Search research articles

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

Surgical Video Understanding with Alignment-Preserving Temporal Adaptation and Action Triplet Text Alignment.

Bioengineering (Basel, Switzerland)·2026

Same author

Transfer Learning Strategies for Pathological Foundation Models: A Systematic Evaluation in Brain Tumor Classification.

Pathology international·2026

Same author

Privacy-Aware Continual Self-Supervised Learning on Multi-Window Chest Computed Tomography for Domain-Shift Robustness.

Bioengineering (Basel, Switzerland)·2026

Same author

Enhancing Adversarial Defense via Brain Activity Integration Without Adversarial Examples.

Sensors (Basel, Switzerland)·2025

Same author

Expert Comment Generation Considering Sports Skill Level Using a Large Multimodal Model with Video and Spatial-Temporal Motion Features.

Sensors (Basel, Switzerland)·2025

Same author

Trial Analysis of Brain Activity Information for the Presymptomatic Disease Detection of Rheumatoid Arthritis.

Bioengineering (Basel, Switzerland)·2024

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

Search research articles

Related Experiment Video

Updated: Jul 9, 2025

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

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

Published on: December 15, 2023

Zero-Shot Traffic Sign Recognition Based on Midlevel Feature Matching.

Yaozong Gan¹, Guang Li², Ren Togo³

¹Graduate School of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Japan.

Sensors (Basel, Switzerland)

|December 9, 2023

Summary

This study introduces a novel zero-shot traffic sign recognition method that bypasses the need for extensive training data. By matching image similarities using mid-level features, it enables recognition of new traffic signs without fine-tuning.

Keywords:

midlevel feature traffic sign matching zero-shot traffic sign recognition

More Related Videos

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

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

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

Related Experiment Videos

Last Updated: Jul 9, 2025

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

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

Published on: December 15, 2023

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

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

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

Area of Science:

Computer Vision
Machine Learning
Artificial Intelligence

Background:

Traffic sign recognition is crucial for road safety and accident reduction.
Current methods, often using Convolutional Neural Networks (CNNs), require large datasets and fine-tuning for new sign categories.
Variations in traffic signs across regions and the introduction of new signs pose challenges for existing recognition systems.

Purpose of the Study:

To develop a traffic sign recognition method that operates without requiring training data (zero-shot recognition).
To enable recognition of new traffic sign categories without the need for additional training or fine-tuning.
To leverage mid-level features from CNNs for robust traffic sign feature representation.

Main Methods:

A traffic sign matching method based on zero-shot recognition is proposed.
The method directly matches the similarity between target and template traffic sign images.
Mid-level features extracted from CNNs are utilized to generate robust feature representations without further training.

Main Results:

The proposed method achieves accurate traffic sign recognition without prior training data.
Utilizing mid-level features significantly enhances the accuracy of zero-shot traffic sign recognition.
Promising recognition results were obtained on the German Traffic Sign Recognition Benchmark and a real-world dataset from Sapporo, Japan.

Conclusions:

The developed traffic sign matching method offers an effective solution for zero-shot recognition.
The approach overcomes limitations of traditional methods by eliminating the need for large datasets and fine-tuning.
This method demonstrates potential for real-world applications, especially in diverse environments with varying traffic sign regulations.