Search research articles

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

Related Concept Videos

Aggregates Classification

Aggregates Classification

Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...

You might also read

Related Articles

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

Sort by

Same author

Can using a pre-trained deep learning model as the feature extractor in the bag-of-deep-visual-words model always improve image classification accuracy?

PloS one·2024

Same author

Flavivirus Immunity in Disease Control and Viral Pathogenesis.

Viral immunology·2020

Same author

Study of KIR gene expression at the mRNA level in specific donor-derived NK cells after allogeneic HSCT.

Immunogenetics·2020

Same author

Effects of Chikungunya virus immunity on Mayaro virus disease and epidemic potential.

Scientific reports·2020

Same author

Interleukin-33-nuclear factor-κB-CCL2 signaling pathway promotes progression of esophageal squamous cell carcinoma by directing regulatory T cells.

Cancer science·2019

Same author

Curcumin Alleviates IUGR Jejunum Damage by Increasing Antioxidant Capacity through Nrf2/Keap1 Pathway in Growing Pigs.

Animals : an open access journal from MDPI·2019

Search research articles

Related Experiment Video

Updated: Dec 19, 2025

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

Pooling region learning of visual word for image classification using bag-of-visual-words model.

Ye Xu¹, Xiaodong Yu², Tian Wang²

¹School of IoT Technology, Wuxi Institute of Technology, Wuxi, China.

|June 6, 2020

Summary

This study introduces a novel Bag-of-Visual-Words (BoVW) approach for image classification, enabling each visual word to have unique pooling regions. This method enhances image representation discriminability and improves classification accuracy, especially when data is limited.

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

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

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Related Experiment Videos

Last Updated: Dec 19, 2025

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

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

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Area of Science:

Computer Vision
Machine Learning
Pattern Recognition

Background:

Deep Learning requires substantial data, making alternatives like Bag-of-Visual-Words (BoVW) crucial for image classification with limited datasets.
Existing BoVW pooling methods apply uniform spatial regions for all visual words, potentially limiting image representation discriminability.
The spatial distribution of local features varies significantly across different visual words, necessitating specialized pooling strategies.

Purpose of the Study:

To propose a novel BoVW pooling method where each visual word possesses its own distinct pooling regions.
To develop an effective and straightforward technique for learning these word-specific pooling regions.
To enhance the discriminability of image representations and improve classification accuracy in data-scarce scenarios.

Main Methods:

Introduced an 'observation window' to capture word responses across the entire image.
Organized pooling regions for each visual word using a tree structure, with nodes representing specific regions.
Learned word-specific pooling regions by constructing trees based on labeled coordinate data (response coordinates and image class labels).

Main Results:

Demonstrated improved classification accuracy ranging from 1% to 2.5% on four benchmark datasets (Scene-15, Caltech-101, Caltech-256, Corel-10).
Experimentally validated that assigning unique pooling regions per visual word benefits image classification.
Confirmed the effectiveness of the proposed method in enhancing image representation discriminability.

Conclusions:

The proposed method of learning word-specific pooling regions significantly enhances image classification performance.
This approach offers a valuable improvement for BoVW models, particularly in scenarios with limited training data.
The findings underscore the importance of adapting spatial pooling strategies to the characteristics of individual visual words.