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

Generic model abstraction from examples.

Yakov Keselman1, Sven Dickinson

  • 1School ofCTI, DePaul University, 243 S. Wabash Ave., Chicago, IL 60604, USA. ykeselman@cti.depaul.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|July 15, 2005
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

Probabilistic Directed Distance Fields for Ray-Based Shape Representations.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

Shape-Based Measures Improve Scene Categorization.

IEEE transactions on pattern analysis and machine intelligence·2023
Same author

Neural correlates of local parallelism during naturalistic vision.

PloS one·2022
Same author

Local contour symmetry facilitates scene categorization.

Cognition·2018
Same author

Spatial relationships between contours impact rapid scene classification.

Journal of vision·2018
Same author

Special issue on shape perception: recent results and models.

Seeing and perceiving·2012
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

This study bridges the representational gap in computer vision for model acquisition. We present a novel graph-theoretical approach to automatically generate 2D view-based class models from images.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Pattern Recognition

Background:

  • The recognition community often avoids bridging the representational gap between low-level image features and generic models.
  • Existing methods artificially bridge this gap using simplified scenes or model templates (3D CAD, 2D appearance).

Purpose of the Study:

  • To bridge the representational gap specifically for model acquisition.
  • To automatically acquire a generic 2D view-based class model from exemplar images.

Main Methods:

  • Introduced a novel graph-theoretical formulation for the problem.
  • Represented image data using region adjacency graphs and lattices.
  • Developed a shortest path-based approximation algorithm to address intractability.

Related Experiment Videos

Main Results:

  • Successfully demonstrated the approach on real imagery.
  • Provided an efficient solution for a previously intractable problem.

Conclusions:

  • The proposed method effectively bridges the representational gap in model acquisition.
  • Enables automatic generation of 2D view-based class models from image sets.