Abnormal event detection in crowded scenes using sparse representation

By Yang Cong, Junsong Yuan, Ji Liu. Pattern Recognition, 2013

318 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Crowded Scene Analysis: A Survey (2015, methodology): “Anomaly detection is a key aspect of the crowded scene analysis, which has attracted much attention [11]–[13], [22], [60], [61], [80]–[84].”
Active Lifelong Learning With "Watchdog" (2018, background): “Motivated by (Cong, Yuan, and Liu 2011; 2013), whether wt+1 is unknown or not is determined by the linear reconstruction cost, defined as: S(wt+1) = 1 2 ‖wt+1 −Dr∗‖22 , s.t. : ‖r∗‖0 ≤ μ1, (7) where r∗ is the optimal sparse coding coefficients, μ ≥ 0 controls the sparsity of r∗, and S(wt+1) can…”
Anomaly Detection in Video via Self-Supervised and Multi-Task Learning (2020, background): “While the early works [1, 2, 6, 25, 29, 32, 33, 46, 58] on video anomaly detection relied heavily on handcrafted appearance and motion features, the recent literature is abundant in deep learning methods [9, 10, 14, 16, 17, 27, 31, 38, 40, 41, 44, 47, 54, 59, 60].”