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

State Space Representation01:27

State Space Representation

316
The frequency-domain technique, commonly used in analyzing and designing feedback control systems, is effective for linear, time-invariant systems. However, it falls short when dealing with nonlinear, time-varying, and multiple-input multiple-output systems. The time-domain or state-space approach addresses these limitations by utilizing state variables to construct simultaneous, first-order differential equations, known as state equations, for an nth-order system.
Consider an RLC circuit, a...
316
Non-equilibrium in the Cell01:16

Non-equilibrium in the Cell

4.9K
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
4.9K
Deconvolution01:20

Deconvolution

271
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...
271
Downsampling01:20

Downsampling

288
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...
288
Stereotype Content Model02:16

Stereotype Content Model

14.9K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
14.9K
Upsampling01:22

Upsampling

342
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
342

You might also read

Related Articles

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

Sort by
Same author

Automatic Visual Inspection for Industrial Application.

Journal of imaging·2025
Same author

Latent Autoimmune Diabetes in Adults: A Diagnostic Challenge in Elderly Patients.

Cureus·2025
Same author

A Machine Learning App for Monitoring Physical Therapy at Home.

Sensors (Basel, Switzerland)·2024
Same author

Data2MV - A user behaviour dataset for multi-view scenarios.

Data in brief·2023
Same author

How to use robot interventions in intramural psychogeriatric care; A feasibility study.

Applied nursing research : ANR·2016
Same author

A Structured and Flexible Language for Physical Activity Assessment and Characterization.

Journal of sports medicine (Hindawi Publishing Corporation)·2015

Related Experiment Video

Updated: Sep 29, 2025

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

9.1K

Photo2Video: Semantic-Aware Deep Learning-Based Video Generation from Still Content.

Paula Viana1,2, Maria Teresa Andrade1,3, Pedro Carvalho1,2

  • 1INESC TEC, 4200-465 Porto, Portugal.

Journal of Imaging
|March 24, 2022
PubMed
Summary

This study introduces a novel machine learning (ML) workflow to automatically transform static photos into dynamic video stories. By analyzing visual content and context, it intelligently applies digital effects for semantically aware multimedia creation.

Keywords:
RoIautomated content creationcontext awarenessdeep learningsemantic awarenessstorytelling

Related Experiment Videos

Last Updated: Sep 29, 2025

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

9.1K

Area of Science:

  • Computer Vision
  • Multimedia Creative Arts
  • Artificial Intelligence

Background:

  • Machine learning (ML), particularly deep learning, is increasingly used for visual content analysis but underexplored in multimedia creative domains.
  • Current ML applications in content creation primarily focus on text or content selection, leaving visual multimedia creation largely untapped.
  • Significant potential exists in integrating ML into the multimedia creative process to automate content generation based on inferred knowledge.

Purpose of the Study:

  • To propose a methodology for retraining neural network models to identify thematic concepts and annotate regions of interest in static visual content.
  • To present digital visual effects and tools that can be automatically applied to analyzed photographs.
  • To define an automated creative workflow for transforming static photos into semantically aware multimedia stories using ML-driven annotations and effects.

Main Methods:

  • Retraining popular neural network models for thematic concept identification and region-based annotation of visual content.
  • Developing and integrating automated tools for applying diverse visual digital effects.
  • Establishing a complete automated workflow encompassing image acquisition, ML annotation, effect application, and multimedia story generation.

Main Results:

  • A methodology for enhancing neural networks to understand and annotate visual content with thematic concepts.
  • A system capable of automatically applying digital effects to photographs based on ML analysis.
  • An end-to-end automated workflow that converts static photos into context-aware video clips, contrasting with random movement generation.

Conclusions:

  • The proposed ML-driven workflow effectively transforms static digital photos into intelligent, semantically aware multimedia video stories.
  • This approach offers a significant advancement over traditional methods by incorporating content and context awareness.
  • The workflow enables the creation of dynamic visual narratives by leveraging ML for content understanding and automated effect application.