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

Parallel Processing01:20

Parallel Processing

350
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
350
Visual System01:26

Visual System

851
Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...
851
Sequence Networks of Rotating Machines01:24

Sequence Networks of Rotating Machines

169
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...
169

You might also read

Related Articles

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

Sort by
Same author

Altered Functional Connectivity Patterns of the Insular Subregions in Psychogenic Nonepileptic Seizures.

Brain topography·2014
Same author

Arterial stiffness is a potential mechanism and promising indicator of orthostatic hypotension in the general population.

VASA. Zeitschrift fur Gefasskrankheiten·2014
Same author

Ligand-exchange assisted formation of Au/TiO2 Schottky contact for visible-light photocatalysis.

Nano letters·2014
Same author

Reduced white matter integrity and cognitive deficits in maintenance hemodialysis ESRD patients: a diffusion-tensor study.

European radiology·2014
Same author

Silencing ADAM10 inhibits the in vitro and in vivo growth of hepatocellular carcinoma cancer cells.

Molecular medicine reports·2014
Same author

Use of a transjugular intrahepatic portosystemic shunt combined with autologous bone marrow cell infusion in patients with decompensated liver cirrhosis: an exploratory study.

Cytotherapy·2014

Related Experiment Video

Updated: Oct 10, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

677

Dynamic Parallel Pyramid Networks for Scene Recognition.

Kai Liu, Seungbin Moon

    IEEE Transactions on Neural Networks and Learning Systems
    |December 9, 2021
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a novel dynamic scene recognition method using a dynamic parallel pyramid (DPP) block. DPP networks improve image recognition accuracy and efficiency by adaptively selecting receptive field sizes for multiscale scene features.

    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

    550
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.4K

    Related Experiment Videos

    Last Updated: Oct 10, 2025

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

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

    Published on: December 15, 2023

    677
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    550
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.4K

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Scene recognition is challenging due to multiscale information in images.
    • Current convolutional neural networks (CNNs) have limitations in fixed receptive field sizes and computational intensity.
    • Existing methods struggle with large-scale variations in scene complexity.

    Purpose of the Study:

    • To develop a lightweight and dynamic scene recognition approach.
    • To address the limitations of fixed receptive fields and high computational costs in CNNs.
    • To improve the accuracy and efficiency of scene recognition models.

    Main Methods:

    • A novel dynamic parallel pyramid (DPP) block is proposed.
    • DPP adaptively selects receptive field size using multiscale input information.
    • Multiscale features are encoded via different convolutional kernels and merged using group attention and channel shuffling.

    Main Results:

    • DPP networks (DPP-Nets) show significant performance improvements on large-scale datasets (Places365, MIT Indoor67, Sun397).
    • The method achieves better results compared to state-of-the-art approaches.
    • General applicability is demonstrated on lightweight models (MobileNetV2, ShuffleNetV2) and smaller datasets (CIFAR-10, CIFAR-100).

    Conclusions:

    • The proposed dynamic scene recognition approach effectively handles multiscale variations.
    • DPP blocks offer a lightweight and efficient solution for deep learning models.
    • DPP-Nets provide a promising direction for advancing scene recognition technology.