Vassilis C. Nicodemou
Vassilis C. Nicodemou

Postdoctoral Researcher

About Me

I am currently a Postdoctoral Researcher in the Human-Centered Computer Vision (HCCV) group, led by Prof. Antonis Argyros, at the Institute of Computer Science, FORTH. I also serve as an Adjunct Lecturer at Hellenic Mediterranean University.

My research interests include artificial neural networks, stress estimation, human pose and body-part estimation, and vision-based human–computer interaction.

Interests
  • Artificial Intelligence
  • Computational Vision
  • Affective Computing
  • Vision-based Human-Computer Interaction
Education
  • Ph.D. in Computer Science

    Computer Science Department, University of Crete

  • M.Sc. in Computer Science and Computer Engineering

    Computer Science Department, University of Crete

  • Computer Science Degree

    Computer Science Department, University of Crete

Research

Combining Facial Videos and Biosignals for Stress Estimation During Driving

Reliable stress recognition is critical in applications such as medical monitoring and safety-critical systems, including real-world driving. While stress is commonly detected using physiological signals such as perinasal perspiration and heart rate, facial activity provides complementary cues that can be captured unobtrusively from video. We propose a multimodal stress estimation framework that combines facial videos and physiological signals, remaining effective even when biosignal acquisition is challenging. Facial behavior is represented using a dense 3D Morphable Model, yielding a 56-dimensional descriptor that captures subtle expression and head-pose dynamics over time. To investigate the correlation between stress and facial motions, we perform extensive experiments involving also physiological markers. Paired hypothesis tests between baseline and stressor phases show that 38 of 56 facial components exhibit consistent, phase-specific stress responses comparable to physiological markers. Building on these findings, we introduce a Transformer-based temporal modeling framework and evaluate unimodal, early-fusion, and cross-modal attention strategies. Combining 3D-derived facial features with physiological signals via cross-modal attention substantially improves performance over physiological signals alone, increasing AUROC from 52.7% and accuracy from 51.0% to 92.0% and 86.7%, respectively. Although evaluated on driving data, the proposed framework and protocol may readily generalize to other stress estimation settings.

Integration of Photogrammetric and Spectral Techniques for Advanced Drone-Based Bathymetry Retrieval Using a Deep Learning Approach

Shallow bathymetry mapping using proximal sensing techniques is an active field of research that offers a new perspective in studying the seafloor. Drone-based imagery with centimeter resolution allows for bathymetry retrieval in unprecedented detail in areas with adequate water transparency. The majority of studies apply either spectral or photogrammetric techniques for deriving bathymetry from remotely sensed imagery. However, spectral methods require a certain amount of ground-truth depth data for model calibration, while photogrammetric methods cannot perform on texture-less seafloor types. The presented approach takes advantage of the interrelation of the two methods, in order to predict bathymetry in a more efficient way. Thus, we combine structure-from-motion (SfM) outputs along with band-ratios of radiometrically corrected drone images within a specially designed deep convolutional neural network (CNN) that outputs a reliable and robust bathymetry estimation. To achieve effective training of our deep learning system, we utilize interpolated uncrewed surface vehicle (USV) sonar measurements. We perform several predictions at three locations in the southern Mediterranean Sea, with varying seafloor types. Our results show low root-mean-square errors over all study areas (average RMSE ≅ 0.3 m), when the method was trained and tested on the same area each time. In addition, we obtain promising cross-validation performance across different study areas (average RMSE ≅ 0.9 m), which demonstrates the potential of our proposed approach in terms of generalization capabilities on unseen data. Furthermore, areas with mixed seafloor types are suitable for building a model that can be applied in similar locations where only drone data is available.

Learning to infer the depth map of a hand from its color image

Experience

  1. Adjunct Lecturer

    Department of Management Science & Technology, Hellenic Mediterranean University
    Teaching the course of Expert Systems
  2. Postdoctoral Researcher

    HCCV Group at ICS - FORTH
    Development of a Computer vision project for measurement and analysis of human-object interaction
  3. Computer systems designer, analyst and programmer

    HCCV Group at ICS - FORTH
    Development and maintenance of computer vision applications in the human motion tracking system (MOCAP)
  4. Additional research staff with a profession in the Research Services in Informatics

    University of Crete
    Evaluation and optimization of optical systems for smart, visual inspection of processes and evaluation of protocols based on visual information, which are used in a work and industrial environment. Contribution to the work unit EE4, aiming at the evaluation and optimization of the optical systems developed by the University of Crete, in the digital platform for dissemination of results, and in the actions for the sustainability of the network of excellence.
  5. Graduate Research Assistant (Ph.D. student position)

    HCCV Group at ICS - FORTH
    • Research and study the domain of Artificial Neural Networks and its applications in order to optimize their performance, by using probabilistic models and representation learning
    • Study, investigate and analyze aspects of human hands, such as depth from color reconstruction and pose estimation with the use of Artificial Neural Networks
    • Contribution to projects of the Computer Vision and Robotics Laboratory: Co4Robots, HealthSign, SignGuide, I.C.Human, ACTYS
  6. Teaching Assistant

    University of Crete
    For the following courses: CS-110 Calculus I, CS-111 Calculus II, CS-118 Discrete Mathematics, CS-150 Programming, CS-225 Computer Organization, CS-240 Data Structures, CS-672 Advanced Topics in Computational Vision.
  7. Graduate Research Assistant (M.Sc. student position)

    HCCV Group at ICS - FORTH
    • Design, implementation and experimental evaluation of methods that focus on 3D hand pose estimation with with the use of Radial Basis Function Networks
    • Contribution to projects of the Computer Vision and Robotics Laboratory: Co4Robots
  8. Undergraduate Research Assistant

    HCCV Group at ICS - FORTH
    • Design and implementation of a virtual touch operated surface, using 3D hand tracking
    • Introduction to research and the field of Computer Vision
Projects

I have participated and contributed in the following projects:

Education

  1. Ph.D. in Computer Science

    Computer Science Department, University of Crete

    During my studies I recieved a scholarship by the Hellenic Foundation for Research and Innovation (HFRI) under the HFRI Ph.D. Fellowship grant (Fellowship Number: 803). The research of this dissertation was also supported by the VMware University Research Fund (VMURF).

    The topic of my dissertation was Multi-Domain Inference and Generative Modeling for Hand Image Synthesis. Supervised by Prof Antonis Argyros.

    Read Thesis
  2. M.Sc. in Computer Science and Computer Engineering

    Computer Science Department, University of Crete

    Specialized on:

    • Cognitive and Computational Vision and Robotics,
    • Algorithms and System Analysis

    Thesis on Single Shot 3D Hand Pose Estimation Using Radial Basis Function Networks Trained on Synthetic Data. Supervised by Prof Antonis Argyros.

    Read Thesis
  3. Computer Science Degree

    Computer Science Department, University of Crete
Contact Info

Feel free to e-mail me.

Address:Institute of Computer Science,
Foundation for Research and Technology - Hellas
N. Plastira 100, Vassilika Vouton, GR-700 13
Heraklion, Crete, Greece
Building:AMI facilities
Office:2.16
Phone:+30 2811 392540