EUVIMEDEUVIMED entdecken
Crossref

Signal Enhancement via Multi-view Dynamic Representation and Alignment-aware Fusion

Zikun Jin, Yuhua Qian, Xinyan Liang, Jiaqian Zhang, Jinpeng Yuan, Shen Hu, Haijun Geng, Honghong Cheng

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (27) · 22454-22462

DOI: 10.1609/aaai.v40i27.39404 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zikun Jin und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Robust signal enhancement under non-stationary and low SNR conditions remains challenging, as methods based on the short-time Fourier transform (STFT) with fixed resolution struggle to represent complex and time–frequency structures. While leveraging the fractional domain as an auxiliary view offers flexibility in modeling time-frequency structures, existing methods typically adopt fixed transform orders and overlook alignment between views, hindering effective integration of complementary representations and leaving frequency domain misalignment unresolved. Therefore, we propose FracFusion, a novel framework that integrates a learnable short-time fractional Fourier Transform (STFrFT) module to generate dynamic auxiliary views, combined with two stage alignment-aware fusion modules: Pearson Channel Fusion for correlation-guided consistency and Efficient Align Fusion for fine-grained, frequency aligned interaction. Experiments on speech and electromagnetic (EM) datasets show that FracFusion consistently outperforms state-of-the-art baselines across diverse noise levels and signal types, demonstrating robust adaptability across domains.

Zitieren

APA

Jin, Z., Qian, Y., Liang, X., Zhang, J., Yuan, J., Hu, S., Geng, H., & Cheng, H. (2026). Signal Enhancement via Multi-view Dynamic Representation and Alignment-aware Fusion. Proceedings of the AAAI Conference on Artificial Intelligence, 40(27), 22454-22462. https://doi.org/10.1609/aaai.v40i27.39404

Vancouver

Jin Z, Qian Y, Liang X, Zhang J, Yuan J, Hu S, et al. Signal Enhancement via Multi-view Dynamic Representation and Alignment-aware Fusion. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(27):22454-22462. doi:10.1609/aaai.v40i27.39404

BibTeX
@article{Jin2026,
  author = {Jin, Zikun and Qian, Yuhua and Liang, Xinyan and Zhang, Jiaqian and Yuan, Jinpeng and Hu, Shen and Geng, Haijun and Cheng, Honghong},
  title = {Signal Enhancement via Multi-view Dynamic Representation and Alignment-aware Fusion},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {27},
  pages = {22454--22462},
  doi = {10.1609/aaai.v40i27.39404}
}
Kostenlos starten →