SWA-SOP shows that sliding-window attention with per-slot spatial embeddings and a center query improves semantic occupancy prediction on LiDAR and camera inputs, but the headline benchmark numbers are second-best rather than state-of-the-art.
A medical image segmentation model with auto-dynamic convolution and location attention mecha- nism,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SWA-SOP: Spatially-aware Window Attention for Semantic Occupancy Prediction in Autonomous Driving
SWA-SOP shows that sliding-window attention with per-slot spatial embeddings and a center query improves semantic occupancy prediction on LiDAR and camera inputs, but the headline benchmark numbers are second-best rather than state-of-the-art.