Tamás Karácsony

Ph.D. Candidate affiliated with INESC-TEC, FEUP PDEEC, CMU RI.

prof_pic.jpg

I am a Ph.D. candidate in the Carnegie Mellon Portugal affiliated Ph.D. (CMU Portugal) program in the Doctoral Program in Electrical and Computer Engineering (PDEEC), at the Department of Electrical and Computer Engineering of the Faculty of Engineering of the University of Porto (FEUP), Portugal, and a researcher at INESC-TEC: Institute for Systems and Computer Engineering, in the Center for Biomedical Engineering Research (C-BER) in the Biomedical Research And INnovation (BRAIN) research group.

My PhD thesis “Explainable Deep Learning Based Epileptic Seizure Classification with Clinical 3D Motion Capture” is supervised by Prof. João Paulo Cunha and co-supervised by Prof. Fernando De la Torre. I am a visiting research scholar at the Computational Behavior (CUBE) Lab collaborating with Prof. László A. Jeni, and at the Human Sensing Laboratory (HSL) working with Prof. Fernando De la Torre at The Robotics Institute (RI), Carnegie Mellon University (CMU).

My research focuses on Advanced Human Sensing, 3D Motion Capture, Action and Pattern Recognition, Computer Vision, and Neuroengineering.

Selected publications

2025

  1. blanketgen2.jpg
    BlanketGen2-Fit3D: Synthetic Blanket Augmentation Towards Improving Real-World In-Bed Blanket Occluded Human Pose Estimation
    Tamás Karácsony, João Carmona, and João Paulo Silva Cunha
    arXiv preprint arXiv:2501.12318, Jan 2025

2024

  1. imavis2024.png
    Deep learning methods for single camera based clinical in-bed movement action recognition
    Tamás Karácsony, László Attila Jeni, Fernando Torre, and João Paulo Silva Cunha
    Image and Vision Computing, Mar 2024
  2. embc2024.jpg
    NeuroKinect4K: A Novel 4K RGB-D-IR Video System with 3D Scene Reconstruction for Enhanced Epileptic Seizure Semiology Monitoring
    Tamás Karácsony, Nicholas Fearns, Christian Vollmar, Denise Birk, Jan Rémi, Soheyl Noachtar, and João Paulo Silva Cunha
    In 2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jul 2024

2023

  1. blanketgen_compressed.gif
    BlanketGen - A Synthetic Blanket Occlusion Augmentation Pipeline for Motion Capture Datasets
    João Carmona, Tamás Karácsony, and João Paulo Silva Cunha
    In 2023 IEEE 7th Portuguese Meeting on Bioengineering (ENBENG), Jul 2023
  2. blanketset.jpg
    BlanketSet - A Clinical Real-World In-Bed Action Recognition and Qualitative Semi-Synchronised Motion Capture Dataset
    João Carmona, Tamás Karácsony, and João Paulo Silva Cunha
    In 2023 IEEE 7th Portuguese Meeting on Bioengineering (ENBENG), Jul 2023

2022

  1. natscirep.png
    Novel 3D video action recognition deep learning approach for near real time epileptic seizure classification
    Tamás Karácsony, Anna Mira Loesch-Biffar, Christian Vollmar, Jan Rémi, Soheyl Noachtar, and João Paulo Silva Cunha
    Scientific Reports, Nov 2022

2021

  1. bhi2021.png
    DeepEpil: Towards an Epileptologist-Friendly AI Enabled Seizure Classification Cloud System based on Deep Learning Analysis of 3D videos
    Tamás Karácsony, Anna Mira Loesch-Biffar, Christian Vollmar, Soheyl Noachtar, and João Paulo Silva Cunha
    In 2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), Nov 2021

2020

  1. icassp2020.png
    A Deep Learning Architecture for Epileptic Seizure Classification Based on Object and Action Recognition
    Tamás Karácsony, Anna Mira Loesch-Biffar, Christian Vollmar, Soheyl Noachtar, and João Paulo Silva Cunha
    In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Nov 2020

2019

  1. BCI_VR.png
    Brain Computer Interface for Neuro-Rehabilitation With Deep Learning Classification and Virtual Reality Feedback
    Tamás Karácsony, John Paulin Hansen, Helle Klingenberg Iversen, and Sadasivan Puthusserypady
    In Proceedings of the 10th Augmented Human International Conference 2019, Nov 2019

Talks and posters

Jun 16, 2023 “In-bed action recognition for clinical diagnosis support: A two-stage, 3D motion capture and skeleton action recognition based approach” DCE23 Best Paper award; Abstract
Mar 26, 2023 “Explainable Deep Learning Based Epileptic Seizure Classification with Clinical 3D Motion Capture” CMU Portugal: PhD Research Presentation During Visit of Minister Elvira Fortunato, Pittsburgh, CMU
Nov 10, 2022 “Explainable Epileptic Seizure Classification: A 2-stage Pipeline” CMU Portugal summit, Lisbon; Poster
May 16, 2022 “3D Motion capture technologies for clinical patient monitoring – a short summary” Ciência 2022, Encontro com a Ciência e Tecnologia em Portugal, Lisbon; Poster
Jan 24, 2020 “An Epileptologist-Friendly Cloud-Based Remote 3Dvideo-EEG Processing Environment For Quantifed Semiology Analysis” Juntos Pelo Fernando Conference, Lisbon