Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Oct 25, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.4K

Anomaly Detection in Videos Using Two-Stream Autoencoder with Post Hoc Interpretability.

Jiangfan Feng1, Yukun Liang1, Lin Li2

  • 1Chongqing University of Posts and Telecommunications, School of Computer Science and Technology, Chongqing, China.

Computational Intelligence and Neuroscience
|August 6, 2021
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Learning Rich Feature Representation and State Change Monitoring for Accurate Animal Target Tracking.

Animals : an open access journal from MDPI·2024
Same author

Multiobject Tracking of Wildlife in Videos Using Few-Shot Learning.

Animals : an open access journal from MDPI·2022
Same author

A Multibranch Object Detection Method for Traffic Scenes.

Computational intelligence and neuroscience·2019
Same author

Bag of Visual Words Model with Deep Spatial Features for Geographical Scene Classification.

Computational intelligence and neuroscience·2017
Same author

Association of homocysteine, asymmetric dimethylarginine, and nitric oxide with preeclampsia.

Archives of gynecology and obstetrics·2009
Same author

[Measurement of fine-structure branching ratios for Rb-He optical collisions].

Guang pu xue yu guang pu fen xi = Guang pu·2009
Same journal

RETRACTION: Real-Time Modulation of Physical Training Intensity Based on Wavelet Recursive Fuzzy Neural Networks.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Multidimensional Heterogeneous Network Link Adaptation Based on Mobile Environment.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Framework to Segment and Evaluate Multiple Sclerosis Lesion in MRI Slices Using VGG-UNet.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Facial Emotion Recognition Using a Novel Fusion of Convolutional Neural Network and Local Binary Pattern in Crime Investigation.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Automatic Intelligent System Using Medical of Things for Multiple Sclerosis Detection.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Intangible Cultural Heritage Reproduction and Revitalization: Value Feedback, Practice, and Exploration Based on the IPA Model.

Computational intelligence and neuroscience·2026
See all related articles

This study introduces a novel two-stream deep learning approach for efficient anomaly detection in surveillance videos. The method accurately identifies unusual events and provides object-level explanations for its decisions.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Machine Learning

Background:

  • Deep learning for video surveillance faces challenges in accuracy and efficiency.
  • Detecting abnormal events in real-time surveillance is a complex problem.

Purpose of the Study:

  • To develop a fast and efficient anomaly detection method for surveillance video.
  • To enable anomaly detection without requiring labeled abnormal event data.
  • To provide interpretable insights into the model's decision-making process.

Main Methods:

  • A two-stream autoencoder-based architecture was employed for anomaly detection.
  • Post hoc interpretability using feature map visualization was implemented.
  • The method was tested on benchmark datasets: Avenue, UCSD Ped2, and Subway.

More Related Videos

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.2K

Related Experiment Videos

Last Updated: Oct 25, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.4K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.2K

Main Results:

  • The proposed method demonstrated effective detection of abnormal events.
  • The approach successfully explained the model's internal logic at the object level.
  • Interpretability revealed decision boundaries within the video sequences.

Conclusions:

  • The developed autoencoder-based two-stream approach offers a promising solution for efficient and interpretable anomaly detection in surveillance.
  • Object-level explanations enhance the understanding and trustworthiness of deep learning models in security applications.
  • This method addresses the need for reliable abnormal event detection in unlabeled surveillance data.