Olivier Pons
Olivier Pons has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Caroline Huron
Inserm U1284, France; Learning Planet Institute, Research Unit Learning Transitions (UR LT, joint unit with CY Cergy Paris University), F-75004, Paris, France
4 shared publications - Isabelle Barbet
Conservatoire National des Arts et Métiers
3 shared publications - Jérôme Dupire
Conservatoire National des Arts et Métiers
2 shared publications - Ayoub Frihaoui
Cedrid CNAM
1 shared publication - Camille Guinaudeau
Université Paris-Saclay, CNRS, LISN
1 shared publication - Céline Hudelot
CentraleSupelec - Université Paris-Saclay
1 shared publication
Latest Publications
- 26 June 2026
- Published by Springer Nature
- p. 185-199
Constraint-Aware Data Collection and Observational Analysis of Digital Labor Platforms
- 26 June 2026
- Published by Springer Nature
- p. 185-199
Constraint-Aware Data Collection and Observational Analysis of Digital Labor Platforms
- 26 June 2026
- Published by Springer Nature
- p. 234-248
Hybrid Vision-Language Extraction for Inclusive and Accessible Educational Content
- 26 June 2026
- Published by Springer Nature
- p. 234-248
Hybrid Vision-Language Extraction for Inclusive and Accessible Educational Content
- 26 June 2026
- Published by Springer Nature
- p. 122-136
A Modular System for VR-Based Upper-limb Rehabilitation: Adaptive Visual Feedback and Structured Kinematic Data Pipeline
- 26 June 2026
- Published by Springer Nature
- p. 122-136
A Modular System for VR-Based Upper-limb Rehabilitation: Adaptive Visual Feedback and Structured Kinematic Data Pipeline
- 19 December 2025
- Published by Taylor & Francis in European Journal of Special Needs Education
- Vol. 41 (5) , 1-14
Disability and competence: insights from French teachers
- 19 December 2025
- Published by Taylor & Francis in European Journal of Special Needs Education
- Vol. 41 (5) , 1-14
Disability and competence: insights from French teachers
- 1 September 2025
- Published by Springer Nature
- p. 397-405
Modeling Transcription Task of Educational Documents for Visually Impaired Students
- 1 September 2025
- Published by Springer Nature
- p. 397-405
Modeling Transcription Task of Educational Documents for Visually Impaired Students
- Open Access
- 20 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 71-78
Noisy and Unbalanced Multimodal Document Classification: Textbook Exercises as a Use Case
In order to foster inclusive education, automatic systems that can adapt textbooks to make them accessible to children with Developmental Coordination Disorder (DCD) are necessary. In this context, we propose a task to classify exercises according to their DCD adaptation type. We introduce a challenging exercise dataset extracted from French textbooks, with two major difficulties: limited and unbalanced, noisy data. To set a baseline on the dataset, we use state-of-the-art models combined through early and late fusion techniques to take advantage of text and vision/layout modalities. Our approach achieves an overall accuracy of 0.802. However, the experiments show the difficulty of the task, especially for minority classes, where the accuracy drops to 0.583.
- 20 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 71-78
Open AccessNoisy and Unbalanced Multimodal Document Classification: Textbook Exercises as a Use Case
In order to foster inclusive education, automatic systems that can adapt textbooks to make them accessible to children with Developmental Coordination Disorder (DCD) are necessary. In this context, we propose a task to classify exercises according to their DCD adaptation type. We introduce a challenging exercise dataset extracted from French textbooks, with two major difficulties: limited and unbalanced, noisy data. To set a baseline on the dataset, we use state-of-the-art models combined through early and late fusion techniques to take advantage of text and vision/layout modalities. Our approach achieves an overall accuracy of 0.802. However, the experiments show the difficulty of the task, especially for minority classes, where the accuracy drops to 0.583.