EUVIMEDEUVIMED entdecken
Crossref

Latent Space Consistency Learning for Few-Shot Individual Gesture Recognition With Millimeter-Wave Radar

Yu Tian, Qin Chen, Yaoxi Chen, Yiming Pi, Zongjie Cao

IEEE Internet of Things Journal · 01.07.2026 · 13 (13) · 29776-29791

DOI: 10.1109/jiot.2026.3687630 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Internet of Things Journal, erschienen am 01.07.2026. Verfasst von Yu Tian und 4 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Sichuan Science and Technology Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Millimeter-wave (mmWave) radar has attracted increasing research interest for contactless gesture recognition. However, in practical deployment, models trained on existing users often exhibit significant performance degradation when applied to unseen users. This decline arises because each user constitutes a distinct domain with unique behavioral patterns and physiological characteristics, leading to severe cross-domain distribution shifts in radar signal features. To address these challenges, we propose a two-stage few-shot gesture recognition adaptation method. During pretraining, a dual-prototype consistency strategy is proposed to explicitly align user-specific subdistributions within each gesture class, overcoming the limitation of conventional methods that treat multiple source users as a single monolithic domain and thereby enhancing the model’s transferability to unseen users. In the adaptation stage, we perform source-free and lightweight fine-tuning using only a few labeled samples from the target domain while avoiding the computational burden and privacy concerns of joint training. Specifically, a variational autoencoder (VAE)-based latent space regularization with z-space alignment is employed to achieve stable and accurate recognition for the new target domain. Furthermore, knowledge distillation (KD) and L2 regularization toward the starting point (L2-SP) are incorporated to mitigate overfitting and prevent catastrophic forgetting of the source gesture knowledge. Experiments on a multisubject mmWave gesture dataset show that the proposed method significantly improves recognition performance for the target domains and maintains high accuracy on the original users. Visualization analyses further confirm effective latent space semantic alignment with minimal supervision.

Förderung

  • National Natural Science Foundation of China
  • Sichuan Science and Technology Program

Zitieren

APA

Tian, Y., Chen, Q., Chen, Y., Pi, Y., & Cao, Z. (2026). Latent Space Consistency Learning for Few-Shot Individual Gesture Recognition With Millimeter-Wave Radar. IEEE Internet of Things Journal, 13(13), 29776-29791. https://doi.org/10.1109/jiot.2026.3687630

Vancouver

Tian Y, Chen Q, Chen Y, Pi Y, Cao Z. Latent Space Consistency Learning for Few-Shot Individual Gesture Recognition With Millimeter-Wave Radar. IEEE Internet of Things Journal. 2026;13(13):29776-29791. doi:10.1109/jiot.2026.3687630

BibTeX
@article{Tian2026,
  author = {Tian, Yu and Chen, Qin and Chen, Yaoxi and Pi, Yiming and Cao, Zongjie},
  title = {Latent Space Consistency Learning for Few-Shot Individual Gesture Recognition With Millimeter-Wave Radar},
  journal = {IEEE Internet of Things Journal},
  year = {2026},
  volume = {13},
  number = {13},
  pages = {29776--29791},
  doi = {10.1109/jiot.2026.3687630}
}
Kostenlos starten →