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

Convolution Properties II01:17

Convolution Properties II

168
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
168
Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

226
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
226
Convolution Properties I01:20

Convolution Properties I

136
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
136
Deconvolution01:20

Deconvolution

129
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...
129
Properties of DTFT II01:24

Properties of DTFT II

179
In the study of discrete-time signal processing, understanding the properties of the Discrete-Time Fourier Transform (DTFT) is crucial for analyzing and manipulating signals in the frequency domain. Several properties, including frequency differentiation, convolution, accumulation, and Parseval's relation, offer powerful tools for signal analysis.
The frequency differentiation property is illustrated by considering a DTFT pair and differentiating both sides with respect to ω.
179
Neural Circuits01:25

Neural Circuits

1.0K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
1.0K

You might also read

Related Articles

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

Sort by
Same author

LivingAvatars: Robust Head Reconstruction With Gaussian Lifecycle Management and Neural Detail Synthesis.

IEEE transactions on visualization and computer graphics·2026
Same author

E$^{3}$3-Net: Efficient E(3)-Equivariant Normal Estimation Network.

IEEE transactions on visualization and computer graphics·2025
Same author

Inhibiting ADORA1 enhances glioma apoptosis and increases its sensitivity to anti-PD1 therapy.

Frontiers in oncology·2025
Same author

Mesh2Brep: B-Rep Reconstruction via Robust Primitive Fitting and Intersection-Aware Constraints.

IEEE transactions on visualization and computer graphics·2025
Same author

Towards Voronoi Diagrams of Surface Patches.

IEEE transactions on visualization and computer graphics·2025
Same author

[Spatio-temporal Differentiation and Its Driving Mechanism of Ecological Vulnerability in Sichuan Province].

Huan jing ke xue= Huanjing kexue·2024

Related Experiment Video

Updated: Jun 4, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K

MPIC: Exploring alternative approach to standard convolution in deep neural networks.

Jie Jiang1, Yi Zhong1, Ruoli Yang1

  • 1National University of Defense Technology, Department of Systems Engineering, the Laboratory for Big Data and Decision, Changsha, 410073, China.

Neural Networks : the Official Journal of the International Neural Network Society
|January 4, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces the Multi-scale Progressive Inference Convolution (MPIC), an innovative deep learning approach that enhances feature extraction in Convolutional Neural Networks (CNNs) without increasing computational cost. MPIC improves performance across various computer vision tasks.

Keywords:
ConvolutionMulti-scaleNeural networksProgressive inference

More Related Videos

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

463
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.3K

Related Experiment Videos

Last Updated: Jun 4, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K
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

463
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.3K

Area of Science:

  • Computer Vision
  • Deep Learning
  • Artificial Intelligence

Background:

  • Convolutional Neural Networks (CNNs) remain vital for grid-structured data processing, despite the rise of Transformers.
  • Enhancing CNN feature extraction while maintaining parameter efficiency is crucial.

Purpose of the Study:

  • To explore novel alternatives to standard and depthwise separable convolutions.
  • To introduce the Multi-scale Progressive Inference Convolution (MPIC) for augmented feature extraction.
  • To ensure compatibility with existing CNN architectures like MobileNet and ResNet.

Main Methods:

  • Development of the Multi-scale Progressive Inference Convolution (MPIC).
  • MPIC integrates large receptive fields, multi-scale processing, and gradual inference.
  • Experiments conducted on multiple benchmark datasets.

Main Results:

  • MPIC significantly enhances feature extraction capabilities compared to standard convolutions.
  • Proposed convolutional alternatives demonstrate improved performance while retaining computational efficiency.
  • Compatibility confirmed with established networks (MobileNet, ResNet, ResNest).

Conclusions:

  • The proposed MPIC and other convolutional alternatives offer substantial performance gains in computer vision.
  • Ablation studies validate the effectiveness of these solutions for object detection, class activation mapping, and salient object detection.