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 Video

Updated: Apr 18, 2026

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

1.2K

Scene recognition by manifold regularized deep learning architecture.

Yuan Yuan, Lichao Mou, Xiaoqiang Lu

    IEEE Transactions on Neural Networks and Learning Systems
    |January 27, 2015
    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

    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

    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

    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

    Hidden Data Recovery and Forecasting via Next-Generation Reservoir Computing With Multiscale Delay Selection.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    CAFF-CIL: Causality-Aware Freedom Forgetting Approach for Class-Incremental Learning.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    Harmonic Autoencoding Framework for Multiple Tasks in Magnetic Particle Imaging Reconstruction.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    A Survey on Human-Centric Voice-Face Multimodal Learning.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    Vision-Assisted Foundation Model for Solving Multitask Vehicle Routing Problems.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    FP3O: Enabling Proximal Policy Optimization in Multiagent Cooperation With Parameter-Sharing Versatility.

    IEEE transactions on neural networks and learning systems·2026
    See all related articles

    This study introduces a novel deep architecture for scene recognition, inspired by the human visual system. This approach effectively utilizes structural data information, outperforming existing methods in computer vision tasks.

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Scene recognition is crucial for bridging the gap in scene understanding between humans and computers.
    • Current semantic modeling techniques often use shallow, single-layer representations, neglecting inter-image structural information and leading to suboptimal performance.
    • The semantic gap in computer vision hinders machines from achieving human-like scene comprehension.

    Purpose of the Study:

    • To propose a novel manifold regularized deep architecture for enhanced scene recognition.
    • To leverage structural information within image data for improved feature learning.
    • To develop an unsupervised approach for learning high-level features in scene recognition.

    Main Methods:

    • A manifold regularized deep architecture is proposed, mimicking the human visual system for improved judgment.

    Related Experiment Videos

    Last Updated: Apr 18, 2026

    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

    1.2K
  • The architecture exploits the inherent structural information of image data to create mappings between visible and hidden layers.
  • An unsupervised learning strategy is employed to train the deep architecture for high-level feature extraction.

    • Main Results:

    • The proposed deep architecture effectively learns high-level features for scene recognition in an unsupervised manner.
    • Experiments conducted on standard datasets demonstrate the superiority of the proposed method over existing state-of-the-art techniques.
    • The method successfully addresses the limitations of shallow representations by incorporating structural data information.

    Conclusions:

    • The manifold regularized deep architecture offers a significant advancement in scene recognition within computer vision.
    • The unsupervised learning approach provides an effective way to learn complex features without labeled data.
    • This research contributes to narrowing the semantic gap, paving the way for more human-like computer vision systems.