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 Concept Videos

Classification of Bones01:18

Classification of Bones

10.4K
The bones of the human skeletal system are of varied shapes, sizes, and functions. They can be classified based on their shape and function into four major classes: long bones, short bones, flat bones, and irregular bones. Some classifications include a fifth type, the sesamoid bones, as a separate class, whereas others categorize them under short bones.
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The...
10.4K
Extraction: Advanced Methods00:56

Extraction: Advanced Methods

1.2K
Metal ions can be separated from one another by complexation with organic ligands–the chelating agent– to form uncharged chelates. Here, the chelating agent must contain hydrophobic groups and behave as a weak acid, losing a proton to bind with the metal. Since most organic ligands used in this process are insoluble or undergo oxidation in the aqueous phase, the chelating agent is initially added to the organic phase and extracted into the aqueous phase. The metal-ligand complex is...
1.2K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

ImageNet3D: Towards General-Purpose Object-Level 3D Understanding.

Advances in neural information processing systems·2026
Same author

CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection.

Proceedings. IEEE International Conference on Computer Vision·2026
Same author

Acquiring Weak Annotations for Tumor Localization in Temporal and Volumetric Data.

Machine intelligence research (Beijing)·2026
Same author

Scaling 3D Compositional Models for Robust Classification and Pose Estimation.

Proceedings. IEEE International Conference on Computer Vision·2026
Same author

A comprehensive survey of AI agents in healthcare.

Journal of biomedical informatics·2026
Same author

Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More.

Proceedings of machine learning research·2026

Related Experiment Video

Updated: Feb 23, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.1K

DeepSkeleton: Learning Multi-Task Scale-Associated Deep Side Outputs for Object Skeleton Extraction in Natural

Wei Shen, Kai Zhao, Yuan Jiang

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |August 8, 2017
    PubMed
    Summary

    This study introduces a new deep learning method for extracting object skeletons from images, accurately capturing their varying thickness. The approach enhances object detection and segmentation tasks by providing detailed skeleton information.

    More Related Videos

    Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
    09:41

    Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

    Published on: April 21, 2023

    2.2K
    A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
    05:41

    A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

    Published on: February 6, 2020

    9.9K

    Related Experiment Videos

    Last Updated: Feb 23, 2026

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    1.1K
    Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
    09:41

    Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

    Published on: April 21, 2023

    2.2K
    A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
    05:41

    A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

    Published on: February 6, 2020

    9.9K

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Image Processing

    Background:

    • Object skeletons offer valuable information for object representation and detection, complementing object contours by detailing scale variations.
    • Extracting accurate object skeletons from natural images is challenging due to the need to process both local and non-local image context to determine skeleton pixel scale.

    Purpose of the Study:

    • To develop a novel fully convolutional network for robust object skeleton extraction from natural images.
    • To effectively determine and represent the scale (thickness) of skeleton pixels.

    Main Methods:

    • A fully convolutional network with multiple scale-associated side outputs was designed.
    • The network employed multi-task learning for skeleton localization (pixel classification) and skeleton scale prediction (pixel regression).
    • Supervision was applied at different network stages to guide scale-associated outputs, and responses were fused for effective multi-scale skeleton detection.

    Main Results:

    • The proposed method achieved promising results on two skeleton extraction datasets.
    • The approach significantly outperformed existing competitor methods in skeleton extraction accuracy.
    • The extracted skeletons and their scales demonstrated utility in foreground object segmentation and object proposal detection.

    Conclusions:

    • The novel network architecture effectively addresses the challenges of object skeleton extraction by incorporating multi-scale information.
    • The method provides accurate skeleton localization and scale prediction, improving upon existing techniques.
    • The validated applications highlight the practical value of detailed object skeletons and their scale information in computer vision tasks.