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

342
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...
342

You might also read

Related Articles

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

Sort by
Same author

MUFOLD-DB: a processed protein structure database for protein structure prediction and analysis.

BMC genomics·2015
Same author

The I-TASSER Suite: protein structure and function prediction.

Nature methods·2014
Same author

Genome-wide expression analysis of soybean NF-Y genes reveals potential function in development and drought response.

Molecular genetics and genomics : MGG·2014
Same author

Classification of lung cancer using ensemble-based feature selection and machine learning methods.

Molecular bioSystems·2014
Same author

Resveratrol possesses protective effects in a pristane-induced lupus mouse model.

PloS one·2014
Same author

Protein-losing enteropathy in systemic lupus erythematosus: 12 years experience from a Chinese academic center.

PloS one·2014

Related Experiment Video

Updated: Oct 29, 2025

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

725

Cross-Dataset Point Cloud Recognition Using Deep-Shallow Domain Adaptation Network.

Feiyu Wang, Wen Li, Dong Xu

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |July 13, 2021
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces the Deep-Shallow Domain Adaptation Network (DSDAN) for 3D point cloud recognition. DSDAN enhances cross-dataset performance by using a two-view learning framework and a two-level adaptation strategy.

    More Related Videos

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

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.5K
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    3.1K

    Related Experiment Videos

    Last Updated: Oct 29, 2025

    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

    725
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.5K
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    3.1K

    Area of Science:

    • Computer Vision
    • Machine Learning
    • 3D Data Analysis

    Background:

    • 3D point cloud recognition is challenging due to missing texture information and distribution mismatches in cross-dataset scenarios.
    • Existing methods struggle with significant domain shifts between training and testing data for point clouds.

    Purpose of the Study:

    • To develop a novel domain adaptation network for robust 3D point cloud recognition across different datasets.
    • To address the limitations of traditional methods in handling sparse and texture-deficient point cloud data.

    Main Methods:

    • Proposed the Deep-Shallow Domain Adaptation Network (DSDAN) featuring a two-view learning framework.
    • Introduced a Bag-of-Points feature method as a complementary view to deep representations.
    • Implemented a two-level adaptation strategy including feature-level alignment and instance-level adaptation with a co-training scheme.

    Main Results:

    • The DSDAN method demonstrated superior performance compared to state-of-the-art methods on benchmark datasets.
    • The two-view learning framework effectively leveraged multiple feature representations for improved recognition.
    • The two-level adaptation strategy successfully mitigated domain distribution mismatch issues.

    Conclusions:

    • The proposed DSDAN method offers a significant advancement in cross-dataset 3D point cloud recognition.
    • The combination of two-view learning and adaptive strategies provides a robust solution for domain adaptation in point cloud analysis.