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: Jan 17, 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

1.0K

Leveraging Semi-Supervised Learning and Meta-Learning for Re-Identification in Few-Shot Spatiotemporal Anomaly

Zhen Zhou, Ziyuan Gu, Pan Liu

    IEEE Transactions on Neural Networks and Learning Systems
    |September 19, 2025
    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

    Identification of Prognostic Markers of DNA Damage and Oxidative Stress in Diagnosing Papillary Renal Cell Carcinoma Based on High-Throughput Bioinformatics Screening.

    Journal of oncology·2023
    Same author

    Activation of Angiopoietin-Tie2 Signaling Protects the Kidney from Ischemic Injury by Modulation of Endothelial-Specific Pathways.

    Journal of the American Society of Nephrology : JASN·2023
    Same author

    Change plane model averaging for subgroup identification.

    Statistical methods in medical research·2023
    Same author

    Biodegradation of polyurethane by the microbial consortia enriched from landfill.

    Applied microbiology and biotechnology·2023
    Same author

    Automatic emotion regulation prompts response inhibition to angry faces in sub-clinical depression: An ERP study.

    Biological psychology·2023
    Same author

    [Effect of different frequencies of Er:YAG laser on bond properties of zirconia ceramic].

    Shanghai kou qiang yi xue = Shanghai journal of stomatology·2023
    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 unsupervised-semi-supervised stacking (USemiS), a novel framework for detecting spatiotemporal anomalies. USemiS effectively addresses challenges posed by limited labeled data, outperforming existing methods in critical applications.

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Data Science

    Background:

    • Spatiotemporal anomaly detection is crucial for public safety, environmental monitoring, and system optimization.
    • Existing methods struggle with sparse labeled data and complex dynamic systems.
    • A robust solution is needed to overcome these limitations.

    Purpose of the Study:

    • To introduce a novel framework, unsupervised-semi-supervised stacking (USemiS), for effective spatiotemporal anomaly detection.
    • To address the challenge of label scarcity in dynamic spatiotemporal systems.
    • To improve the performance and generalizability of anomaly detection models.

    Main Methods:

    • USemiS combines semi-supervised learning with ensemble meta-learning.
    • It utilizes unsupervised component learners for low-level anomaly representation.

    Related Experiment Videos

    Last Updated: Jan 17, 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

    1.0K
  • A consensus-based tuning mechanism weights robust learners, and spatiotemporal MixUp (ST-MixUp) enhances decision boundaries through data augmentation.

    • Main Results:

    • USemiS achieves state-of-the-art performance on traffic anomaly and crowd fall detection datasets.
    • It outperforms existing methods by 1.3% and 2.1% in AUC under extreme low-label conditions (0.4% and 0.8% labeled data).
    • The framework demonstrates significant improvements in detecting anomalies with minimal labeled data.

    Conclusions:

    • USemiS provides a scalable and robust solution for spatiotemporal anomaly detection in real-world scenarios.
    • The framework effectively disentangles latent anomaly patterns and mitigates the impact of label scarcity.
    • USemiS shows strong generalization capabilities across diverse spatiotemporal contexts.