A dual-branch transformer framework that combines time-domain and DCT frequency representations with multi-scale patch embeddings achieves state-of-the-art trajectory prediction on ETH-UCY, SDD, NBA, and JRDB.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PatchTraj: Unified Time-Frequency Representation Learning via Dynamic Patches for Trajectory Prediction
A dual-branch transformer framework that combines time-domain and DCT frequency representations with multi-scale patch embeddings achieves state-of-the-art trajectory prediction on ETH-UCY, SDD, NBA, and JRDB.