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

Upsampling01:22

Upsampling

188
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...
188
Super-resolution Fluorescence Microscopy01:37

Super-resolution Fluorescence Microscopy

6.8K
Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...
6.8K
Downsampling01:20

Downsampling

121
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...
121
Continuous -time Fourier Transform01:11

Continuous -time Fourier Transform

269
The Fourier series is instrumental in representing periodic functions, offering a powerful method to decompose such functions into a sum of sinusoids. This technique, however, necessitates modification when applied to nonperiodic functions. Consider a pulse-train waveform consisting of a series of rectangular pulses. When these pulses have a finite period, they can be accurately represented by a Fourier series. Yet, as the period approaches infinity, resulting in a single, isolated pulse, the...
269
Fast Fourier Transform01:10

Fast Fourier Transform

252
The Fast Fourier Transform (FFT) is a computational algorithm designed to compute the Discrete Fourier Transform (DFT) efficiently. By breaking down the calculations into smaller, manageable sections, the FFT significantly reduces the computational complexity involved. Direct computation of an N-point DFT requires N2 complex multiplications, whereas the FFT algorithm needs only (N/2)log⁡2N multiplications, offering a much faster performance.
The computational efficiency of the FFT becomes...
252
Reconstruction of Signal using Interpolation01:10

Reconstruction of Signal using Interpolation

157
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...
157

You might also read

Related Articles

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

Sort by
Same author

Delivery Strategies for Colchicine as a Critical Dose Drug: Reducing Toxicity and Enhancing Efficacy.

Pharmaceutics·2024
Same author

Occult urothelial carcinoma with mediastinal metastasis: A case report.

Oncology letters·2024
Same author

Phase Identification and Discovery of an Elusive Polymorph of Drug-Polymer Inclusion Complex Using Automated 3D Electron Diffraction.

Angewandte Chemie (International ed. in English)·2024
Same author

Mediating and moderating effects of authoritative parenting styles on adolescent behavioral problems.

Frontiers in psychology·2024
Same author

A transformer-based diffusion probabilistic model for heart rate and blood pressure forecasting in Intensive Care Unit.

Computer methods and programs in biomedicine·2024
Same author

Scalable production of recombinant three-finger proteins: from inclusion bodies to high quality molecular probes.

Microbial cell factories·2024
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

Related Experiment Video

Updated: May 24, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.7K

Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-Resolution.

Ao Li, Le Zhang, Yun Liu

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |March 3, 2025
    PubMed
    Summary
    This summary is machine-generated.

    We introduce CRAFT, a novel transformer for single image super-resolution (SISR) that enhances high-frequency details. Our method integrates convolutional and transformer strengths, outperforming existing techniques in both full-precision and quantized settings.

    More Related Videos

    Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform
    06:25

    Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

    Published on: February 12, 2014

    8.4K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    348

    Related Experiment Videos

    Last Updated: May 24, 2025

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    1.7K
    Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform
    06:25

    Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

    Published on: February 12, 2014

    8.4K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    348

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Image Processing

    Background:

    • Transformer models excel at long-range dependency extraction in single image super-resolution (SISR).
    • Existing transformers often prioritize global information capture, potentially neglecting crucial high-frequency image priors.
    • Transformers show limitations in high-frequency representation compared to convolutional neural networks.

    Purpose of the Study:

    • To develop a novel transformer architecture for SISR that effectively integrates high-frequency priors.
    • To improve the capacity of transformers in constructing high-frequency representations.
    • To enhance the efficiency of transformer-based SISR through quantization.

    Main Methods:

    • Proposed the Cross-Refinement Adaptive Feature Modulation Transformer (CRAFT) architecture.
    • Incorporated a High-Frequency Enhancement Residual Block (HFERB) for high-frequency information extraction.
    • Utilized a Shift Rectangle Window Attention Block (SRWAB) for global information capture and a Hybrid Fusion Block (HFB) for refinement.
    • Introduced a frequency-guided post-training quantization (PTQ) method with adaptive dual clipping and boundary refinement for efficiency.
    • Extended the PTQ strategy as a general quantization method for transformer-based SISR.

    Main Results:

    • CRAFT demonstrated superior performance over state-of-the-art methods in single image super-resolution.
    • The proposed architecture effectively captures both low-frequency and high-frequency image information.
    • The frequency-guided PTQ method significantly enhanced CRAFT's efficiency without compromising performance.
    • The PTQ strategy proved effective and universal for other transformer-based SISR techniques.

    Conclusions:

    • Transformer-based SISR can be significantly improved by incorporating high-frequency priors.
    • The CRAFT architecture offers a robust solution by hybridizing convolutional and transformer strengths.
    • The developed frequency-guided PTQ method provides an efficient and generalizable approach for quantizing transformer-based SISR models.