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 Concept Videos

Observational Learning01:12

Observational Learning

1.5K
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
1.5K
Steps in Outbreak Investigation01:18

Steps in Outbreak Investigation

779
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
779

You might also read

Related Articles

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

Sort by
Same author

Epigenetic regulation of post-stroke cognitive impairment by gut microbiota and their metabolites.

Frontiers in cellular and infection microbiologyยท2026
Same author

Engineered zwitterion-nanodelivery for precision targeting of brain metastases.

Nature communicationsยท2026
Same author

Mutant superoxide dismutase 1-catalyzed hydrogen therapy for amyotrophic lateral sclerosis achieved by intercepting oxidative stress-neuroinflammation crosstalk.

Acta biomaterialiaยท2026
Same author

A UV-vis-fluorescence-smartphone-assisted hydrogel "three-in-one" platform based on light-responsive carbon dots nanozyme for multimodal glyphosate detection.

Mikrochimica actaยท2026
Same author

Assessing decarbonization strategies and industrial symbiosis in the chemical and waste-to-energy sector.

Journal of industrial ecologyยท2026
Same author

Leptomeningeal metastatic cancer cells induce a permissive choroid plexus vasculature through extracellular-vesicle-derived 5-HIAA signaling.

Nature cancerยท2026

Related Experiment Video

Updated: May 2, 2026

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

8.7K

Multi-instance dictionary learning for detecting abnormal events in surveillance videos.

Jing Huo1, Yang Gao, Wanqi Yang

  • 1State Key Laboratory for Novel Software Technology, Nanjing University, P. R. China.

International Journal of Neural Systems
|February 21, 2014
PubMed
Summary

This study introduces Multi-Instance Dictionary Learning (MIDL) for detecting abnormal events in crowded videos. The novel MIDL method achieves comparable or improved performance over existing techniques for abnormal event detection.

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

8.6K

Related Experiment Videos

Last Updated: May 2, 2026

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

8.7K
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

8.6K

Area of Science:

  • Computer Vision
  • Machine Learning
  • Artificial Intelligence

Background:

  • Crowded scenes present challenges for event detection due to complex interactions.
  • Existing methods often struggle with identifying both global and local abnormalities.

Purpose of the Study:

  • To propose a novel Multi-Instance Dictionary Learning (MIDL) method for abnormal event detection in crowded videos.
  • To develop and evaluate different MIDL variants for improved detection accuracy.

Main Methods:

  • Modeled events as bags of instances (sub-events) within a multi-instance learning framework.
  • Jointly learned dictionaries for sparse representations and multi-instance classifiers.
  • Introduced Max-Pooling-based MIDL (MP-MIDL), Instance-based MIDL (Inst-MIDL), and Bag-based MIDL (Bag-MIDL).

Main Results:

  • MP-MIDL and Bag-MIDL achieved comparable or improved performance on UMN and UCSD datasets for abnormal event detection.
  • MP-MIDL demonstrated superior results compared to other multi-instance learning methods.
  • The proposed methods effectively detect both global and local abnormalities.

Conclusions:

  • The novel Multi-Instance Dictionary Learning (MIDL) framework offers an effective approach for abnormal event detection in crowded scenes.
  • Specific MIDL variants, particularly MP-MIDL, show significant promise for enhancing detection accuracy and robustness.