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 Videos

Sabine Sternig1, Peter M Roth, Horst Bischof

  • 1Institute for Computer Graphics and Vision, Graz University of Technology, Austria.

Pattern Recognition Letters
|May 5, 2012
PubMed
Summary
This summary is machine-generated.

This study introduces inverse multiple instance learning (IMIL) to enhance object detection systems. IMIL improves recall and accuracy for non-moving objects by adapting online learning with temporal background image analysis.

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

Harnessing deep learning to detect bronchiolitis obliterans syndrome from chest CT.

Communications medicine·2025
Same author

Image capturing, segmentation and data analysis of shredded refuse streams.

Waste management & research : the journal of the International Solid Wastes and Public Cleansing Association, ISWA·2024
Same author

Automated cross-sectional view selection in CT angiography of aortic dissections with uncertainty awareness and retrospective clinical annotations.

Computers in biology and medicine·2023
Same author

Automatic Detection of Periapical Osteolytic Lesions on Cone-beam Computed Tomography Using Deep Convolutional Neuronal Networks.

Journal of endodontics·2022
Same author

Enzyme activity profiling for physiological phenotyping within functional phenomics: plant growth and stress responses.

Journal of experimental botany·2022
Same author

Critical Aspects of Person Counting and Density Estimation.

Journal of imaging·2021
Same journal

Regional patch-based MRI brain age modeling with an interpretable cognitive reserve proxy.

Pattern recognition letters·2026
Same journal

Plug and Play Labeling Strategies for Boosting Small Brain Lesion Segmentation.

Pattern recognition letters·2026
Same journal

MedLesSynth-LD: Lesion synthesis using physics-based noise models for robust lesion segmentation in low-data medical imaging regimes.

Pattern recognition letters·2025
Same journal

Time to retire F1-binary score for action unit detection.

Pattern recognition letters·2024
Same journal

On the bias in the AUC variance estimate.

Pattern recognition letters·2024
Same journal

A too-good-to-be-true prior to reduce shortcut reliance.

Pattern recognition letters·2023
See all related articles

Area of Science:

  • Computer Vision
  • Machine Learning

Background:

  • Classifier grids are effective for object detection from static cameras.
  • Online learning offers adaptive yet stable detection systems.
  • Current systems struggle with short-term drifting for non-moving objects.

Purpose of the Study:

  • To overcome short-term drifting in object detection systems.
  • To increase detection recall while maintaining accuracy.
  • To adapt multiple instance learning (MIL) for online boosting.

Main Methods:

  • Applied inverse multiple instance learning (IMIL) to online boosting.
  • Utilized temporal bags of background images across different time scales.
  • Ensured negative samples within each temporal bag for theoretical requirements.

Related Experiment Videos

Main Results:

  • Demonstrated superior classification results for non-moving objects.
  • Successfully addressed the short-term drifting problem.
  • Enhanced system recall without compromising accuracy.

Conclusions:

  • Inverse multiple instance learning is effective for improving object detection.
  • The proposed method enhances stability and performance in challenging scenarios.
  • This approach offers a robust solution for static object detection.