DIPSER multimodal classroom dataset for in-person student engagement and attention recognition¶
Product or Programme · All products and programmes
Evidence · 3 claims (3 for) · 1 study (1 design),q2· 0 of 1 report an effect size · 3 claims rest on one study
Description¶
A multimodal classroom dataset created by Christoforos Fragkiadakis et al. containing synchronized video and smartwatch sensor recordings with attention, emotion, and demographic annotations for modeling student engagement in real educational activities.
Components¶
Claims¶
- Facial visual dynamics provide the most informative cues for attention estimation: the Visual GRU outperforms both the train-mean baseline and the Sensor GRU [+W]
- The Residual Fusion Transformer shows the lowest worst-group MAE and smallest gender gap among baselines, while the Sensor GRU shows the smallest age gap alongside the weakest overall performance [+W]
- Densely sampled visual frames and sensor representations offered no reliable predictive advantage over the 1 FPS setting in the higher-frequency experiment [+W]
Related Products and Programmes¶
Key Sources¶
- Christoforos Fragkiadakis, Seyed Sahand Mohammadi Ziabari, and Ali Mohammed Mansoor Alsahag. (2026). Fairness-Aware Multimodal Transformer Modeling for Real-Time Student Attention Estimation. https://arxiv.org/abs/2609.02232
Page metadata
| Field | Value |
|---|---|
type |
product |
id |
dipser-multimodal-classroom-dataset-for-in-person-student-engagement-and-attention-recogni |
title |
DIPSER multimodal classroom dataset for in-person student engagement and attention recognition |
description |
A multimodal classroom dataset created by Christoforos Fragkiadakis et al. |
status |
review |
product_kind |
dataset |
generated |
by process:settle-candidates on 2026-10-11 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.