Metraipolis › archive › dc_f3c0fc79a5bf

Fairness-Aware Multimodal Transformer Modeling for Real-Time Student Attention Estimation — arXiv:2609.02232

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02232
License (as archived)
CC0-1.0
Archived
2026-10-17T04:26:16.212Z
SHA-256 of the archived text
9a22466cf726d83696799089416f6061ddd838791471945c4ba02cb0cace708b
Stable URL of this page
https://metraipolis.com/documento/dc_f3c0fc79a5bf

How to cite

Fairness-Aware Multimodal Transformer Modeling for Real-Time Student Attention Estimation — arXiv:2609.02232 — arXiv (en), https://arxiv.org/abs/2609.02232 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f3c0fc79a5bf (Metraipolis archive dc_f3c0fc79a5bf, sha256 9a22466cf726d83696799089416f6061ddd838791471945c4ba02cb0cace708b)
BibTeX
@misc{dcf3c0fc79a5bf,
  title = {Fairness-Aware Multimodal Transformer Modeling for Real-Time Student Attention Estimation — arXiv:2609.02232},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02232},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f3c0fc79a5bf; sha256 9a22466cf726d83696799089416f6061ddd838791471945c4ba02cb0cace708b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02232. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Automated student-attention estimation can support learning analytics, but aggregate predictive metrics can conceal demographic disparities. This study evaluates fairness-aware multimodal temporal models on DIPSER, a naturalistic classroom dataset combining facial images, wearable-sensor measurements, attention annotations, and automatically inferred demographic metadata. Three baselines are compared across 10 training seeds: a Visual GRU, a Sensor GRU, and a Residual Fusion Transformer. The multimodal model achieves the best mean test performance (MAE 0.283, RMSE 0.363) and the lowest worst-group error among the evaluated baselines, although its gain over the Visual GRU is modest. Gender- and age-targeted MAE-gap regularization reduces disparities on validation data, but these gains do not consistently transfer to held-out subjects or repeated subject-level splits. On an NVIDIA A100-SXM4-40GB GPU, the warm end-to-end pipeline averages 50.65 ms per prediction window at a one-second stride, while the temporal model itself requires 1.02 ms. The findings show that multimodal fusion can modestly improve prediction and worst-group performance, but validation-level fairness gains should not be assumed to generalize. Robust fairness assessment therefore requires subgroup-aware evaluation, repeated subject-level validation, and larger, better balanced demographic samples.

Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-09-03 in cs.CY).
Categorie arXiv: Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2609.02232 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T04:04:04.796Z dalla pagina https://arxiv.org/catchup/cs.CY/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).