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: Dec 11, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

876

Self-supervised Agent Learning for Unsupervised Cross-Domain Person Re-identification.

Kongzhu Jiang, Tianzhu Zhang, Yongdong Zhang

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |August 21, 2020
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    Masking and Demasking Agents01:19

    Masking and Demasking Agents

    3.3K
    EDTA titrations may necessitate masking and demasking agents to temporarily protect a particular metal ion in a mixture from the EDTA reaction. These agents facilitate the sequential analysis of the metal ions by forming stable complexes with some—but not all—metal ions during certain steps.
    There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...
    3.3K

    You might also read

    Related Articles

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

    Sort by
    Same author

    Long non-coding RNA UCA1 promotes the tumorigenesis in pancreatic cancer.

    Biomedicine & pharmacotherapy = Biomedecine & pharmacotherapie·2016
    Same author

    Facile Synthesis of Boron-Doped rGO as Cathode Material for High Energy Li-O2 Batteries.

    ACS applied materials & interfaces·2016
    Same author

    Identification of functional farnesoid X receptors in brain neurons.

    FEBS letters·2016
    Same author

    The hydrogen tunneling splitting in malonaldehyde: A full-dimensional time-independent quantum mechanical method.

    The Journal of chemical physics·2016
    Same author

    Cycloaddition Reaction of Vinylphenylfurans and Dimethyl Acetylenedicarboxylate to [8 + 2] Isomers via Tandem [4 + 2]/Diradical Alkene-Alkene Coupling/[1,3]-H Shift Reactions: Experimental Exploration and DFT Understanding of Reaction Mechanisms.

    The Journal of organic chemistry·2016
    Same author

    Surface Modification of Li-Rich Cathode Materials for Lithium-Ion Batteries with a PEDOT:PSS Conducting Polymer.

    ACS applied materials & interfaces·2016

    This study introduces Self-supervised Agent Learning (SAL) for unsupervised person re-identification (Re-ID), enabling better scalability and practicality. SAL effectively reduces domain gaps, learning discriminative models without manual annotations.

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Unsupervised person re-identification (Re-ID) offers practical advantages over supervised methods but struggles with learning discriminative models without labeled data.
    • Domain gaps between datasets hinder the performance of unsupervised Re-ID models in real-world deployments.

    Purpose of the Study:

    • To propose an end-to-end Self-supervised Agent Learning (SAL) algorithm for unsupervised cross-domain person Re-ID.
    • To reduce domain discrepancies and learn domain-invariant, discriminative representations for improved Re-ID performance.

    Main Methods:

    • The SAL algorithm utilizes a set of agents to bridge domain gaps, facilitating unsupervised cross-domain person Re-ID.
    • Employs three learning mechanisms: supervised label learning in the source domain, similarity consistency learning in the target domain, and cross-domain self-supervised learning.

    Related Experiment Videos

    Last Updated: Dec 11, 2025

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    876
  • Leverages agent learning principles to adaptively reduce domain discrepancy and learn robust representations.

    • Main Results:

    • The proposed SAL algorithm demonstrates effectiveness in learning discriminative Re-ID models without relying on annotations.
    • Achieves favorable performance against state-of-the-art unsupervised person Re-ID methods on three standard benchmarks.
    • Successfully learns domain-invariant representations by minimizing domain gaps through agent-based learning.

    Conclusions:

    • Self-supervised Agent Learning (SAL) is a novel and effective approach for unsupervised person Re-ID.
    • The method addresses the challenge of learning discriminative models in the absence of labeled data by reducing domain gaps.
    • SAL offers a scalable and practical solution for real-world person Re-ID applications.