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

Progressive Dictionary Learning With Hierarchical Predictive Structure for Low Bit-Rate Scalable Video Coding.

Wenrui Dai, Yangmei Shen, Hongkai Xiong

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |April 20, 2017
    PubMed
    Summary

    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

    Information-Theoretic Optimization for Task-Adapted Compressed Sensing Magnetic Resonance Imaging.

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

    Privacy-Preserving Verification of ML Preprocessing via Model Behavior Indicators.

    IEEE transactions on privacy·2026
    Same author

    Inhibitory regulation of itch and associated negative emotions by ventral hippocampal neurons in rats.

    The Journal of investigative dermatology·2026
    Same author

    Information extraction from clinical notes: are we ready to switch to large language models?

    Journal of the American Medical Informatics Association : JAMIA·2026
    Same author

    Secure distributed multiple imputation enables missing data inference for private data proprietors.

    NPJ digital medicine·2026
    Same author

    Diffusion-Augmented Graph Contrastive Learning for Knowledge-Aware Recommendation.

    IEEE transactions on neural networks and learning systems·2025

    This study introduces a novel progressive dictionary learning framework for scalable video coding, enhancing efficiency in low bitrates. The method improves coding performance by adaptively capturing structures and exploiting layer correlations.

    Area of Science:

    • Computer Science
    • Signal Processing
    • Information Theory

    Background:

    • Conventional hybrid coding frameworks face limitations in scalable video coding due to rigid sequential training and prediction.
    • Dictionary learning offers a promising alternative but requires adaptation for scalable video applications, particularly at low bitrates.

    Purpose of the Study:

    • To propose a progressive dictionary learning framework with a hierarchical predictive structure for efficient scalable video coding.
    • To enhance coding efficiency in the low bitrate region for enhancement layers while ensuring reconstruction performance.

    Main Methods:

    • Utilized sparse representation with a spatio-temporal dictionary for pyramidal layers.
    • Developed progressive dictionary learning for temporal scalability and error propagation control.

    Related Experiment Videos

  • Employed online learning within a hierarchical predictive structure for improved convergence and performance.
  • Integrated standardized codec cores (H.264/AVC, HEVC) for base and enhancement layer encoding.

    • Main Results:

    • The proposed framework adaptively captures local structures along motion trajectories.
    • Exploited correlations between neighboring resolution layers for improved efficiency.
    • Demonstrated superior performance compared to HEVC scalable extensions and simulcast across various resolutions.

    Conclusions:

    • The progressive dictionary learning framework with hierarchical prediction significantly improves scalable video coding efficiency, especially at low bitrates.
    • The method effectively balances coding efficiency with reconstruction performance.
    • The approach is compatible with current video coding standards like HEVC.