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

Temporal segmentation of video objects for hierarchical object-based motion description.

Yue Fu1, Ahmet Ekin, A Murat Tekalp

  • 1Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY 14627-0126, USA.

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|February 5, 2008
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

Interpretable machine learning-based automated HPLC/MS<sup>2</sup> platform using ion-molecule reactions for the identification of functionalities in analytes.

Chemical science·2026
Same author

Lipid droplet-mitochondria tethering releases MAVS inhibition to potentiate antiviral immunity.

Cell reports·2026
Same author

OCT-Based Quantitative Comparison of Full-Thickness Healing of Corneal Incisions in Cataract Surgery Between Diabetic and Nondiabetic Patients.

Cornea·2026
Same author

Polyamine sequestration of 2'3'-cGAMP constrains intercellular transmission and STING engagement to subvert antitumor immunity.

The Journal of clinical investigation·2026
Same author

A Rare Occurrence of Chronic Recurrent Multifocal Osteomyelitis in Clavicle: Case Report.

Journal of orthopaedic case reports·2026
Same author

Machine learning for oral frailty factors in hospitalized schizophrenia patients: two-stage feature selection and SHAP analysis.

Frontiers in psychiatry·2026
Same journal

Style-Aware Contrastive Test-Time Adaptation: A Dual-Cache Model for Robust Vision-Language Alignment.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Semantic Frame Interpolation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Physics-Guided Cross-Modal Decoupling with Test-Time Adaptation for Hyperspectral Image Restoration.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
See all related articles

This study introduces a hierarchical method for describing video object motion and interactions. It segments video into elementary motion units (EMU) and elementary reaction units (ERU) for efficient retrieval and summarization.

Area of Science:

  • Computer Vision
  • Video Analysis
  • Machine Learning

Background:

  • Current video analysis methods often lack detailed object-centric motion descriptions.
  • Describing complex object interactions in videos remains a challenge.

Purpose of the Study:

  • To develop a hierarchical framework for object-based motion and interaction description in videos.
  • To enable efficient video summarization, browsing, and retrieval through motion unit decomposition.

Main Methods:

  • Proposed a temporal hierarchy for object motion: elementary motion units (EMU) and action units (AU).
  • Decomposed object interactions into elementary reaction units (ERU) and interaction units (IU).
  • Developed algorithms for temporal segmentation of video objects into EMUs with dominant affine models and for ERU identification/classification.

Related Experiment Videos

Main Results:

  • Experimental results show that segmenting objects into EMUs and ERUs aids in generating high-level visual summaries.
  • The approach facilitates fast browsing and navigation of video content.
  • Demonstrated query-by-example retrieval of EMUs based on affine model similarity.

Conclusions:

  • Hierarchical decomposition of object motion and interactions improves video analysis.
  • The proposed methods enable efficient video summarization and retrieval.
  • Further research can focus on automating high-level action and interaction unit formation.