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 1, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

983

Research on pedestrian recognition in complex scenarios based on data augmentation using large language models.

Yuxuan Zhang1, Yueqiu Jiang2

  • 1Institute of Information Science and Engineering, Shenyang Ligong University, Shenyang, 110000, China.

Scientific Reports
|December 26, 2025
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models01:06

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models

333
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
333

You might also read

Related Articles

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

Sort by
Same author

Dual Roles of Exosomes in Tumor Progression and Their Bioengineering as Targeted Drug Carriers.

Analytical chemistry·2026
Same author

Physics-informed deep learning framework for wavefront sensing via optical beam pattern analysis.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same author

An Intelligent Ship Detection Algorithm Based on Visual Sensor Signal Processing for AIoT-Enabled Maritime Surveillance Automation.

Sensors (Basel, Switzerland)·2026
Same author

Topological charge recognition of vortex beams based on a convolutional neural network.

Journal of the Optical Society of America. A, Optics, image science, and vision·2025
Same author

Systematic Evaluation of Polarizing Agents for Dynamic Nuclear Polarization Enhanced NMR.

Angewandte Chemie (International ed. in English)·2025
Same author

LAG3 as a marker of immune activation in esophageal squamous carcinoma treated with concurrent chemoradiotherapy.

Cancer immunology, immunotherapy : CII·2025

This study introduces REG-YOLO, an improved pedestrian detection model for complex scenes. It enhances accuracy and reduces model size, outperforming baseline models and maintaining efficiency.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Machine Learning

Background:

  • Pedestrian detection in complex scenes is a significant challenge due to high false positive rates and large model parameter counts in existing algorithms.
  • Current methods struggle with accuracy and efficiency, particularly in diverse and challenging environmental conditions.

Purpose of the Study:

  • To propose an improved REG-YOLO model that enhances pedestrian detection accuracy and model lightness in complex scenarios.
  • To validate the model's generalization capabilities using data augmentation techniques.
  • To reduce computational complexity and the number of model parameters while improving detection stability.

Main Methods:

  • Developed an improved REG-YOLO model by coordinating multiple modules within the YOLO framework.

Related Experiment Videos

Last Updated: May 1, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

983
  • Employed data augmentation using large language model image generation to enhance generalization.
  • Validated performance through experimental comparisons against baseline and lightweight models.

    • Main Results:

    • The improved REG-YOLO model achieved increases of 0.5% in mAP@0.5, 1.3% in mAP@0.5:0.95, 1.1% in Precision, and 0.9% in Recall compared to the baseline.
    • Model parameters and computational complexity were reduced by 29.2% and 26.4%, respectively.
    • The model demonstrated superior stability in complex scenes and outperformed lightweight models in recall and mAP@0.5.

    Conclusions:

    • The enhanced REG-YOLO model significantly improves pedestrian detection accuracy, speed, and stability in complex environments.
    • The model effectively reduces detection failures and maintains low energy consumption.
    • Data augmentation with large language models successfully addressed sample deficiencies and enhanced the model's generalization capabilities.