FP-ANet uses fixed-point theory and dual-attention to achieve better channel estimation accuracy than prior methods in hybrid-field THz UM-MIMO while keeping similar computational cost.
F is fed through a shared multi-layer perceptron (MLP) to generate a channel attention map Fc ∈R 1×1×C
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
-
FP-ANeT: A Fixed-Point Attention Network for Hybrid-Field THz Ultra-massive MIMO Channel Estimation
FP-ANet uses fixed-point theory and dual-attention to achieve better channel estimation accuracy than prior methods in hybrid-field THz UM-MIMO while keeping similar computational cost.