Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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 CXCL9/SPP1 polarity axis in tumor-associated macrophages: immunoregulatory and prognostic significance in non-small cell lung cancer.

Frontiers in immunology·2026

Same author

Subspecialty-specific foundation model for intelligent gastrointestinal pathology.

NPJ digital medicine·2026

Same author

Multi-omics integration reveals that pyrimidine metabolism in lung adenocarcinoma drives an immunosuppressive microenvironment.

iScience·2026

Same author

Molecular classification and prognosis study of pancreatic ductal adenocarcinoma through multi-omics integrated clustering analysis.

PeerJ·2026

Same author

Next Bit Prediction: A Unified Lossless and Lossy Point Cloud Geometry Compression Framework.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

Glycosylated IgG antibodies contribute to the recovery of haemorrhagic fever with renal syndrome patients.

eLife·2025

Search research articles

Related Experiment Video

Updated: Jul 13, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Towards Codebook-Free Deep Probabilistic Quantization for Image Retrieval.

Min Wang, Wengang Zhou, Xin Yao

IEEE Transactions on Pattern Analysis and Machine Intelligence

|October 13, 2023

Summary

DeepIndex uses deep neural networks for semantic-aware image retrieval, improving upon traditional quantization methods. This approach optimizes retrieval accuracy by learning a more discriminative feature space partition.

More Related Videos

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Published on: November 2, 2012

Quantifying Intermembrane Distances with Serial Image Dilations

Quantifying Intermembrane Distances with Serial Image Dilations

Published on: September 28, 2018

Related Experiment Videos

Last Updated: Jul 13, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Published on: November 2, 2012

Quantifying Intermembrane Distances with Serial Image Dilations

Quantifying Intermembrane Distances with Serial Image Dilations

Published on: September 28, 2018

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Quantization is a key technique for scalable image retrieval, often using inverted indices.
Traditional Voronoi cell-based quantization struggles with discriminative space partitioning for semantic retrieval.

Purpose of the Study:

To develop a novel deep probabilistic quantization method for enhanced semantic image retrieval.
To explore semantic-aware feature space partitioning using deep neural networks.

Main Methods:

Proposed DeepIndex method, a deep probabilistic quantization approach.
Utilized a deep neural network to output probabilities for assigning images to inverted index lists.
Optimized the neural network by maximizing retrieval accuracy rewards during training.

Main Results:

Achieved more semantically discriminative space partitioning compared to existing quantization methods.
Demonstrated the effectiveness of DeepIndex on public image datasets for semantic image retrieval.

Conclusions:

DeepIndex offers a superior alternative to traditional quantization for semantic image retrieval.
Deep learning enables more effective feature space partitioning for improved retrieval accuracy.