计算机科学
背景(考古学)
异常检测
人工智能
水准点(测量)
特征(语言学)
计算机视觉
帧(网络)
模棱两可
对象(语法)
光流
目标检测
利用
异常(物理)
模式识别(心理学)
图像(数学)
古生物学
哲学
物理
生物
程序设计语言
地理
电信
语言学
计算机安全
凝聚态物理
大地测量学
作者
Wenhao Zhou,Yingxuan Li,Chunhui Zhao
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2022-07-18
卷期号:: 1-6
被引量:20
标识
DOI:10.1109/icme52920.2022.9859927
摘要
Video anomaly detection is challenging due to the lack of abnormal videos and ambiguity of anomaly definition. Context information is important to identify anomalous events and can be reflected from the salient objects and related background. In this paper, we propose a new multi-level attention network consisting of an Object-Guided Attention Module (OGAM) and a Motion-Refined Attention Module (MRAM) to fully exploit context by leveraging both frame-level and object-level semantics. Specifically, OGAM highlights features of salient objects on frame features for future frame prediction. MRAM further leverages global positions and optical flow of objects to improve the prediction loss. By multi-level attention, objects are highlighted in the predicted frame and necessary context information is preserved at both feature level and pixel level to identify anomalies. Experiments demonstrate our method achieves state-of-the-art performance on benchmark datasets including Avenue, UCSD Ped2 and ShanghaiTech, specifically obtaining a frame-level AUC of 92.6% on Avenue.
科研通智能强力驱动
Strongly Powered by AbleSci AI