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

Learning local objective functions for robust face model fitting.

Matthias Wimmer1, Freek Stulp, Sylvia Pietzsch

  • 1Technische Universität München, Informatik 9-Bildverstehen und Wissenbasierte Systeme, Garching bei München, Germany. matthias.wimmer@cs.tum.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|June 21, 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

RETRACTED ARTICLE: Numerical Simulation of Gravity Flow in Sublevel Caving Based on Polyhedron DEM.

Mining, metallurgy & exploration·2025
Same author

Shared control in assistive robotics: A Cybathlon-winning approach.

Science robotics·2025
Same author

An assistive robot that enables people with amyotrophia to perform sequences of everyday activities.

Scientific reports·2025
Same author

Robotic world models-conceptualization, review, and engineering best practices.

Frontiers in robotics and AI·2023
Same author

Latent Ergonomics Maps: Real-Time Visualization of Estimated Ergonomics of Human Movements.

Sensors (Basel, Switzerland)·2022
Same author

A Digital Twin Approach for Contextual Assistance for Surgeons During Surgical Robotics Training.

Frontiers in robotics and AI·2021
Same journal

TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering.

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

SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving.

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

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

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

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

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

Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

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

Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

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

Researchers developed a new method to automatically learn objective functions for image analysis, improving model fitting accuracy and robustness compared to traditional ad hoc designs.

Area of Science:

  • Computer Vision
  • Image Analysis
  • Machine Learning

Background:

  • Model-based techniques excel at image interpretation, relying on fitting algorithms to optimize objective functions for accurate model fitting.
  • Current objective functions are often designed empirically, lacking robustness and requiring domain-specific knowledge.

Purpose of the Study:

  • To develop a novel approach for learning robust objective functions for image analysis.
  • To automate feature selection and minimize domain-specific knowledge requirements in objective function design.

Main Methods:

  • Formulated desirable properties for objective functions and proposed a learning-based approach.
  • Generated training data from manual image annotations and an ideal objective function.
  • Automated critical steps like feature selection.

Related Experiment Videos

Main Results:

  • Learned objective functions demonstrated increased robustness in empirical evaluations.
  • Fitting algorithms using learned objective functions achieved more accurate model fits than those using designed functions.

Conclusions:

  • Learned objective functions offer a more robust and automated alternative to traditional ad hoc designs.
  • This approach enhances the accuracy and reliability of model fitting in image analysis.