Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Accelerating scientific discovery with Co-Scientist.

Nature·2026

Same author

Advancing conversational diagnostic AI with multimodal reasoning.

Nature medicine·2026

Same author

Advancing regulatory variant effect prediction with AlphaGenome.

Nature·2026

Same author

Olympiad-level formal mathematical reasoning with reinforcement learning.

Nature·2025

Same author

Improving cosmological reach of a gravitational wave observatory using Deep Loop Shaping.

Science (New York, N.Y.)·2025

Same author

Publisher Correction: Wearable blood pressure sensors for cardiovascular monitoring and machine learning algorithms for blood pressure estimation.

Nature reviews. Cardiology·2025

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

Same journal

GoP-based Quality Enhancement on Video Compression.

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

Same journal

Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

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

Same journal

Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

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

See all related articles

Search research articles

Related Experiment Video

Updated: May 18, 2026

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Published on: February 18, 2015

Task-specific image partitioning.

Sungwoong Kim¹, Sebastian Nowozin, Pushmeet Kohli

¹Qualcomm Research Korea, Seoul 135-010, Korea. sungwoong.kim01@gmail.com

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society

|September 26, 2012

Summary

This summary is machine-generated.

We developed a novel task-specific image partitioning framework for computer vision. This approach enhances performance by creating region-based image representations tailored to specific tasks.

More Related Videos

Rapid Setup of Tissue Microarray and Tiled Area Imaging on the Multiplexed Ion Beam Imaging Microscope Using the Tile/SED/Array Interface

Rapid Setup of Tissue Microarray and Tiled Area Imaging on the Multiplexed Ion Beam Imaging Microscope Using the Tile/SED/Array Interface

Published on: September 15, 2023

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

Related Experiment Videos

Last Updated: May 18, 2026

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Published on: February 18, 2015

Rapid Setup of Tissue Microarray and Tiled Area Imaging on the Multiplexed Ion Beam Imaging Microscope Using the Tile/SED/Array Interface

Rapid Setup of Tissue Microarray and Tiled Area Imaging on the Multiplexed Ion Beam Imaging Microscope Using the Tile/SED/Array Interface

Published on: September 15, 2023

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

Area of Science:

Computer Vision
Machine Learning
Image Processing

Background:

Image partitioning is crucial for high-level computer vision tasks.
Current methods often partition images without considering the specific task.
This limitation can hinder overall task performance.

Purpose of the Study:

To introduce a task-specific image partitioning framework.
To improve high-level computer vision task performance through tailored image representation.
To outperform existing task-oblivious and supervised partitioning methods.

Main Methods:

Image partitioning using correlation clustering on a superpixel graph.
Maximizing a linear discriminant function defined over the superpixel graph.
Estimating task-specific similarity parameters via structured support vector machine (S-SVM) learning with training data.

Main Results:

Task-aware partitioning significantly improved labeling performance on benchmark datasets.
The proposed method outperformed state-of-the-art general-purpose and supervised partitioning algorithms.
S-SVM learning enhanced generalization ability and superpixel graph construction improved robustness.

Conclusions:

Task-specific image partitioning offers a superior approach to general methods.
The framework is widely applicable for enhancing performance in high-level image understanding.
This paradigm shift promises advancements in computer vision applications.