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

Deconvolution01:20

Deconvolution

601
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...
601
Protein Networks02:26

Protein Networks

4.6K
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,...
4.6K
Protein Networks02:26

Protein Networks

2.9K
2.9K
Network Covalent Solids02:18

Network Covalent Solids

16.2K
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...
16.2K
Network Function of a Circuit01:25

Network Function of a Circuit

880
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.
880
Sequence Networks of Rotating Machines01:24

Sequence Networks of Rotating Machines

503
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...
503

You might also read

Related Articles

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

Sort by
Same author

A Review of Deep Learning for Video Captioning.

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

Adaptive Siamese Tracking With a Compact Latent Network.

IEEE transactions on pattern analysis and machine intelligence·2023
Same author

A Survey on Deep Learning Technique for Video Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2022
Same author

Stylized Adversarial Defense.

IEEE transactions on pattern analysis and machine intelligence·2022
Same author

Underwater Image Enhancement With Hyper-Laplacian Reflectance Priors.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2022
Same author

Guidance Through Surrogate: Toward a Generic Diagnostic Attack.

IEEE transactions on neural networks and learning systems·2022

Related Experiment Video

Updated: Feb 13, 2026

Dissection and Immunostaining of Imaginal Discs from Drosophila melanogaster
10:10

Dissection and Immunostaining of Imaginal Discs from Drosophila melanogaster

Published on: September 20, 2014

27.7K

Imagining the Unimaginable Faces by Deconvolutional Networks.

Xin Yu, Fatih Porikli

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |March 20, 2018
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a novel deep learning method for aggressive super-resolution of thumbnail face images. The approach leverages global context and image class priors to generate high-resolution faces from extremely low-resolution inputs, outperforming existing methods.

    More Related Videos

    Analysis of SEC-SAXS data via EFA deconvolution and Scatter
    10:59

    Analysis of SEC-SAXS data via EFA deconvolution and Scatter

    Published on: January 28, 2021

    9.9K
    Dissection of Imaginal Discs from 3rd Instar Drosophila Larvae
    07:36

    Dissection of Imaginal Discs from 3rd Instar Drosophila Larvae

    Published on: February 17, 2007

    26.0K

    Related Experiment Videos

    Last Updated: Feb 13, 2026

    Dissection and Immunostaining of Imaginal Discs from Drosophila melanogaster
    10:10

    Dissection and Immunostaining of Imaginal Discs from Drosophila melanogaster

    Published on: September 20, 2014

    27.7K
    Analysis of SEC-SAXS data via EFA deconvolution and Scatter
    10:59

    Analysis of SEC-SAXS data via EFA deconvolution and Scatter

    Published on: January 28, 2021

    9.9K
    Dissection of Imaginal Discs from 3rd Instar Drosophila Larvae
    07:36

    Dissection of Imaginal Discs from 3rd Instar Drosophila Larvae

    Published on: February 17, 2007

    26.0K

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Image Processing

    Background:

    • Thumbnail face images present extreme super-resolution challenges due to their minimal pixel information.
    • Conventional super-resolution methods based on patch matching are inadequate for such low-resolution inputs.

    Purpose of the Study:

    • To develop an aggressive super-resolution technique for thumbnail face images.
    • To enhance image resolution by effectively utilizing global context and image class priors.

    Main Methods:

    • A deconvolutional neural network (DNN) was employed, incorporating a pixel-wise appearance similarity objective.
    • The DNN learns mappings from low-resolution to high-resolution face images.
    • A sub-network with additional convolutional layers was used to mitigate artifacts in upsampled feature maps.

    Main Results:

    • The method successfully super-resolves face images, preserving natural face structure and global context.
    • The network demonstrates robustness to variations in pose, facial expression, and translational misalignments.
    • Data augmentation enabled effective super-resolution for rotationally unaligned faces.

    Conclusions:

    • The proposed deconvolutional neural network approach achieves superior and more appealing results compared to state-of-the-art methods.
    • The method significantly reduces the need for precise face alignments in training datasets.
    • This technique offers a robust solution for high-fidelity face image super-resolution from very low-resolution sources.