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

Manifold Regularized Correlation Object Tracking.

Hongwei Hu, Bo Ma, Jianbing Shen

    IEEE Transactions on Neural Networks and Learning Systems
    |April 20, 2017
    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

    The second extracellular domain of connexin 50 is important for in cell adhesion, lens differentiation, and adhesion molecule expression.

    The Journal of biological chemistry·2023
    Same author

    Sertoli cells-derived exosomal miR-30a-5p regulates ubiquitin E3 ligase Zeb2 to affect the spermatogonial stem cells proliferation and differentiation.

    Reproductive toxicology (Elmsford, N.Y.)·2023
    Same author

    Polymorphisms in TRIB2 and CAPRIN2 Genes Contribute to the Susceptibility to High Myopia-Induced Cataract in Han Chinese Population.

    Medical science monitor : international medical journal of experimental and clinical research·2023
    Same author

    CoP@Ni core-shell heterostructure nanowire array: A highly efficient electrocatalyst for hydrogen evolution.

    Journal of colloid and interface science·2023
    Same author

    Duck gasdermin E is a substrate of caspase-3/-7 and an executioner of pyroptosis.

    Frontiers in immunology·2023
    Same author

    Vitamin B12 Ameliorates the Pathological Phenotypes of Multiple Parkinson's Disease Models by Alleviating Oxidative Stress.

    Antioxidants (Basel, Switzerland)·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 a semisupervised learning framework for object tracking using manifold regularization and augmented samples. The method improves tracking accuracy by leveraging unlabeled data and efficiently updating the correlation filter for online performance.

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Object tracking is crucial in computer vision.
    • Existing methods struggle with unlabeled data and complex sample spaces.
    • Correlation filters offer efficient tracking but can be improved with semisupervised approaches.

    Purpose of the Study:

    • To develop a novel manifold regularized correlation tracking method.
    • To enhance the utilization of unlabeled data in object tracking.
    • To improve the efficiency and accuracy of online visual tracking.

    Main Methods:

    • A manifold regularization-based correlation filter is introduced to leverage unlabeled data and sample space structure.
    • A semisupervised learning framework trains the classifier using positive, negative, and unlabeled samples.

    Related Experiment Videos

  • Block optimization strategies are employed for efficient online learning and filter updates.

    • Main Results:

    • The proposed method effectively utilizes unlabeled data through manifold regularization.
    • The semisupervised framework demonstrates robust performance across diverse tracking scenarios.
    • Experimental results show superior performance compared to state-of-the-art tracking algorithms.

    Conclusions:

    • The manifold regularized correlation tracking method offers significant improvements in accuracy and efficiency.
    • This semisupervised approach provides a robust solution for challenging visual tracking tasks.
    • The proposed technique advances the field of real-time object tracking.