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

Structural Classification of Joints01:20

Structural Classification of Joints

8.9K
Joints, also known as articulations, are classified based on their structural characteristics, i.e., based on whether the articulating surfaces of the adjacent bones are directly connected by fibrous connective tissue or cartilage, or whether the articulating surfaces contact each other within a fluid-filled joint cavity. These differences serve to divide the joints of the body into three structural classifications.
A fibrous joint is where the adjacent bones are united by fibrous connective...
8.9K

You might also read

Related Articles

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

Sort by
Same author

Correction to "Assembly of Chiral Helical Quinones via Enantioselective Organocatalytic [4+2] Annulation".

Organic letters·2026
Same author

Assembly of Chiral Helical Quinones via Enantioselective Organocatalytic [4+2] Annulation.

Organic letters·2026
Same author

Recent Progress of Small-molecule Inhibitors of O-GlcNAcase for Alzheimer's Disease.

Mini reviews in medicinal chemistry·2025
Same author

Pd/NHC sequentially catalyzed atroposelective synthesis of planar-chiral macrocycles.

Chemical science·2024
Same author

The characteristic pattern of functional connectivity density influenced by postmenopausal females in the preclinical stage of dementia.

Cerebral cortex (New York, N.Y. : 1991)·2024
Same author

Extracellular Expression of Feruloyl Esterase and Xylanase in <i>Escherichia coli</i> for Ferulic Acid Production from Agricultural Residues.

Microorganisms·2023

Related Experiment Video

Updated: Apr 15, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

294

Hierarchical Compositional Alignment for Zero-Shot Part-Level Segmentation.

Shan Yang1, Shujie Ji1, Zhendong Xiao1

  • 1School of Automation Science and Engineering, South China University of Technology, Guangzhou 510640, China.

Sensors (Basel, Switzerland)
|April 14, 2026
PubMed
Summary
This summary is machine-generated.

This study introduces a novel method for robotic part segmentation, enhancing visual language models (VLMs) to accurately identify object components. The approach improves zero-shot part segmentation performance for complex robotic tasks.

Keywords:
multi-hierarchy featuremultimodal alignmentpart segmentationvisual language models

More Related Videos

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

886
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.7K

Related Experiment Videos

Last Updated: Apr 15, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

294
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

886
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.7K

Area of Science:

  • Computer Vision
  • Robotics
  • Artificial Intelligence

Background:

  • Robotic fine-grained tasks require detailed object component understanding.
  • Visual Language Models (VLMs) excel at object recognition but struggle with part-level segmentation.
  • Existing VLMs face challenges in visual granularity, semantic hierarchy, and cross-modal bias for part segmentation.

Purpose of the Study:

  • To propose a one-stage VLM-based method for accurate part segmentation.
  • To address the limitations of current VLMs in understanding object components for robotic applications.

Main Methods:

  • Developed a Hierarchy-Aware Feature Selection mechanism to enhance spatial and semantic precision.
  • Implemented a Multi-Hierarchy Feature Adapter to bridge object-to-part feature granularity.
  • Introduced a Hierarchical Multimodal Alignment Module to harmonize classification accuracy and mask integrity, mitigating cross-modal bias.

Main Results:

  • Achieved improved zero-shot part segmentation performance.
  • Obtained 25.86% on Pascal-Part and 13.09% on ADE20K-Part.
  • Demonstrated significant gains of +0.81% hIoU and +2.96% hIoU over baseline methods.

Conclusions:

  • The proposed method advances robotic visual perception capabilities.
  • This work has potential applications in intelligent manufacturing and intelligent service industries.
  • The approach effectively enhances VLM performance for detailed part-level understanding.