1 code implementation • 28 Oct 2024 • Manuel Benavent-Lledo, David Mulero-Pérez, David Ortiz-Perez, Jose Garcia-Rodriguez, Antonis Argyros
In this study, we present a novel approach to improve action recognition by exploiting the hierarchical organization of actions and by incorporating contextualized textual information, including location and prior actions to reflect the sequential context.
1 code implementation • 7 Oct 2024 • Nikolaos Vasilikopoulos, Drosakis Drosakis, Antonis Argyros
We present D-PoSE (Depth as an Intermediate Representation for 3D Human Pose and Shape Estimation), a one-stage method that estimates human pose and SMPL-X shape parameters from a single RGB image.
1 code implementation • 11 Sep 2024 • Giorgos Savathrakis, Antonis Argyros
Transformers demonstrate competitive performance in terms of precision on the problem of vision-based object detection.
no code implementations • 21 May 2024 • Victoria Manousaki, Konstantinos Bacharidis, Filippos Gouidis, Konstantinos Papoutsakis, Dimitris Plexousakis, Antonis Argyros
In this work, we introduce (a) the new problem of anticipating object state changes in images and videos during procedural activities, (b) new curated annotation data for object state change classification based on the Ego4D dataset, and (c) the first method for addressing this challenging problem.
no code implementations • 18 Mar 2024 • Filippos Gouidis, Katerina Papantoniou, Konstantinos Papoutsakis, Theodore Patkos, Antonis Argyros, Dimitris Plexousakis
Domain-specific knowledge can significantly contribute to addressing a wide variety of vision tasks.
no code implementations • 22 Jul 2023 • Filipos Gouidis, Theodore Patkos, Antonis Argyros, Dimitris Plexousakis
We investigate the problem of Object State Classification (OSC) as a zero-shot learning problem.
1 code implementation • 29 Apr 2023 • Nikolaos Vasilikopoulos, Nikos Kolotouros, Aggeliki Tsoli, Antonis Argyros
Existing methods ignore the ambiguities of the reconstruction and provide a single deterministic estimate for the 3D pose.
Ranked #58 on
3D Human Pose Estimation
on MPI-INF-3DHP
no code implementations • 12 Sep 2022 • Victoria Manousaki, Konstantinos Papoutsakis, Antonis Argyros
We present a novel approach for the visual prediction of human-object interactions in videos.
1 code implementation • 15 Dec 2021 • Filippos Gouidis, Theodore Patkos, Antonis Argyros, Dimitris Plexousakis
This study enables the setup of a baseline on the performance of SD, as well as its relative performance in comparison to OD, in a variety of scenarios.
1 code implementation • 9 Dec 2021 • Paschalis Panteleris, Antonis Argyros
Vision transformer architectures have been demonstrated to work very effectively for image classification tasks.
Ranked #9 on
Pose Estimation
on MS COCO
1 code implementation • 8 Jul 2021 • Dennis Bautembach, Iason Oikonomidis, Antonis Argyros
It offers higher bandwidth than event-driven plasticity alone and achieves a 1. 5x-2x speedup over our closest competitor.
1 code implementation • 27 Mar 2021 • Sergiu Oprea, Giorgos Karvounas, Pablo Martinez-Gonzalez, Nikolaos Kyriazis, Sergio Orts-Escolano, Iason Oikonomidis, Alberto Garcia-Garcia, Aggeliki Tsoli, Jose Garcia-Rodriguez, Antonis Argyros
Relying on image-to-image translation, we improve the appearance of synthetic hands to approximate the statistical distribution underlying a collection of real images of hands.
no code implementations • 9 Feb 2021 • Dennis Bautembach, Iason Oikonomidis, Antonis Argyros
We present a SNN simulator which scales to millions of neurons, billions of synapses, and 8 GPUs.
no code implementations • 10 Apr 2020 • Sergiu Oprea, Pablo Martinez-Gonzalez, Alberto Garcia-Garcia, John Alejandro Castro-Vargas, Sergio Orts-Escolano, Jose Garcia-Rodriguez, Antonis Argyros
The ability to predict, anticipate and reason about future outcomes is a key component of intelligent decision-making systems.
no code implementations • 26 Dec 2019 • Filippos Gouidis, Alexandros Vassiliades, Theodore Patkos, Antonis Argyros, Nick Bassiliades, Dimitris Plexousakis
Object perception is a fundamental sub-field of Computer Vision, covering a multitude of individual areas and having contributed high-impact results.
1 code implementation • 16 Dec 2019 • Dennis Bautembach, Iason Oikonomidis, Nikolaos Kyriazis, Antonis Argyros
We present a clock-driven Spiking Neural Network simulator which is up to 3x faster than the state of the art while, at the same time, being more general and requiring less programming effort on both the user's and maintainer's side.
no code implementations • 14 Oct 2019 • Giorgos Karvounas, Iason Oikonomidis, Antonis Argyros
On top of this representation, we design, implement and evaluate ReActNet, a lightweight convolutional neural network that classifies a given frame as belonging (or not) to a repetitive video segment.
no code implementations • 19 Dec 2018 • Filippos Gouidis, Paschalis Panteleris, Iason Oikonomidis, Antonis Argyros
We present a novel approach for 2D hand keypoint localization from regular color input.
no code implementations • 6 Dec 2018 • Vassilis C. Nicodemou, Iason Oikonomidis, Georgios Tzimiropoulos, Antonis Argyros
We propose the first approach to the problem of inferring the depth map of a human hand based on a single RGB image.
no code implementations • 25 Oct 2018 • Iason Oikonomidis, Guillermo Garcia-Hernando, Angela Yao, Antonis Argyros, Vincent Lepetit, Tae-Kyun Kim
The fourth instantiation of this workshop attracted significant interest from both academia and the industry.
no code implementations • 30 Apr 2018 • Ammar Qammaz, Sokol Kosta, Nikolaos Kyriazis, Antonis Argyros
This paper presents the case study of a non-intrusive porting of a monolithic C++ library for real-time 3D hand tracking, to the domain of edge-based computation.
no code implementations • 11 Dec 2017 • Paschalis Panteleris, Iason Oikonomidis, Antonis Argyros
We present a method for the real-time estimation of the full 3D pose of one or more human hands using a single commodity RGB camera.
1 code implementation • CVPR 2018 • Shanxin Yuan, Guillermo Garcia-Hernando, Bjorn Stenger, Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee, Pavlo Molchanov, Jan Kautz, Sina Honari, Liuhao Ge, Junsong Yuan, Xinghao Chen, Guijin Wang, Fan Yang, Kai Akiyama, Yang Wu, Qingfu Wan, Meysam Madadi, Sergio Escalera, Shile Li, Dongheui Lee, Iason Oikonomidis, Antonis Argyros, Tae-Kyun Kim
Official Torch7 implementation of "V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map", CVPR 2018
Ranked #5 on
Hand Pose Estimation
on HANDS 2017
no code implementations • 15 May 2017 • Paschalis Panteleris, Antonis Argyros
Unfortunately, this does not work well in practice because the stereo-based, dense 3D reconstruction of hands is far less accurate than the one obtained by RGBD cameras.
no code implementations • CVPR 2014 • Nikolaos Kyriazis, Antonis Argyros
We consider the problem of tracking multiple interacting objects in 3D, using RGBD input and by considering a hypothesize-and-test approach.
no code implementations • CVPR 2013 • Nikolaos Kyriazis, Antonis Argyros
In several hand-object(s) interaction scenarios, the change in the objects' state is a direct consequence of the hand's motion.