SynHAT uses a novel two-stage spatio-temporal diffusion framework with Latent Spatio-Temporal U-Net to synthesize realistic human activity traces, outperforming baselines by 52% on spatial and 33% on temporal metrics across four cities.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Re-identification analysis of the YJMob100K anonymized trajectories shows that ad hoc sanitization leaves substantial spatio-temporal leakage, with small numbers of anchors or sensitive locations often sufficient for unique user identification.
citing papers explorer
-
SynHAT: A Two-stage Coarse-to-Fine Diffusion Framework for Synthesizing Human Activity Traces
SynHAT uses a novel two-stage spatio-temporal diffusion framework with Latent Spatio-Temporal U-Net to synthesize realistic human activity traces, outperforming baselines by 52% on spatial and 33% on temporal metrics across four cities.
-
How Tough Is Location Anonymization? Re-identifying 100K Real-User Trajectories in Japan
Re-identification analysis of the YJMob100K anonymized trajectories shows that ad hoc sanitization leaves substantial spatio-temporal leakage, with small numbers of anchors or sensitive locations often sufficient for unique user identification.