EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Resource-Efficient Gesture Recognition through Convexified Attention EICS006

Daniel Schwartz, Dario Salvucci, Yusuf Osmanlioglu, Richard Vallett, Genevieve Dion, Ali Shokoufandeh

Proceedings of the ACM on Human-Computer Interaction · 30.06.2026 · 10 (4) · 1-25

DOI: 10.1145/3815369 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Human-Computer Interaction, online erschienen am 29.06.2026. Verfasst von Daniel Schwartz und 5 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wearable e-textile interfaces require gesture recognition capabilities but face severe constraints in power consumption, computational capacity, and form factor that make traditional deep learning impractical. While lightweight architectures like MobileNet improve efficiency, they still demand thousands of parameters, limiting deployment on textile-integrated platforms. We introduce a convexified attention mechanism for wearable applications that dynamically weights features while preserving convexity through nonexpansive simplex projection and convex loss functions. Unlike conventional attention mechanisms using non-convex softmax operations, our approach employs Euclidean projection onto the probability simplex combined with multi-class hinge loss, ensuring global convergence guarantees. Implemented on a textile-based capacitive sensor with four connection points, our approach achieves 100.00% accuracy on tap gestures and 100.00% on swipe gestures—consistent across 10-fold cross-validation and held-out test evaluation—while requiring only 120–360 parameters, a 97% reduction compared to conventional approaches. With sub-millisecond inference times (290–296 μ s) and minimal storage requirements (< 7KB), our method enables gesture interfaces directly within e-textiles without external processing. Our evaluation, conducted in controlled laboratory conditions with a single-user dataset, demonstrates feasibility for basic gesture interactions. Real-world deployment would require validation across multiple users, environmental conditions, and more complex gesture vocabularies. These results demonstrate how convex optimization can enable efficient on-device machine learning for textile interfaces.

Zitieren

APA

Schwartz, D., Salvucci, D., Osmanlioglu, Y., Vallett, R., Dion, G., & Shokoufandeh, A. (2026). Resource-Efficient Gesture Recognition through Convexified Attention EICS006. Proceedings of the ACM on Human-Computer Interaction, 10(4), 1-25. https://doi.org/10.1145/3815369

Vancouver

Schwartz D, Salvucci D, Osmanlioglu Y, Vallett R, Dion G, Shokoufandeh A. Resource-Efficient Gesture Recognition through Convexified Attention EICS006. Proceedings of the ACM on Human-Computer Interaction. 2026;10(4):1-25. doi:10.1145/3815369

BibTeX
@article{Schwartz2026,
  author = {Schwartz, Daniel and Salvucci, Dario and Osmanlioglu, Yusuf and Vallett, Richard and Dion, Genevieve and Shokoufandeh, Ali},
  title = {Resource-Efficient Gesture Recognition through Convexified Attention EICS006},
  journal = {Proceedings of the ACM on Human-Computer Interaction},
  year = {2026},
  volume = {10},
  number = {4},
  pages = {1--25},
  doi = {10.1145/3815369}
}
Kostenlos starten →