Metraipolis › archive › dc_dfdfe714dd6f

Self-Supervised Pretraining for Label-Efficient Facial Expression Recognition using Smart Glasses — arXiv:2611.05711

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.05711
License (as archived): CC0-1.0
Archived: 2026-11-05T18:16:44.886Z
SHA-256 of the archived text: 15a47f950be1cc9b58b17f298848f5d719df54e892c83755b420e68c68a46803
Stable URL of this page: https://metraipolis.com/documento/dc_dfdfe714dd6f

How to cite

Self-Supervised Pretraining for Label-Efficient Facial Expression Recognition using Smart Glasses — arXiv:2611.05711 — arXiv (en), https://arxiv.org/abs/2611.05711 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dfdfe714dd6f (Metraipolis archive dc_dfdfe714dd6f, sha256 15a47f950be1cc9b58b17f298848f5d719df54e892c83755b420e68c68a46803)

BibTeX

@misc{dcdfdfe714dd6f,
  title = {Self-Supervised Pretraining for Label-Efficient Facial Expression Recognition using Smart Glasses — arXiv:2611.05711},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05711},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dfdfe714dd6f; sha256 15a47f950be1cc9b58b17f298848f5d719df54e892c83755b420e68c68a46803},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05711. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Facial Expression Recognition (FER) on optomyographic (OMG) smart glasses such as OCOsense enables privacy-preserving, camera-free affect sensing for health and well-being. Most FER systems are fully supervised, i.e., they rely either on hand-crafted expert features with classical machine learning, or on end-to-end deep models trained from labelled data. Both depend on large quantities of labelled expressions, which are costly to collect and limit deployment in real-world, personalized settings. We investigate Self-Supervised Learning (SSL) as a route to label-efficient FER on these glasses. We pretrain a Vision Transformer with a masked-autoencoder objective on unlabelled OCOsense recordings and finetune it for five-class FER under person-independent cross-validation. Across label budgets from 5% to 100%, pretraining consistently improves performance; with only 5% of the labels, the pretrained model outperforms the from-scratch model trained with all labels. Our results show that SSL pretraining is a practical way to reduce labelling cost for smart eyewear FER, and we discuss the implications for future personalization and continual adaptation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.05711 — 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 2026-11-05T18:12:48.998Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).