar ↗