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 Experiment Videos

Semi-Supervised Multitask Learning for Scene Recognition.

Xiaoqiang Lu, Xuelong Li, Lichao Mou

    IEEE Transactions on Cybernetics
    |November 26, 2014
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    You might also read

    Related Articles

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

    Sort by
    Same author

    Semantic consistency-aware pseudo-temporal framework for multimodal remote sensing image segmentation.

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

    Reconstruction-Contrast Coupling Learning for Open-Set Semi-Supervised Hyperspectral Image Classification.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same author

    ReCoTR: Reducing Semantic Cognitive Shift via Dual-Consensus Token Compression for Remote Sensing Image-Text Retrieval.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same author

    Noise fingerprint-based infrared fixed pattern noise removal.

    Applied optics·2026
    Same author

    Exempting axillary staging surgery in breast cancer using multimodal ultrasound imaging and radiomics of sentinel lymph nodes.

    EClinicalMedicine·2026
    Same author

    Like Human Rethinking: Contour Transformer AutoRegression for Referring Remote Sensing Interpretation.

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

    Robust Semiglobal and Global Stabilization for Nonlinear Normal Form Systems by Time-Varying Feedback.

    IEEE transactions on cybernetics·2026
    Same journal

    Adaptive Global Asymptotic Output Stabilization of Uncertain Nonlinear Systems Under Dynamic State/Input Quantization.

    IEEE transactions on cybernetics·2026
    Same journal

    Accelerated Distributed Gradient Tracking for Constrained Aggregative Optimization Over Time-Varying Digraphs.

    IEEE transactions on cybernetics·2026
    Same journal

    Small-Gain-Based Plug-and-Play Distributed Control Framework for DC Microgrids With Decentralized Reconfiguration.

    IEEE transactions on cybernetics·2026
    Same journal

    Prescribed-Time Impulsive Control of High-Order Integrator Systems.

    IEEE transactions on cybernetics·2026
    Same journal

    Relaxed Stability Conditions for Model Predictive Control of Hybrid Dynamical Systems Using Hybrid Recurrent Neural Networks.

    IEEE transactions on cybernetics·2026
    See all related articles

    This study introduces a novel semi-supervised learning method to enhance scene recognition accuracy. By integrating multi-resolution images and sparse feature selection, it overcomes limitations in current visual analysis techniques.

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Artificial Intelligence

    Background:

    • Scene recognition is crucial for understanding visual information, focusing on objects and their relationships.
    • Existing methods struggle with accuracy due to limitations in analyzing multi-scale relationships and handling redundant features.

    Purpose of the Study:

    • To develop a semi-supervised learning mechanism to improve scene recognition accuracy.
    • To address limitations in multi-scale analysis and redundant feature identification in current approaches.

    Main Methods:

    • A multitask model was proposed to integrate scene images at different resolutions, addressing scale-related limitations.
    • A sparse feature selection-based manifold regularization (SFSMR) model was developed to select optimal features and preserve data manifold structure.

    Related Experiment Videos

  • The multitask model and SFSMR were combined to create a unified semi-supervised learning method.

    • Main Results:

    • The proposed semi-supervised learning method demonstrated improved accuracy in scene recognition tasks.
    • The integration of multi-resolution images and sparse feature selection effectively reduced limitations in existing methods.
    • Experimental results validated the efficacy of the developed approach in enhancing visual scene understanding.

    Conclusions:

    • The novel semi-supervised learning approach effectively enhances scene recognition by addressing multi-scale relationships and feature redundancy.
    • The combination of multitask learning and SFSMR offers a robust solution for improving visual information analysis.
    • This research contributes to advancing the field of scene recognition through innovative machine learning techniques.