JACoP is a new framework using an anchor-based profiler and MRF aligner to produce multi-agent trajectory predictions with optimal scene-level compliance by minimizing joint social and environmental costs.
Fend: A future enhanced distribution-aware contrastive learning framework for long-tail trajectory prediction
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
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
JACoP: Joint Alignment for Compliant Multi-Agent Prediction
JACoP is a new framework using an anchor-based profiler and MRF aligner to produce multi-agent trajectory predictions with optimal scene-level compliance by minimizing joint social and environmental costs.