scispace - formally typeset
A

Antonis A. Argyros

Researcher at University of Crete

Publications -  227
Citations -  8061

Antonis A. Argyros is an academic researcher from University of Crete. The author has contributed to research in topics: Pose & Video tracking. The author has an hindex of 37, co-authored 215 publications receiving 7134 citations. Previous affiliations of Antonis A. Argyros include Foundation for Research & Technology – Hellas & University of Bonn.

Papers
More filters
Journal ArticleDOI

FaceGuard: A Wearable System To Avoid Face Touching

TL;DR: In this article, a 1D-CNN based prediction model was developed and trained with data from 4,800 trials recorded from 40 participants, with a prediction accuracy of more than 92% with less than 550 ms of IMU data.
Journal ArticleDOI

A Framework for Online Segmentation and Classification of Modeled Actions Performed in the Context of Unmodeled Ones

TL;DR: Extensive quantitative results obtained demonstrate that the proposed approach is of comparable accuracy with the state-of-the-art approaches for online stream segmentation and classification when all performed actions are known, and performs considerably better in the presence of unmodeled actions.
Proceedings ArticleDOI

A HIMI model for collaborative multi-touch multimedia education

TL;DR: A Human-Intention-Machine-Interpretation (HIMI) model is proposed, which applies a graph-based approach to recognize hand gestures and interpret user intentions and facilitates natural interactions using hand movements on simple tasks, but also supports complex collaborative operations.
Book ChapterDOI

Macedonia from fragments to pixels: a permanent exhibition of interactive systems at the archaeological museum of thessaloniki

TL;DR: The theme of this paper is an exhibition of prototypical interactive systems with subjects drawn from ancient Macedonia, named "Macedonia from fragments to pixels", which comprises 7 interactive systems based on some research outcomes of the Ambient Intelligence Programme.
Proceedings ArticleDOI

Fast trifocal tensor estimation using virtual parallax

TL;DR: The proposed method represents projective space through a "plane + parallax" decomposition and employs a novel technique for estimating the homographies induced by a virtual 3D plane between successive image pairs.