Alina Glushkova

Research Scientist

Email address: alina.glushkova@minesparis.ps.eu
Discipline(s): Computer Science, Education Sciences, Human Movement Sciences, Physical Activities and Sport, Philosophy, Digital Humanities, Signal, Image, Automatic Control, Robotics and Industrial Engineering
Topic(s): AI Impact, Biomechanics, Robotics

Keywords

Team

CAOR

Biography

Alina Glushkova is a researcher specializing in the analysis and modeling of human movement, with particular expertise in the fields of human-computer interaction, gesture recognition, and ergonomics as applied to workplace environments. Her work focuses on the use of advanced machine learning methods, such as *Multi-Task Learning* (MTL) and *Meta Learning*, to improve the generalization of human action recognition models, particularly in industrial or rehabilitation contexts. She also explores hybrid approaches combining stochastic and biomechanical models, such as the *Gesture Operational Model* (GOM), to capture the dynamics of work-related movements and extract explainable representations from them. Her research includes the development of digital tools, such as *PosePilot*, a web application dedicated to the visualization and analysis of real-time motion data, as well as interactive platforms for the transmission of artisanal know-how or the prevention of work-related musculoskeletal disorders. His methodological approach systematically integrates on-site data collection, semantic annotation, and quantitative evaluation, aiming to produce adaptable, end-user-centered solutions for researchers, industry professionals, and learners alike.

Publication(s)

2026
Meta and Multi-Task Learning for Action Recognition: A Survey DOI : 10.1109/ACCESS.2026.3665252
2026
From Motion Analysis to Motion Learning: Interface Mediation for Embodied and Vocational Skill Training DOI : hal-05621251
2026
PosePilot-V3D: Interactive Exploration and Analysis of 3D Human Motion from Monocular Video DOI : 10.1109/FG67764.2026.11556994
2026
PosePilot-V3D: A web-based framework for 3D hierarchical skeleton reconstruction from monocular video DOI : 10.1109/FG67764.2026.11556941
2026
Toward a Cross-Domain Taxonomy of Motion Quality Metrics DOI : 10.1109/FG67764.2026.11556523
2026
Cross-Modal Retrieval-Augmented Generation for Craft Gestures Learning: Enabling Dialogue with Multimodal Pedagogical Contents DOI : 10.1145/3802842.3802892
2026
PosePilot-GOM: A Web-based application for dexterity analysis of human movement DOI : 10.1145/3802842.3802905
2025
PosePilot - A Web-Based Application for Human Motion Data Analysis and Visualization DOI : 10.1109/FG61629.2025.11099475
2025
Multi-Task Learning for Hierarchical Professional Gesture Recognition: State-Space Modeling for Task Temporal Dependencies DOI : 10.1109/FG61629.2025.11099170
2025
VIBE: An Open-Source Platform for Benchmarking Vision Models for Gesture-Based Interaction DOI : hal-05312001
2025
Multi-step Forecasting contact Wrenches for Proactive Control in Human-Robot Collaboration DOI : hal-05507640
2025
Multi-step Forecasting Contact Wrenches and Motion Synergies for Proactive Control in Human Robot Collaboration DOI : hal-05507702
2025
Dynamic Modelling of Human Movements for Reactive Control of a Robotic arm DOI : hal-05002769
2025
Working with AI in Cultural and Creative Industries. DOI : hal-05016368
2024
Explainable AI in human motion: A comprehensive approach to analysis, modeling, and generation DOI : 10.1016/j.patcog.2024.110418
2024
Interactive Visualization and Dexterity Analysis of Human Movement: AIMove Platform DOI : 10.1109/FG59268.2024.10581928
2023
Improving Human-Robot Collaboration in TV Assembly Through Computational Ergonomics: Effective Task Delegation and Robot Adaptation DOI : 10.1109/SMC53992.2023.10394021
2023
Embodied edutainment experience in a museum: discovering glass-blowing gestures DOI : 10.1145/3610661.3616180
2023
Motion Capture Benchmark of Real Industrial Tasks and Traditional Crafts for Human Movement Analysis DOI : 10.1109/ACCESS.2023.3269581
2023
Interactive Sensorimotor Guidance for Learning Motor Skills of a Glass Blower DOI : 10.1007/978-3-031-34732-0_3
2022
Traditional Craft Training and Demonstration in Museums DOI : 10.3390/heritage5010025
2022
Mixed-Reality Demonstration and Training of Glassblowing DOI : 10.3390/heritage5010006
2022
A Representation Protocol for Traditional Crafts DOI : 10.3390/heritage5020040
2022
Multimodal Narratives for the Presentation of Silk Heritage in the Museum DOI : 10.3390/heritage5010027
2021
Stochastic-biomechanic modeling and recognition of human movement primitives, in industry, using wearables DOI : 10.3390/s21072497
2020
Analyzing the kinematic and kinetic contributions of the human upper body’s joints for ergonomics assessment DOI : 10.1007/s12652-020-01926-y
2020
Human Movement Representation on Multivariate Time Series for Recognition of Professional Gestures and Forecasting Their Trajectories DOI : 10.3389/frobt.2020.00080
2020
Hidden Markov Modelling and Recognition of Euler-Based Motion Patterns for Automatically Detecting Risks Factors from the European Assembly Worksheet DOI : 10.1109/ICIP40778.2020.9190756
2019
Designing a web-based Automatic Ergonomic Assessment using Motion Data DOI : 10.1145/3316782.3322758
2019
Extracting the Inertia Properties of the Human Upper Body Using Computer Vision DOI : 10.1007/978-3-030-34995-0_54
2019
Towards a Professional Gesture Recognition with RGB-D from Smartphone DOI : 10.1007/978-3-030-34995-0_22
2018
Gesture recognition and sensorimotor learning-by-doing of motor skills in manual professions: A case study in the wheel-throwing art of pottery DOI : 10.1111/jcal.12210
2016
3D-scene modelling of professional gestures when interacting with moving, deformable and revolving objects DOI : 10.1145/2948910.2948949
2016
Fingers gestures early-recognition with a unified framework for RGB or depth camera DOI : 10.1145/2948910.2948947
2015
Novel 3D game-like applications driven by body interactions for learning specific forms of intangible cultural heritage DOI : 10.5220/0005456606510660
2015
Gesture recognition technologies for gestural know-how management: Preservation and transmission of expert gestures in wheel throwing pottery DOI : 10.5220/0005475904050410
2015
A hybrid content-learning management system for education and access to intangible cultural heritage DOI : 10.5220/0005409302020207
2015
Modelling Gestural Know-how in Pottery Based on State-space Estimation and System Dynamic Simulation DOI : 10.1016/j.promfg.2015.07.883
2014
Capture, modeling, and recognition of expert technical gestures in wheel-throwing art of pottery DOI : 10.1145/2627729
Integrating a hierarchical structure of situated human motion in Multi-task learning for professional gesture recognition DOI : hal-04585865
Deep state-space modeling for explainable representation, analysis, and generation of professional human poses

