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: May 26, 2026

Whole-cell Super-Resolution Imaging via DNA-PAINT on a Spinning Disk Confocal with Optical Photon Reassignment
07:12

Whole-cell Super-Resolution Imaging via DNA-PAINT on a Spinning Disk Confocal with Optical Photon Reassignment

Published on: January 6, 2026

Aggregating local image descriptors into compact codes.

Hervé Jégou1, Florent Perronnin, Matthijs Douze

  • 1INRIA, Campus de Beaulieu, 35042 Rennes, France. herve.jegou@inria.fr

IEEE Transactions on Pattern Analysis and Machine Intelligence
|December 14, 2011
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Aggregates Classification01:29

Aggregates Classification

Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Prevalence of allergic diseases and evaluation of total IgE and blood eosinophils as diagnostic biomarkers in Colombia, a tropical country.

The World Allergy Organization journal·2026
Same author

Knowledge among primary care physicians on urticaria treatment: Impact of educational interventions.

The journal of allergy and clinical immunology. Global·2026
Same author

Prevalence of adverse reactions and food allergies in Colombia: Cross-sectional national study.

The journal of allergy and clinical immunology. Global·2026
Same author

Identifying Implementation Gaps in the HIV Prevention Cascade among Peruvian Men Who Have Sex with Men.

AIDS and behavior·2026
Same author

An Ecological Momentary Assessment Smartphone App for High-Risk HIV Populations: Development and Usability Study.

JMIR formative research·2026
Same author

Autoallergy in chronic rhinosinusitis and its clinical relevance.

The World Allergy Organization journal·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
Same journal

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads.

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

Achieving Text-based Person Retrieval with Any Granularity.

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

This study introduces efficient large-scale image search methods. The Fisher kernel and optimized dimensionality reduction significantly improve search accuracy and reduce memory usage for vast image datasets.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Large-scale image search presents challenges in balancing accuracy, efficiency, and memory usage.
  • Existing methods like bag-of-visual words have limitations in performance and representation compactness.

Purpose of the Study:

  • To develop and evaluate novel techniques for aggregating local image descriptors.
  • To optimize dimensionality reduction and indexing for efficient and accurate large-scale image retrieval.
  • To achieve high search accuracy with significantly reduced memory footprint.

Main Methods:

  • Evaluation of various methods for aggregating local image descriptors into vectors.
  • Comparison of Fisher kernel against the bag-of-visual words approach.

Related Experiment Videos

Last Updated: May 26, 2026

Whole-cell Super-Resolution Imaging via DNA-PAINT on a Spinning Disk Confocal with Optical Photon Reassignment
07:12

Whole-cell Super-Resolution Imaging via DNA-PAINT on a Spinning Disk Confocal with Optical Photon Reassignment

Published on: January 6, 2026

  • Joint optimization of dimensionality reduction and indexing strategies.
  • Assessment of image representation size and search performance on a large dataset.

    • Main Results:

    • The Fisher kernel demonstrates superior performance over the bag-of-visual words approach for image descriptor aggregation.
    • Image representations can be compressed to a few dozen bytes without compromising accuracy.
    • Accurate search of a 100 million image dataset is achieved in approximately 250 ms on a single processor core.

    Conclusions:

    • The proposed methods effectively address the constraints of large-scale image search.
    • Fisher kernel and optimized dimensionality reduction offer a powerful solution for efficient and accurate image retrieval.
    • The approach enables highly accurate image searching with minimal memory requirements.