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

Embedding Based on Function Approximation for Large Scale Image Search.

Thanh-Toan Do, Ngai-Man Cheung

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |March 31, 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

    Biomarkers.

    Alzheimer's & dementia : the journal of the Alzheimer's Association·2025
    Same author

    Artificial intelligence for predicting hearing improvement after myringoplasty: a pilot study.

    Singapore medical journal·2023
    Same author

    Instance-Level Few-Shot Learning With Class Hierarchy Mining.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2023
    Same author

    FS-BAN: Born-Again Networks for Domain Generalization Few-Shot Classification.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2023
    Same author

    PAC-Bayes Meta-Learning With Implicit Task-Specific Posteriors.

    IEEE transactions on pattern analysis and machine intelligence·2022
    Same author

    Multimodal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing.

    IEEE transactions on neural networks and learning systems·2022
    Same journal

    TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering.

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

    SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving.

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

    HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

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

    Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

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

    Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

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

    Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

    IEEE transactions on pattern analysis and machine intelligence·2026
    See all related articles

    This study introduces a novel embedding method for image retrieval, enhancing local image features into higher dimensions. The proposed approach improves search accuracy and efficiency, outperforming existing methods on benchmarks.

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Information Retrieval

    Background:

    • Image retrieval relies on effective feature representation.
    • Existing methods like VLAD approximate features but have limitations.
    • High-dimensional embeddings can improve retrieval performance.

    Purpose of the Study:

    • To design an embedding method mapping local image features (e.g., SIFT) to high-dimensional representations for image retrieval.
    • To develop a computationally efficient, closed-form version for large-scale applications.
    • To evaluate the proposed method against state-of-the-art techniques.

    Main Methods:

    • Proposing a new function approximation approach for embedding local image features.
    • Aggregating embedded vectors to create a unified image representation.

    Related Experiment Videos

  • Deriving a fast, closed-form computation for the embedding method.
  • Conducting comparative experiments on standard image retrieval benchmarks.

    • Main Results:

    • The proposed embedding methods demonstrate superior performance compared to existing state-of-the-art techniques.
    • Effectiveness shown across various image vector representations (medium, short, binary).
    • The fast version ensures scalability for large-scale image search problems.

    Conclusions:

    • The novel embedding method offers significant improvements in image retrieval accuracy.
    • The efficient implementation makes it suitable for practical, large-scale image search systems.
    • This work advances feature representation techniques in computer vision and information retrieval.