Open access
2026
FASTe: Framework With Application-Driven Spatio-Temporal Efficiency for Video Anomaly Detection
FASTe introduces a LogSumExp-based multiple instance learning (MIL) aggregation strategy for robust training on variable-length inputs, and introduces frame-level anomaly localization under weak supervision, without requiring dense labels.
Jihun Jeon, Raeyoung Chang, Jisu Kim et al.
· IEEE Access · 0 citations