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 Video

Updated: May 26, 2026

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts.

João Carreira1, Cristian Sminchisescu

  • 1Computer Vision and Machine Learning Group, Institute for Numerical Simulation, University of Bonn, Quinta da Fonte Nova, lote 39, 1 degree, Alcobac¸a 2460, Portugal. carreira@ins.uni-bonn.de

IEEE Transactions on Pattern Analysis and Machine Intelligence
|December 7, 2011
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

Reconstructing Three-Dimensional Models of Interacting Humans.

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

Improving duplex ultrasound methods for diagnosing functional popliteal artery entrapment syndrome.

Scandinavian journal of medicine & science in sports·2024
Same author

Accelerated Measurement of Carotid Plaque Volume Using Artificial Intelligence Enhanced 3D Ultrasound.

Annals of vascular surgery·2023
Same author

The Importance of Patient Position When Defining Normal Versus Pathological Functionality in the Diagnosis of Popliteal Artery Entrapment Syndrome with Duplex Ultrasound.

European journal of vascular and endovascular surgery : the official journal of the European Society for Vascular Surgery·2023
Same author

Aneurysm Geometry Analyzed by the Novel Three-Dimensional Tomographic Ultrasound Relates to Abdominal Aortic Aneurysm Growth.

Annals of vascular surgery·2022
Same author

Evaluating Potential Autologous Bypass Grafts with Tomographic Three-Dimensional Ultrasound Compared with Standard Color Duplex.

Annals of vascular surgery·2022
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 introduces a new method for identifying object boundaries in images using computational processes. The approach effectively ranks segmentation hypotheses, outperforming existing techniques in image segmentation challenges.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Image Processing

Background:

  • Object segmentation is crucial for image understanding.
  • Existing methods often require class-specific knowledge or extensive training data.
  • Accurate spatial extent determination remains a challenge in computer vision.

Purpose of the Study:

  • To develop a novel framework for generating and ranking object segmentation hypotheses in images.
  • To achieve automatic segmentation without prior knowledge of object classes.
  • To improve the accuracy and robustness of image segmentation algorithms.

Main Methods:

  • Utilized bottom-up computational processes and mid-level cues for hypothesis generation.
  • Employed Constrained Parametric Min-Cut (CPMC) problems for automatic figure-ground segmentation.

More Related Videos

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: May 26, 2026

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

  • Trained a continuous model to rank segments based on mid-level region properties and real-world regularities.
  • Applied maximum marginal relevance measures for score diversification.

    • Main Results:

    • The proposed framework significantly outperforms state-of-the-art methods in low-level segmentation tasks.
    • Achieved top ranking in the VOC 2009 and VOC 2010 image segmentation and labeling challenges.
    • Demonstrated successful application in segmentation-based visual object category recognition pipelines.

    Conclusions:

    • The novel framework provides an effective approach for generating and ranking object segmentation hypotheses.
    • The method's ability to work without class-specific priors makes it broadly applicable.
    • This research advances the state of the art in automatic image segmentation and object recognition.