ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
会议论文

Comprehensive Regularization in a Bi-directional Predictive Network for Video Anomaly Detection

Chen, Chengwei; Xie, Yuan*; Lin, Shaohui; Yao, Angela; Jiang, Guannan; Zhang, Wei; Qu, Yanyun; Qiao, Ruizhi; Ren, Bo; Ma, Lizhuang*厦门大学; y
36th AAAI Conference on Artificial Intelligence / 34th Conference on Innovative Applications of Artificial Intelligence / 12th Symposium on Educational Advances in Artificial Intelligence2022
6被引6阅读
引用收藏
分享

摘要

Video anomaly detection aims to automatically identify unusual objects or behaviours by learning from normal videos. Previous methods tend to use simplistic reconstruction or prediction constraints, which leads to the insufficiency of learned representations for normal data. As such, we propose a novel bi-directional architecture with three consistency constraints to comprehensively regularize the prediction task from pixel-wise, cross-modal, and temporal-sequence levels. First, predictive consistency is proposed to consider the symmetry property of motion and appearance in forwards and backwards time, which ensures the highly realistic appearance and motion predictions at the pixel-wise level. Second, association consistency considers the relevance between different modalities and uses one modality to regularize the prediction of another one. Finally, temporal consistency utilizes the relationship of the video sequence and ensures that the predictive network generates temporally consistent frames. During inference, the pattern of abnormal frames is unpredictable and will therefore cause higher prediction errors. Experiments show that our method outperforms advanced anomaly detectors and achieves state-of-the-art results on UCSD Ped2, CUHK Avenue, and ShanghaiTech datasets.

相关
加载中…
  • Anomaly Detection With Bidirectional Consistency in Videos
    Fang, Zhiwen; Liang, Jiafei; Zhou, Joey Tianyi*; Xiao, Yang; Yang, FengIEEE Transactions on Neural Networks and Learning Systems, 2022, 33(3): 1079-1092.被引 17
  • Multi-Encoder Towards Effective Anomaly Detection in Videos
    Fang, Zhiwen; Zhou, Joey Tianyi*; Xiao, Yang; Li, Yanan; Yang, FengIEEE TRANSACTIONS ON MULTIMEDIA, 2021, 23: 4106-4116.被引 18
  • A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction
    Liu, Zhian; Nie, Yongwei*; Long, Chengjiang; Zhang, Qing; Li, Guiqing18th IEEE/CVF International Conference on Computer Vision (ICCV), ELECTR NETWORK, 2021-10-11 To 2021-10-17.被引 66
查看全部 →

会议信息

会议名称
36th AAAI Conference on Artificial Intelligence / 34th Conference on Innovative Applications of Artificial Intelligence / 12th Symposium on Educational Advances in Artificial Intelligence
会议日期
2022-02-22 至 2022
论文集名
THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE
发表日期
2022
起止页码
230-238
资助标注
National Natural Science Foundation of China [61972157, 62176092, 61876161, 61902129, 62102151, 72192821]; Natural Science Foundation of Shanghai [20ZR1417700]; National Key Research and Development Program of China [2019YFC1521104, 2020AAA0108301]; Shanghai Municipal Commission of Economy and Information [XXRGZN01-19-6348]; Shanghai Science and Technology Commission [21511100700]; Shanghai Jiao Tong University, Shanghai Sailing Program [21YF1411200]; Shanghai Municipal Science and Technology Major Project [2021SHZDZX0102]; Zhejiang Lab [2020NB0AB01]
收录
ISTP

作者

  • C

    Chen, Chengwei (第一作者)

  • X

    Xie, Yuan (通讯)

查看全部 10 位作者收起作者
  • L

    Lin, Shaohui

  • Y

    Yao, Angela

  • J

    Jiang, Guannan

  • Z

    Zhang, Wei

  • Q

    Qu, Yanyun

    xiamen univ

  • Q

    Qiao, Ruizhi

    tencent

  • R

    Ren, Bo

    tencent

  • M

    Ma, Lizhuang (通讯)

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417