Saved in:
Bibliographic Details
Main Authors: Zhao, Xiaotong, Cui, Yuanhao, Yuan, Weijie, Jia, Ziye, Liu, Heng, Xing, Chengwen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.02563
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914177414594560
author Zhao, Xiaotong
Cui, Yuanhao
Yuan, Weijie
Jia, Ziye
Liu, Heng
Xing, Chengwen
author_facet Zhao, Xiaotong
Cui, Yuanhao
Yuan, Weijie
Jia, Ziye
Liu, Heng
Xing, Chengwen
contents Accurate beam prediction is essential for maintaining reliable links and high spectral efficiency in dynamic low-altitude wireless networks. However, existing approaches often fail to capture the deep correlations across heterogeneous sensing modalities, limiting their adaptability in complex three-dimensional environments. To overcome these challenges, we propose a multi-modal predictive beamforming method based on a cross-attention fusion mechanism that jointly leverages visual and structured sensor data. The proposed model utilizes a Convolutional Neural Network (CNN) to learn multi-scale spatial feature hierarchies from visual images and a Transformer encoder to capture cross-dimensional dependencies within sensor data. Then, a cross-attention fusion module is introduced to integrate complementary information between the two modalities, generating a unified and discriminative representation for accurate beam prediction. Through experimental evaluations conducted on a real-world dataset, our method reaches 79.7% Top-1 accuracy and 99.3% Top-3 accuracy, surpassing the 3D ResNet-Transformer baseline by 4.4%-23.2% across Top-1 to Top-5 metrics. These results verify that multi-modal cross-attention fusion is effective for intelligent beam selection in dynamic low-altitude wireless networks.
format Preprint
id arxiv_https___arxiv_org_abs_2512_02563
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Predictive Beamforming in Low-Altitude Wireless Networks: A Cross-Attention Approach
Zhao, Xiaotong
Cui, Yuanhao
Yuan, Weijie
Jia, Ziye
Liu, Heng
Xing, Chengwen
Signal Processing
Accurate beam prediction is essential for maintaining reliable links and high spectral efficiency in dynamic low-altitude wireless networks. However, existing approaches often fail to capture the deep correlations across heterogeneous sensing modalities, limiting their adaptability in complex three-dimensional environments. To overcome these challenges, we propose a multi-modal predictive beamforming method based on a cross-attention fusion mechanism that jointly leverages visual and structured sensor data. The proposed model utilizes a Convolutional Neural Network (CNN) to learn multi-scale spatial feature hierarchies from visual images and a Transformer encoder to capture cross-dimensional dependencies within sensor data. Then, a cross-attention fusion module is introduced to integrate complementary information between the two modalities, generating a unified and discriminative representation for accurate beam prediction. Through experimental evaluations conducted on a real-world dataset, our method reaches 79.7% Top-1 accuracy and 99.3% Top-3 accuracy, surpassing the 3D ResNet-Transformer baseline by 4.4%-23.2% across Top-1 to Top-5 metrics. These results verify that multi-modal cross-attention fusion is effective for intelligent beam selection in dynamic low-altitude wireless networks.
title Predictive Beamforming in Low-Altitude Wireless Networks: A Cross-Attention Approach
topic Signal Processing
url https://arxiv.org/abs/2512.02563