Reliable Multimodal Semantic Communication for Audio-Visual Event Localization
IEEE Communications Letters · 2026 · 30 · 317-321
DOI: 10.1109/lcomm.2025.3635906 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Communications Letters, 2026. Verfasst von Yuandi Li und 7 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 14 Literaturangaben. Gefördert von: Liaoning Revitalization Talents Program (Postdoctoral Reserve Project), General Program of the Natural Science Foundation of Liaoning Province, National Natural Science Foundation of China, State Administration of Science, Technology and Industry for National Defense, PRC.
Abstract (Originalsprache)
The widespread adoption of smart mobile devices and applications has driven an exponential growth in wireless data traffic, posing significant challenges to modern communication systems. Ensuring reliable task-oriented multimodal semantic communication has become increasingly critical. In this letter, we propose RMMSC, a novel framework designed to enhance the effectiveness and reliability of Audio-Visual Event (AVE) localization-driven multimodal semantic communication. Specifically, RMMSC improves the accuracy of multimodal semantic information through advanced semantic encoding and cross-modal feature integration. It employs a two-level coding scheme that combines error-correcting codes with semantic encoders to enhance the reliability of multimodal semantic transmission. As an optional design choice, RMMSC supports a hybrid encryption mechanism to protect transmitted data if required by the application context. Simulation results validate the effectiveness of RMMSC, demonstrating significant improvements in accuracy and reliability for the AVE task.
Förderung
- Liaoning Revitalization Talents Program (Postdoctoral Reserve Project), General Program of the Natural Science Foundation of Liaoning Province
- National Natural Science Foundation of China
- State Administration of Science, Technology and Industry for National Defense, PRC
- Doctoral Research Start-up Foundation of Liaoning University of Technology
Zitieren
APA
Li, Y., Xiang, Z., Yu, F., Zhang, Z., Wang, Y., Guan, Z., Ji, H., & Wan, Z. (2026). Reliable Multimodal Semantic Communication for Audio-Visual Event Localization. IEEE Communications Letters, 30, 317-321. https://doi.org/10.1109/lcomm.2025.3635906
Vancouver
Li Y, Xiang Z, Yu F, Zhang Z, Wang Y, Guan Z, et al. Reliable Multimodal Semantic Communication for Audio-Visual Event Localization. IEEE Communications Letters. 2026;30:317-321. doi:10.1109/lcomm.2025.3635906
BibTeX
@article{Li2026,
author = {Li, Yuandi and Xiang, Zhe and Yu, Fei and Zhang, Zhuoran and Wang, Yanhao and Guan, Zhangshuang and Ji, Hui and Wan, Zhiguo},
title = {Reliable Multimodal Semantic Communication for Audio-Visual Event Localization},
journal = {IEEE Communications Letters},
year = {2026},
volume = {30},
pages = {317--321},
doi = {10.1109/lcomm.2025.3635906}
}
EUVIMED