The BEV-Fusion framework unifies multi-modal sensor inputs in bird's-eye-view space with cross-attention and temporal transformers to achieve approximately 87% distance-based accuracy for sequential beam prediction in mmWave systems on DeepSense 6G scenarios 32-34, outperforming TransFuser.
EfficientNet: Rethinking model scaling for convolu- tional neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A BEV-Fusion Based Framework for Sequential Multi-Modal Beam Prediction in mmWave Systems
The BEV-Fusion framework unifies multi-modal sensor inputs in bird's-eye-view space with cross-attention and temporal transformers to achieve approximately 87% distance-based accuracy for sequential beam prediction in mmWave systems on DeepSense 6G scenarios 32-34, outperforming TransFuser.