EUVIMEDEUVIMED entdecken
Crossref

Light but Sharp: SlimSTAD for Real-Time Action Detection from Sensor Data

Wei Cui, Lukai Fan, Zhenghua Chen, Min Wu, Shili Xiang, Haixia Wang, Bing Li

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (1) · 156-165

DOI: 10.1609/aaai.v40i1.36975 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Wei Cui und 6 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sensory Temporal Action Detection (STAD) aims to localize and classify human actions within long, untrimmed sequences captured by non-visual sensors such as WiFi or inertial measurement units (IMUs). Unlike video-based TAD, STAD poses unique challenges due to the low-dimensional, noisy, and heterogeneous nature of sensory data, as well as the real-time and resource constraints on edge devices. While recent STAD models have improved detection performance, their high computational cost hampers practical deployment. In this paper, we propose SlimSTAD, a simple yet effective framework that achieves both high accuracy and low latency for STAD. SlimSTAD features a novel Decoupled Channel Modeling (DCM) encoder, which preserves modality-specific temporal features and enables efficient inter-channel aggregation via lightweight graph attention. An anchor-free cascade predictor then refines action boundaries and class predictions in a two-stage design without dense proposals. Experiments on two real-world datasets demonstrate that SlimSTAD outperforms strong video-derived and sensory baselines by an average of 2.1 mAP, while significantly reducing GFLOPs, parameters, and latency, validating its effectiveness for real-world, edge-aware STAD deployment.

Zitieren

APA

Cui, W., Fan, L., Chen, Z., Wu, M., Xiang, S., Wang, H., & Li, B. (2026). Light but Sharp: SlimSTAD for Real-Time Action Detection from Sensor Data. Proceedings of the AAAI Conference on Artificial Intelligence, 40(1), 156-165. https://doi.org/10.1609/aaai.v40i1.36975

Vancouver

Cui W, Fan L, Chen Z, Wu M, Xiang S, Wang H, et al. Light but Sharp: SlimSTAD for Real-Time Action Detection from Sensor Data. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(1):156-165. doi:10.1609/aaai.v40i1.36975

BibTeX
@article{Cui2026,
  author = {Cui, Wei and Fan, Lukai and Chen, Zhenghua and Wu, Min and Xiang, Shili and Wang, Haixia and Li, Bing},
  title = {Light but Sharp: SlimSTAD for Real-Time Action Detection from Sensor Data},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {1},
  pages = {156--165},
  doi = {10.1609/aaai.v40i1.36975}
}
Kostenlos starten →