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 Concept Videos

Relationship Formation02:12

Relationship Formation

39.9K
What do you think is the single most influential factor in determining with whom you become friends and whom you form romantic relationships? You might be surprised to learn that the answer is simple: the people with whom you have the most contact. This most important factor is proximity. You are more likely to be friends with people you have regular contact with. For example, there are decades of research that shows that you are more likely to become friends with people who live in your dorm,...
39.9K

You might also read

Related Articles

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

Sort by
Same author

Integrating Agglomerative Perception with One-step Action Generation for Robotic Manipulation.

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

Synergistic effects of plaque geometry and composition on coronary hemodynamics and mechanical stability: a multiscale computational study.

Biomedical physics & engineering express·2026
Same author

Deployment Prior Injection for Run-Time Re-Biasable Object Detection.

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

Unifying Multi-Modal Hair Editing via Proxy Feature Blending.

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

Data-Driven Bidirectional Spatial-Adaptive Network for Weakly Supervised Object Detection in Remote Sensing Images.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

Sparse Trajectory Prediction.

IEEE transactions on pattern analysis and machine intelligence·2025

Related Experiment Video

Updated: Jun 13, 2025

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments
08:12

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

Published on: March 1, 2022

2.4K

Meta Pairwise Relationship Distillation for Unsupervised Person Re-Identification.

Haoxuanye Ji, Le Wang, Sanping Zhou

    IEEE Transactions on Neural Networks and Learning Systems
    |September 16, 2024
    PubMed
    Summary

    This study introduces a novel unsupervised person re-identification (Re-ID) method using meta pairwise relationship distillation (MPRD). MPRD effectively guides feature learning with pairwise relationships, outperforming existing methods on benchmark datasets.

    More Related Videos

    Spotting Cheetahs: Identifying Individuals by Their Footprints
    09:47

    Spotting Cheetahs: Identifying Individuals by Their Footprints

    Published on: May 1, 2016

    14.8K
    Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues
    07:34

    Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues

    Published on: June 3, 2013

    17.3K

    Related Experiment Videos

    Last Updated: Jun 13, 2025

    A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments
    08:12

    A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

    Published on: March 1, 2022

    2.4K
    Spotting Cheetahs: Identifying Individuals by Their Footprints
    09:47

    Spotting Cheetahs: Identifying Individuals by Their Footprints

    Published on: May 1, 2016

    14.8K
    Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues
    07:34

    Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues

    Published on: June 3, 2013

    17.3K

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Unsupervised person re-identification (Re-ID) is crucial for surveillance and security.
    • Existing methods often struggle with inaccurate cluster number estimation, impacting performance.
    • Lack of ground-truth labels presents a significant challenge in unsupervised Re-ID.

    Purpose of the Study:

    • To propose a novel unsupervised person Re-ID method that avoids determining the number of clusters.
    • To leverage pairwise pseudo-labels for robust feature learning.
    • To enhance the accuracy and efficiency of unsupervised Re-ID systems.

    Main Methods:

    • Meta pairwise relationship distillation (MPRD) using a graph convolutional network (GCN) for high-fidelity pairwise relationship supervision.
    • Incorporation of metadata with high-confidence pairwise relationships and unlabeled pairs into GCN training.
    • Introduction of a hard sample deduction (HSD) module to mitigate noisy labels and a positive pair alignment (PPA) module to reduce feature redundancy.

    Main Results:

    • The proposed MPRD method demonstrates superior performance compared to state-of-the-art unsupervised Re-ID techniques.
    • Experiments conducted on Market-1501, DukeMTMC-reID, and MSMT17 datasets validate the effectiveness of the approach.
    • The method successfully addresses the limitations of cluster number estimation in traditional unsupervised Re-ID.

    Conclusions:

    • MPRD offers a robust and effective solution for unsupervised person Re-ID by utilizing pairwise relationships.
    • The integration of GCN, HSD, and PPA modules significantly improves feature learning and model accuracy.
    • This work advances the field of unsupervised Re-ID, providing a promising direction for future research.