An attention-based pose encoder improves trajectory prediction across LSTM, GAN, MLP, and Transformer models on several datasets, though a capacity confound weakens the attribution.
Yves V on Cramon, and Ricarda Schubotz
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
-
Social-Pose: Enhancing Trajectory Prediction with Human Body Pose
An attention-based pose encoder improves trajectory prediction across LSTM, GAN, MLP, and Transformer models on several datasets, though a capacity confound weakens the attribution.