A hybrid MLP, multi-scale CNN, and cross-attention model reduces trajectory prediction error by a few percent over ModernTCN on the GeoLife dataset, with the largest gain on the 15-second sampling interval data.
Improving next location recommendation services with spatial-temporal multi-group contrastive learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
User Trajectory Prediction Unifying Global and Local Temporal Information
A hybrid MLP, multi-scale CNN, and cross-attention model reduces trajectory prediction error by a few percent over ModernTCN on the GeoLife dataset, with the largest gain on the 15-second sampling interval data.