SocialMOIF combines multi-order attention fusion, a VAE-style trajectory distribution approximator, and a KAN-based global optimizer to achieve reported state-of-the-art ADE/FDE on ETH/UCY, NBA, SDD, and NuScenes.
Pedestrian trajec- tory prediction in heterogeneous traffic using pose keypoints- based convolutional encoder-decoder network
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
-
SocialMOIF: Multi-Order Intention Fusion for Pedestrian Trajectory Prediction
SocialMOIF combines multi-order attention fusion, a VAE-style trajectory distribution approximator, and a KAN-based global optimizer to achieve reported state-of-the-art ADE/FDE on ETH/UCY, NBA, SDD, and NuScenes.