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

Protein Networks02:26

Protein Networks

4.5K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.5K
Protein Networks02:26

Protein Networks

2.8K
2.8K
Network Covalent Solids02:18

Network Covalent Solids

16.1K
Network covalent solids contain a three-dimensional network of covalently bonded atoms as found in the crystal structures of nonmetals like diamond, graphite, silicon, and some covalent compounds, such as silicon dioxide (sand) and silicon carbide (carborundum, the abrasive on sandpaper). Many minerals have networks of covalent bonds.
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
16.1K
Excitation-Contraction Coupling in Skeletal Muscles01:20

Excitation-Contraction Coupling in Skeletal Muscles

14.6K
Excitation-contraction coupling is a series of events that occur between generating an action potential and initiating a muscle contraction. It occurs at the triad, a structure found in skeletal muscle fibers that comprise a T-tubule and terminal cisternae of the sarcoplasmic reticulum on each side. These triads are visible in longitudinally sectioned muscle fibers. They are typically located at the A-I junction — the junction between the A and I bands of the sarcomere.
When an action...
14.6K
Network Function of a Circuit01:25

Network Function of a Circuit

681
Frequency response analysis in electrical circuits provides vital insights into a circuit's behavior as the frequency of the input signal changes. The transfer function, a mathematical tool, is instrumental in understanding this behavior. It defines the relationship between phasor output and input and comes in four types: voltage gain, current gain, transfer impedance, and transfer admittance. The critical components of the transfer function are the poles and zeros.
681
Sequence Networks of Rotating Machines01:24

Sequence Networks of Rotating Machines

489
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
489

You might also read

Related Articles

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

Sort by
Same author

Extended reality in clinical neurology: From interdisciplinary innovations to clinical practice.

Cell reports. Medicine·2026
Same author

Learnable Object Queries for Few-Shot Semantic Segmentation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Grid Convolution for 3D Human Pose Estimation.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

An adaptive AI-based virtual reality sports system for adolescents with excess body weight: a randomized controlled trial.

Nature medicine·2025
Same author

Dual Branch Multi-Level Semantic Learning for Few-Shot Segmentation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2024
Same author

Efficient Binocular Rendering of Volumetric Density Fields With Coupled Adaptive Cube-Map Ray Marching for Virtual Reality.

IEEE transactions on visualization and computer graphics·2023

Related Experiment Video

Updated: Jan 25, 2026

Observing the Transformation of Bodily Self-consciousness in the Squeeze-machine Experiment
07:20

Observing the Transformation of Bodily Self-consciousness in the Squeeze-machine Experiment

Published on: March 8, 2019

14.2K

Squeeze-and-Excitation Networks.

Jie Hu, Li Shen, Samuel Albanie

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |April 30, 2019
    PubMed
    Summary

    This study introduces Squeeze-Excitation (SE) blocks to improve convolutional neural networks (CNNs). These blocks adaptively recalibrate channel-wise features, significantly boosting CNN performance with minimal computational overhead.

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Convolutional Neural Networks (CNNs) rely on convolution operators to extract features by combining spatial and channel information.
    • Prior research has focused on enhancing spatial feature encoding within CNNs.
    • The importance of channel interdependencies in feature representation remains an area for exploration.

    Purpose of the Study:

    • To propose a novel architectural unit, the Squeeze-Excitation (SE) block, for adaptively recalibrating channel-wise feature responses.
    • To investigate the explicit modeling of interdependencies between channels within CNNs.
    • To enhance the representational power of CNNs by focusing on channel relationships.

    Main Methods:

    • Introduction of the Squeeze-Excitation (SE) block as a novel architectural unit.

    More Related Videos

    Cell Squeezing as a Robust, Microfluidic Intracellular Delivery Platform
    08:02

    Cell Squeezing as a Robust, Microfluidic Intracellular Delivery Platform

    Published on: November 7, 2013

    13.3K
    External Excitation of Neurons Using Electric and Magnetic Fields in One- and Two-dimensional Cultures
    08:32

    External Excitation of Neurons Using Electric and Magnetic Fields in One- and Two-dimensional Cultures

    Published on: May 7, 2017

    13.9K

    Related Experiment Videos

    Last Updated: Jan 25, 2026

    Observing the Transformation of Bodily Self-consciousness in the Squeeze-machine Experiment
    07:20

    Observing the Transformation of Bodily Self-consciousness in the Squeeze-machine Experiment

    Published on: March 8, 2019

    14.2K
    Cell Squeezing as a Robust, Microfluidic Intracellular Delivery Platform
    08:02

    Cell Squeezing as a Robust, Microfluidic Intracellular Delivery Platform

    Published on: November 7, 2013

    13.3K
    External Excitation of Neurons Using Electric and Magnetic Fields in One- and Two-dimensional Cultures
    08:32

    External Excitation of Neurons Using Electric and Magnetic Fields in One- and Two-dimensional Cultures

    Published on: May 7, 2017

    13.9K
  • Stacking SE blocks to form Squeeze-Excitation Networks (SENets).
  • Integration of SE blocks into existing state-of-the-art CNN architectures.

    • Main Results:

    • SENets demonstrate highly effective generalization across diverse datasets.
    • SE blocks yield significant performance improvements in existing CNNs.
    • The proposed approach achieved first place in the ILSVRC 2017 classification challenge, reducing top-5 error by ~25% relative to the previous year.

    Conclusions:

    • Squeeze-Excitation blocks offer an effective mechanism for improving CNN performance by adaptively recalibrating channel-wise feature responses.
    • The SE block represents a computationally efficient method for enhancing feature representation in deep learning models.
    • The success in the ILSVRC 2017 challenge validates the efficacy of SE Networks for image classification tasks.