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

Labeling Emotion01:20

Labeling Emotion

594
Emotional labeling is a cognitive process that involves identifying and naming one's emotions, such as anger, fear, happiness, or sadness. It allows individuals to recognize and express their internal emotional states, a critical aspect of emotional regulation and communication. Labeling emotions requires more than mere recognition; it also involves drawing upon memory and contextual cues to understand the current situation and apply a corresponding emotional label. For instance, feeling...
594

You might also read

Related Articles

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

Sort by
Same author

Large aperture PPMgLN based high-power optical parametric oscillator at 3.8 µm pumped by a nanosecond linearly polarized fiber MOPA.

Optics express·2012
Same author

Neuroprotective effects of allicin on spinal cord ischemia-reperfusion injury via improvement of mitochondrial function in rabbits.

Neurochemistry international·2012
Same author

Genotoxicity evaluation of titanium dioxide nanoparticles using the Ames test and Comet assay.

Journal of applied toxicology : JAT·2012
Same author

Optimal dosing of cancer chemotherapy using model predictive control and moving horizon state/parameter estimation.

Computer methods and programs in biomedicine·2012
Same author

Metamaterials application in sensing.

Sensors (Basel, Switzerland)·2012
Same author

PoseShop: human image database construction and personalized content synthesis.

IEEE transactions on visualization and computer graphics·2012

Related Experiment Video

Updated: Jan 12, 2026

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

3.2K

Multi-label tongue image classification via label semantics-driven feature interaction enhancement.

Xiang Lu1, Yue Feng1, Xudong Jia2

  • 1School of Electronics and Information Engineering Wuyi University, Jiangmen 529020, China.

Computational Biology and Chemistry
|November 8, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a new framework for classifying tongue images in Traditional Chinese Medicine (TCM), improving diagnostic accuracy by better utilizing label semantics and feature interactions for intelligent healthcare applications.

Keywords:
Content-Guided AttentionCross-Modal Feature FusionInstance-Level RepresentationLabel-Semantics DrivenMulti-label Tongue Image Classification

More Related Videos

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.5K
Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology
05:38

Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology

Published on: June 29, 2021

2.8K

Related Experiment Videos

Last Updated: Jan 12, 2026

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

3.2K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.5K
Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology
05:38

Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology

Published on: June 29, 2021

2.8K

Area of Science:

  • Medical Imaging Analysis
  • Artificial Intelligence in Healthcare
  • Traditional Chinese Medicine Diagnostics

Background:

  • Multilabel classification of tongue images is crucial for intelligent diagnosis in Traditional Chinese Medicine (TCM).
  • Existing methods struggle with label semantics, local features, and hierarchical feature integration, limiting classification performance.
  • There's a need for enhanced methods to bridge the semantic gap and leverage comprehensive feature representations for accurate medical diagnoses.

Purpose of the Study:

  • To propose a novel multilabel tongue image classification framework, Label Semantic-Driven Feature Interaction Enhancement (LSDFIE).
  • To improve cross-modal interaction efficiency by integrating label semantics with local and spatial features.
  • To enhance classification performance by effectively utilizing synergistic and complementary mechanisms among hierarchical features.

Main Methods:

  • The LSDFIE framework integrates instance-level (local) and spatial-level (contextual) representations.
  • A Cross-Modal Fusion Module aligns label semantics with local tongue image features using low-rank bilinear attention.
  • An Image Modality Attention Enhancement Module evaluates correlations between spatial-level and instance-level representations, with fusion guided by content-attention.

Main Results:

  • The proposed method achieved a mean average precision (mAP) of 93.02% on the MlLTID dataset and 95.33% on the Tooth-Marked dataset.
  • On the ChestX-ray14 dataset, LSDFIE attained an area under the curve (AUC) of 84.11%, surpassing state-of-the-art by 0.36%.
  • Demonstrated superior classification accuracy and strong generalization capabilities across diverse medical imaging tasks.

Conclusions:

  • The LSDFIE framework effectively bridges the semantic gap between modalities and comprehensively leverages hierarchical features.
  • The method significantly enhances discriminative features while suppressing irrelevant ones, leading to robust recognition.
  • The validated superior performance highlights the potential of LSDFIE in advancing intelligent diagnosis within TCM and broader healthcare applications.