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

Adaptive vector quantization with codebook updating based on locality and history.

Guobin Shen1, Bing Zeng, Ming-L Liou

  • 1Microsoft Res. Asia, Beijing, China. jackysh@microsoft.com

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|February 2, 2008
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

Active substances were screened out from the volatile compounds of mulberry leaves that have an Oviposition-attracting effect on female Glyphodes pyloalis (Lepidoptera: Pyralidae).

Journal of economic entomology·2026
Same author

Optimal Exercise Modality and Dose to Alleviate Depressive and Anxiety Symptoms in Patients With Cancer: A Network Meta-Analysis and Dose-Response Study.

Psycho-oncology·2026
Same author

CDsyn: A comprehensive database for deleterious human synonymous variation prediction.

iScience·2026
Same author

Supervised Small-Baseline and Large-Baseline Homography Learning With Diffusion-Based Data Generation.

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

Optimal exercise modalities and doses for improving quality of life in patients with Parkinson's disease: a network meta-analysis and dose-response study.

Journal of neurology·2026
Same author

Integrated network pharmacology and experimental verification to reveal the mechanisms of curcumin in the treatment of colorectal cancer.

Frontiers in pharmacology·2026
Same journal

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

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

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

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

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

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

GoP-based Quality Enhancement on Video Compression.

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

Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

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

Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
See all related articles

This study introduces two novel techniques for adaptive vector quantization (AVQ) systems: locality-based codebook updating and history aid. Combining these methods significantly enhances AVQ performance, especially for small codebook sizes.

Area of Science:

  • Digital Signal Processing
  • Data Compression
  • Machine Learning

Background:

  • Adaptive Vector Quantization (AVQ) is crucial for efficient data compression.
  • Existing AVQ systems face challenges with codebook updating efficiency and performance, particularly with small codebook sizes.
  • High correlation between neighboring vectors in data streams is often underutilized.

Purpose of the Study:

  • To propose and evaluate two novel techniques to improve Adaptive Vector Quantization (AVQ) systems.
  • To enhance the efficiency and effectiveness of codebook updating in AVQ.
  • To demonstrate significant performance gains over existing AVQ methods.

Main Methods:

  • Introduced 'locality-based codebook updating' where updates consider neighboring codewords in a cached manner.

Related Experiment Videos

  • Developed 'history aid' to leverage previously coded vectors for current quantization when codebooks are updated.
  • Combined both techniques for a synergistic improvement in AVQ systems.

    • Main Results:

    • The combined techniques offer substantial improvements over benchmark AVQ systems, particularly the Generalized Threshold Replenishment (GTR).
    • For a codebook size of 32, the proposed AVQ system achieved over 4 dB gain compared to GTR at 0.5 bpp on non-stationary signals.
    • Drastic improvements were observed when the operational codebook size was relatively small.

    Conclusions:

    • The proposed locality-based codebook updating and history aid techniques effectively enhance AVQ system performance.
    • The combined approach provides a significant advantage over traditional methods, especially in scenarios with limited codebook size.
    • These techniques offer a promising direction for future research and application in data compression.