Projects

2013-2017 I-treasures Participant
2018-2022 MINGEI Participant
2018-2022 Collaborate Partner
2022-2026 CRAEFT Participant
2023-2029 ReSource Scientific Director

Teaching

Collaborative Robotics

Lecturer

The main objective of this course is to provide the basic knowledge needed to address the following topics: new applications of gesture recognition in artistic processes (creation, sensorimotor experiments, etc.) and industrial processes (ergonomics, collaborative robotics, etc.). the capture of human movement using sensors and the modeling of a specific gesture using statistical learning computer-assisted interaction in emerging artistic and industrial applications (gesture-based composition, gesture-based sound systems, sensorimotor learning of professional gestures, etc.) The course introduces various technological methods and paradigms related to human motion capture and appropriate sensors, as well as machine learning and deep learning methods and models for recognizing patterns of human behavior and their artistic and industrial applications

PhD supervision

2024 Dynamic neural rendering through egocentric robotic vision SU Sichen
2024 The impact of human factors on motor performance indicators: analysis and visual representation ZENG Linghao
2024 AI-based interaction mechanism for augmented sensorimotor return strategies SICHLER Romaric
2023 Multimodal gesture recognition for reactive collaborative robotics in the luxury industry PAPANAGIOTOU Dimitrios
2022 Exploration of multi-task learning and meta-learning for simultaneous and hierarchical recognition of activities, actions, and professional intentions SENTERI Gavriela
2019 Modélisation profonde espace-état pour la représentation explicable, l'analyse et la prédiction des dynamiques du corps humain dans la compréhension de la dextérité et l'ergonomie computationnelle Brenda Olivas