Multi-timescale pose prediction, trained with supervision at intermediate layers, detects both short-term and long-term human anomalies and outperforms prior pose-based detectors on HR-ShanghaiTech and HR-Avenue.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multi-timescale Trajectory Prediction for Abnormal Human Activity Detection
Multi-timescale pose prediction, trained with supervision at intermediate layers, detects both short-term and long-term human anomalies and outperforms prior pose-based detectors on HR-ShanghaiTech and HR-Avenue.