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

Collisions in Multiple Dimensions: Problem Solving01:06

Collisions in Multiple Dimensions: Problem Solving

4.2K
In multiple dimensions, the conservation of momentum applies in each direction independently. Hence, to solve collisions in multiple dimensions, we should write down the momentum conservation in each direction separately. To help understand collisions in multiple dimensions, consider an example.
A small car of mass 1,200 kg traveling east at 60 km/h collides at an intersection with a truck of mass 3,000 kg traveling due north at 40 km/h. The two vehicles are locked together. What is the...
4.2K
ER Retrieval Pathway01:45

ER Retrieval Pathway

3.8K
In the secretory pathway, vesicles transport proteins from one cellular compartment to another in forward transport to deliver the protein to its correct location. Occasionally, misfolded proteins and incorrect proteins escape their original compartments, and a retrieval pathway is used to return the escaped proteins to their original compartment.
The ER uses many checkpoints to prevent the entry of incorrectly folded or a resident protein as cargo onto a transport vesicle. These mechanisms...
3.8K
Collisions in Multiple Dimensions: Introduction01:05

Collisions in Multiple Dimensions: Introduction

5.4K
It is far more common for collisions to occur in two dimensions; that is, the initial velocity vectors are neither parallel nor antiparallel to each other. Let's see what complications arise from this. The first idea is that momentum is a vector. Like all vectors, it can be expressed as a sum of perpendicular components (usually, though not always, an x-component and a y-component, and a z-component if necessary). Thus, when the statement of conservation of momentum is written for a...
5.4K
Imaging Biological Samples with Optical Microscopy01:18

Imaging Biological Samples with Optical Microscopy

4.7K
Optical microscopy uses optic principles to provide detailed images of samples. Antonie van Leeuwenhoek designed the first compound optical microscope in the 17th century to visualize blood cells, bacteria, and yeast cells. In 1830, Joseph Jackson Lister created an essentially modern light microscope. The 20th century saw the development of microscopes with enhanced magnification and resolution.
In optical microscopy, the specimen to be viewed is placed on a glass slide and clipped on the stage...
4.7K

You might also read

Related Articles

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

Sort by
Same author

Genome-wide association analysis reveals the genetic basis of thermal tolerance in dwarf surf clam Mulinia lateralis.

Genomics·2024
Same author

The Antiviral Potential of <i>Perilla frutescens</i>: Advances and Perspectives.

Molecules (Basel, Switzerland)·2024
Same author

Long-term path planning with optimal deployment of a charging station for monitoring photovoltaic solar farms.

Scientific reports·2024
Same author

In Situ High-Precision Measurement of Deep-Sea Dissolved Methane by Quartz-Enhanced Photoacoustic and Light-Induced Thermoelastic Spectroscopy.

Analytical chemistry·2024
Same author

Stimuli-responsive AIEgens with an ultra acidochromic scope for self-reporting soft actuators.

Biosensors & bioelectronics·2024
Same author

A colorimetric/electrochemical microfluidic biosensor using target-triggered DNA hydrogels for organophosphorus detection.

Biosensors & bioelectronics·2024

Related Experiment Video

Updated: Jul 2, 2025

Multimodal Hierarchical Imaging of Serial Sections for Finding Specific Cellular Targets within Large Volumes
11:19

Multimodal Hierarchical Imaging of Serial Sections for Finding Specific Cellular Targets within Large Volumes

Published on: March 20, 2018

10.4K

Hierarchical matching and reasoning for multi-query image retrieval.

Zhong Ji1, Zhihao Li2, Yan Zhang2

  • 1School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-inspired Intelligence Technology, Tianjin University, Tianjin, 300072, China; Shanghai Artificial Intelligence Laboratory, Shanghai, 200232, China.

Neural Networks : the Official Journal of the International Neural Network Society
|February 29, 2024
PubMed
Summary

This study introduces a Hierarchical Matching and Reasoning Network (HMRN) for Multi-Query Image Retrieval (MQIR). HMRN improves image retrieval accuracy by considering hierarchical similarities and semantic correlations between text queries and image regions.

Keywords:
Hierarchical structureHigh-level semantic correlationMulti-level alignmentMulti-query image retrieval

More Related Videos

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

839
Executing Complexity-Increasing Queries in Relational MySQL and NoSQL MongoDB and EXist Size-Growing ISO/EN 13606 Standardized EHR Databases
07:26

Executing Complexity-Increasing Queries in Relational MySQL and NoSQL MongoDB and EXist Size-Growing ISO/EN 13606 Standardized EHR Databases

Published on: March 19, 2018

9.3K

Related Experiment Videos

Last Updated: Jul 2, 2025

Multimodal Hierarchical Imaging of Serial Sections for Finding Specific Cellular Targets within Large Volumes
11:19

Multimodal Hierarchical Imaging of Serial Sections for Finding Specific Cellular Targets within Large Volumes

Published on: March 20, 2018

10.4K
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

839
Executing Complexity-Increasing Queries in Relational MySQL and NoSQL MongoDB and EXist Size-Growing ISO/EN 13606 Standardized EHR Databases
07:26

Executing Complexity-Increasing Queries in Relational MySQL and NoSQL MongoDB and EXist Size-Growing ISO/EN 13606 Standardized EHR Databases

Published on: March 19, 2018

9.3K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Information Retrieval

Background:

  • Multi-Query Image Retrieval (MQIR) enables searching for relevant images using multiple text descriptions for specific image regions.
  • Current MQIR methods often overlook hierarchical similarities and high-level semantic correlations, leading to incomplete image-text alignments.
  • Existing approaches primarily focus on single-level similarity, failing to capture the nuanced relationships required for effective retrieval.

Purpose of the Study:

  • To propose a novel Hierarchical Matching and Reasoning Network (HMRN) to address the limitations of existing MQIR methods.
  • To enhance MQIR by incorporating hierarchical semantic representations and exploring semantic correlations among region-query pairs.
  • To improve the accuracy and completeness of image retrieval in response to multiple, region-specific text queries.

Main Methods:

  • Developed a Hierarchical Matching and Reasoning Network (HMRN) that disentangles MQIR into three hierarchical semantic representations: local details, global context, and inherent correlations.
  • Implemented a Scalar-based Matching (SM) module for multi-level alignment similarity, including fine-grained local and context-aware global levels.
  • Introduced a Vector-based Reasoning (VR) module to uncover semantic correlations among multiple region-query pairs, capturing high-level reasoning similarity.

Main Results:

  • The proposed HMRN significantly outperforms current state-of-the-art methods on benchmark datasets.
  • Achieved a substantial improvement of 23.4% in the R@1 metric compared to the previous best method, Drill-down.
  • Demonstrated the effectiveness of integrating hierarchical similarities and semantic reasoning for superior MQIR performance.

Conclusions:

  • The HMRN effectively addresses the limitations of existing MQIR methods by incorporating hierarchical matching and reasoning.
  • The network's ability to capture fine-grained local details, contextual global scopes, and high-level correlations leads to superior retrieval accuracy.
  • The proposed approach represents a significant advancement in Multi-Query Image Retrieval technology.