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

Types Of Transformers01:16

Types Of Transformers

954
Transformers can provide desired voltages to a circuit by modifying the number of turns in the secondary windings.
If the ratio of the number of turns in the secondary winding to that of the primary winding is greater than one, then the transformer is said to be a step-up transformer. In a step-up transformer, the voltage at the secondary winding is greater than the voltage applied at the primary winding.
However, if this ratio is less than one, the transformer is said to be a step-down...
954
Transformers in Distribution System01:27

Transformers in Distribution System

99
Transformers in distribution systems can be broadly categorized into distribution substation transformers and other distribution transformers. They are crucial for stepping down high transmission voltages to levels suitable for distribution and end-user applications.
Distribution substation transformers come in various ratings and typically use mineral oil for insulation and cooling. To prevent moisture and air from entering the oil, some transformers use an inert gas like nitrogen to fill the...
99
The Ideal Transformer01:26

The Ideal Transformer

366
In single-phase two-winding transformers, two windings are coiled around a magnetic core characterized by cross-sectional area A and magnetic permeability μ. A phasor current i1 enters the left winding while i2 exits the right winding, establishing the fundamental working of the transformer through electromagnetic principles.
Ampere's Law forms the basis of understanding the magnetic field within the transformer. It states that the integral of the magnetic field intensity's...
366
Transformers with Off-Nominal Turns Ratios01:25

Transformers with Off-Nominal Turns Ratios

142
In scenarios involving parallel transformers with disparate ratings, developing per-unit models requires accommodating off-nominal turns ratios. This situation arises when the selected base voltages are not proportional to the transformer’s voltage ratings. Consider a transformer where the rated voltages are related by the term a. If the chosen voltage bases satisfy a relationship involving term b, term c is defined as the ratio of these bases. This ratio is then substituted into the...
142
Deconvolution01:20

Deconvolution

141
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
141
Cross Product01:25

Cross Product

235
The cross product is a fundamental concept in vector algebra that is a vector operation on two different vectors to obtain a third vector. Unlike the scalar product, the cross product results in a vector quantity perpendicular to both the original vectors.
The magnitude of the cross product is obtained by multiplying the magnitude of both the vectors and the sine of the angle between them. This means that a larger angle between the vectors will lead to a greater magnitude of the cross product.
235

You might also read

Related Articles

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

Sort by
Same author

Mycobacterium tuberculosis identification and antibiotic resistance gene profiling using nanopore sequencing: A new approach for tailoring more effective treatments for patients.

International journal of medical microbiology : IJMM·2026
Same author

Predicting response to neoadjuvant therapy in breast cancer using longitudinal DCE-MRI deep learning integrated with tumor microenvironment data.

Frontiers in immunology·2026
Same author

Dried persimmon peel as a sustainable feed ingredient for goats: Effects on nutrient digestion, energy-nitrogen metabolism, and methane mitigation.

Animal nutrition (Zhongguo xu mu shou yi xue hui)·2026
Same author

Aetiological Description of Urinary Tract Infections in Patients with Type 2 Diabetes and Construction of a Clinical Prediction Model: A Retrospective Study.

Archivos espanoles de urologia·2026
Same author

Analysis of the Efficacy and Safety of Retrograde Intrarenal Surgery Versus Percutaneous Nephrolithotomy in Elderly Patients with Renal Calculi.

Archivos espanoles de urologia·2026
Same author

Heavy Metal Contamination and Risk Assessment in Soil-Wheat/Corn Systems near Metal Mining Areas in Northwestern China.

Biology·2025

Related Experiment Video

Updated: Jun 14, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K

Decoupled Cross-Modal Transformer for Referring Video Object Segmentation.

Ao Wu1, Rong Wang1,2, Quange Tan1

  • 1School of Information and Cyber Security, People's Public Security University of China, Beijing 100038, China.

Sensors (Basel, Switzerland)
|August 29, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces DCT, a new transformer model for referring video object segmentation. DCT improves accuracy by better integrating language and visual data across multiple scales.

Keywords:
cross-modal transformerdecoupled queriesfeature pyramid networkreferring video object segmentation

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

379
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

8.9K

Related Experiment Videos

Last Updated: Jun 14, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

379
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

8.9K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Natural Language Processing

Background:

  • Referring video object segmentation (R-VOS) is crucial for understanding video content based on language.
  • Existing methods struggle with balanced cross-modal feature fusion and information loss during multi-scale processing.
  • Challenges include effectively transferring linguistic information to visual features and mitigating attention bias.

Purpose of the Study:

  • To propose DCT, an end-to-end decoupled cross-modal transformer for improved R-VOS.
  • To enhance the utilization of multi-modal and multi-scale information in R-VOS.
  • To address limitations in feature fusion and cross-modal information transfer.

Main Methods:

  • Developed a Language-Guided Visual Enhancement Module (LGVE) for linguistic information integration.
  • Introduced a decoupled transformer decoder with object queries for independent feature gathering.
  • Implemented a Cross-layer Feature Pyramid Network (CFPN) to preserve multi-scale visual details.

Main Results:

  • DCT demonstrates competitive segmentation accuracy on benchmark datasets (A2D-Sentences, JHMDB-Sentences, Ref-Youtube-VOS).
  • The proposed modules effectively improve the utilization of multi-modal and multi-scale information.
  • DCT achieves state-of-the-art performance compared to existing R-VOS methods.

Conclusions:

  • DCT offers a novel and effective approach to referring video object segmentation.
  • The decoupled cross-modal transformer architecture successfully addresses previous limitations.
  • DCT advances the field by improving segmentation accuracy and feature integration.