User profiles for Nikolaos Athanasiou

Nikos Athanasiou

- Verified email at tuebingen.mpg.de - Cited by 1376

Nikolaos Athanasiou

- Verified email at med.uoa.gr - Cited by 339

Vibe: Video inference for human body pose and shape estimation

M Kocabas, N Athanasiou… - Proceedings of the IEEE …, 2020 - openaccess.thecvf.com
Human motion is fundamental to understanding behavior. Despite progress on single-image
3D pose and shape estimation, existing video-based state-of-the-art methods fail to …

[HTML][HTML] From recession to depression? Prevalence and correlates of depression, anxiety, traumatic stress and burnout in healthcare workers during the COVID-19 …

S Pappa, N Athanasiou, N Sakkas, S Patrinos… - International journal of …, 2021 - mdpi.com
The COVID-19 pandemic has the potential to adversely affect the mental health of healthcare
workers (HCWs). The public healthcare system in Greece was already facing serious …

Ntua-slp at semeval-2018 task 1: Predicting affective content in tweets with deep attentive rnns and transfer learning

C Baziotis, N Athanasiou, A Chronopoulou… - arXiv preprint arXiv …, 2018 - arxiv.org
In this paper we present deep-learning models that submitted to the SemEval-2018 Task~1
competition: "Affect in Tweets". We participated in all subtasks for English tweets. We …

BABEL: Bodies, action and behavior with english labels

…, A Chandrasekaran, N Athanasiou… - Proceedings of the …, 2021 - openaccess.thecvf.com
Understanding the semantics of human movement--the what, how and why of the movement--is
an important problem that requires datasets of human actions with semantic labels. …

Learning to regress bodies from images using differentiable semantic rendering

SK Dwivedi, N Athanasiou… - Proceedings of the …, 2021 - openaccess.thecvf.com
Learning to regress 3D human body shape and pose (eg SMPL parameters) from
monocular images typically exploits losses on 2D keypoints, silhouettes, and/or part-segmentation …

Teach: Temporal action composition for 3d humans

N Athanasiou, M Petrovich, MJ Black… - … Conference on 3D …, 2022 - ieeexplore.ieee.org
Given a series of natural language descriptions, our task is to generate 3D human motions
that correspond semantically to the text, and follow the temporal order of the instructions. In …

[HTML][HTML] Depression, insomnia and post-traumatic stress disorder in COVID-19 survivors: role of gender and impact on quality of life

S Pappa, Z Barmparessou, N Athanasiou… - Journal of Personalized …, 2022 - mdpi.com
Evidence to date suggests that a significant proportion of COVID-19 patients experience
adverse psychological outcomes and neuropsychiatric complications. The aim of this study was …

Ntua-slp at semeval-2018 task 3: Tracking ironic tweets using ensembles of word and character level attentive rnns

C Baziotis, N Athanasiou, P Papalampidi… - arXiv preprint arXiv …, 2018 - arxiv.org
In this paper we present two deep-learning systems that competed at SemEval-2018 Task 3
"Irony detection in English tweets". We design and ensemble two independent models, …

SINC: Spatial composition of 3D human motions for simultaneous action generation

N Athanasiou, M Petrovich… - Proceedings of the …, 2023 - openaccess.thecvf.com
Our goal is to synthesize 3D human motions given textual inputs describing simultaneous
actions, for examplewaving hand'whilewalking'at the same time. We refer to generating such …

[HTML][HTML] Glycemia, beta-cell function and sensitivity to insulin in mildly to critically ill covid-19 patients

…, M Pratikaki, E Botoula, E Jahaj, N Athanasiou… - Medicina, 2021 - mdpi.com
Background and objectives: Critically and non-critically ill patients with SARS-CoV-2
infection (Covid-19) may present with higher-than-expected glycemia, even in the absence of …