Chen, Yang, Lee, Ickjai, Lu, Zhigang, Shen, Xiaoqin, Cheng, Ziyang, and Zhou, Junhui (2025) Spatial Neighborhood-Enhanced Framework for Efficient Loss and Regularization in Skeleton-Based Anomaly Detection. In: Proceedings of the IEEE International Conference on Big Data. pp. 4865-4873. From: BigData 2025: IEEE International Conference on Big Data, 8-11 December 2025, Macau, China.

PDF (Published Version) - Published Version Restricted to Repository staff only

Abstract

Skeleton-based video anomaly detection has emerged as a privacy-preserving alternative to appearance-based surveillance, yet existing methods face a fundamental trade-off: they either converge slowly in structured environments or overfit rapidly in complex ones. We present Spatial Neighborhood-Enhanced Loss (SNE), a lightweight auxiliary objective that resolves this dilemma by exploiting a simple spatial prior - nearby individuals tend to move similarly. SNE adapts its role to scene characteristics: in structured datasets (Avenue, STC), it accelerates convergence by 20.8-86.2% while improving accuracy (+0.85-3.30% AUC); in complex datasets (UBnormal), it acts as a regularizer that prevents catastrophic overfitting through a novel three-phase learning dynamic. Cross-domain experiments confirm SNE's robustness, maintaining 92.9% performance retention and achieving a +2.43% average improvement across diverse deployment scenarios.

Actions (Repository Staff Only)

Item Control Page