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

Downsampling01:20

Downsampling

493
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
493
Linear Approximation in Frequency Domain01:26

Linear Approximation in Frequency Domain

280
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
280
Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

7.9K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
7.9K
Linear Approximation in Time Domain01:21

Linear Approximation in Time Domain

235
Nonlinear systems often require sophisticated approaches for accurate modeling and analysis, with state-space representation being particularly effective. This method is especially useful for systems where variables and parameters vary with time or operating conditions, such as in a simple pendulum or a translational mechanical system with nonlinear springs.
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
235
Residuals and Least-Squares Property01:11

Residuals and Least-Squares Property

8.7K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
8.7K
Curvilinear Motion: Rectangular Components01:23

Curvilinear Motion: Rectangular Components

941
Curvilinear motion characterizes the movement of a particle or object along a curved path, notably evident when envisioning a car navigating a winding road. If the car starts at point A, its position vector is established within a fixed frame of reference, where the ratio of the position vector to its magnitude signifies the unit vector pointing in the position vector's direction.
As the car advances, its position evolves over time. Quantifying the car's velocity involves computing the...
941

You might also read

Related Articles

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

Sort by
Same author

Band Gap Prediction of Two-Dimensional Materials Using a Gradient-Boosted Feature Selection Approach.

Journal of chemical information and modeling·2026
Same author

The ACPGBI AI taskforce report: A mixed-methods roadmap for AI in colorectal surgery.

Colorectal disease : the official journal of the Association of Coloproctology of Great Britain and Ireland·2025
Same author

Editorial: Robust Artificial Intelligence for Neurorobotics.

Frontiers in neurorobotics·2022
Same author

Expectations and Perceptions of Healthcare Professionals for Robot Deployment in Hospital Environments During the COVID-19 Pandemic.

Frontiers in robotics and AI·2021
Same author

The Active Inference Approach to Ecological Perception: General Information Dynamics for Natural and Artificial Embodied Cognition.

Frontiers in robotics and AI·2021
Same author

Autonomous multi-species environmental gas sensing using drone-based Fourier-transform infrared spectroscopy.

Optics express·2019
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

Related Experiment Video

Updated: Dec 6, 2025

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing
06:25

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

938

Lower dimensional kernels for video discriminators.

Emmanuel Kahembwe1, Subramanian Ramamoorthy2

  • 1Robust Autonomy and Decisions Group, The School of Informatics, The University of Edinburgh, 10 Crichton St, Edinburgh EH8 9AB, United Kingdom; The Edinburgh Centre of Robotics, The University of Edinburgh's Bayes Centre, 47 Potterrow, Edinburgh EH8 9BT, United Kingdom; The School of Engineering and Physical Sciences, The Robotarium, Heriot-Watt University, Edinburgh, EH14 4AS, United Kingdom.

Neural Networks : the Official Journal of the International Neural Network Society
|October 11, 2020
PubMed
Summary
This summary is machine-generated.

This study analyzes video discriminators in Generative Adversarial Networks (GANs), finding high curvature issues. We introduce efficient Lower-Dimensional Video Discriminators (LDVDs) to improve GAN performance and efficiency.

Keywords:
Discriminator analysisGenerative Adversarial NetworksVideo generation

More Related Videos

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

9.4K

Related Experiment Videos

Last Updated: Dec 6, 2025

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing
06:25

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

938
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

9.4K

Area of Science:

  • Computer Vision
  • Machine Learning
  • Deep Learning

Background:

  • Unconstrained video discriminator architectures in Generative Adversarial Networks (GANs) can lead to optimization difficulties due to high-curvature loss surfaces.
  • This curvature issue intensifies with increasing maximal kernel dimensions in video discriminators.

Purpose of the Study:

  • To analyze the impact of unconstrained architectures on video GAN discriminators.
  • To propose an efficient methodology for designing effective lower-dimensional video discriminators for GANs.
  • To enhance the performance and efficiency of video GAN models.

Main Methods:

  • Analysis of loss surface curvature in unconstrained video discriminators.
  • Development of a methodology for creating Lower-Dimensional Video Discriminators (LDVDs).
  • Application and evaluation of LDVD-GANs on complex datasets like UCF-101.

Main Results:

  • Identified high curvature in unconstrained video discriminators as a key optimization challenge.
  • Proposed LDVD-GANs significantly improve performance and efficiency of video GANs.
  • LDVDs demonstrated the ability to double the performance of Temporal-GANs.
  • Achieved state-of-the-art results on a single GPU.

Conclusions:

  • Lower-dimensional video discriminators offer a solution to optimization challenges in GANs.
  • The proposed LDVD-GAN methodology enhances both performance and computational efficiency.
  • LDVD-GANs represent a significant advancement for practical video generation with GANs.