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: Apr 19, 2026

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

1.2K

Weakly Supervised Composed Object Re-Identification With Large Models.

Yan Huang, Jie Lu, Qiang Wu

    IEEE Transactions on Cybernetics
    |April 17, 2026
    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

    Immune-related nephritis, ureteritis and cystitis secondary to immune checkpoint inhibitors: A case report and review of the literature.

    Experimental and therapeutic medicine·2026
    Same author

    Identification of the CYP19A1-GPER1 axis as a critical oncogenic driver in hepatocellular carcinoma via AKT activation.

    Journal of translational medicine·2026
    Same author

    Cosolvent-Modulated Donor Preaggregation Enhances Molecular Order in 20% Efficient Bilayer Organic Solar Cells.

    ACS applied materials & interfaces·2026
    Same author

    The prognostic significance of cholesterol, high-density lipoprotein and glucose (CHG) index in evaluating all-cause mortality risk in metabolic dysfunction-associated steatotic liver disease (MASLD) individuals: evidence from two cohort studies.

    Cardiovascular diabetology·2026
    Same author

    Nicotinamide N-Methyltransferase Inhibition Mitigates Cerulein-Induced Pancreatic Fibrosis via Galectin-3-Mediated Regulation of Stellate Cell Activation and Macrophage M2 Polarization in Mice.

    Inflammation·2026
    Same author

    Correction: UBL4A inhibits autophagy-mediated proliferation and metastasis of pancreatic ductal adenocarcinoma via targeting LAMP1.

    Journal of experimental & clinical cancer research : CR·2026
    Same journal

    A Novel One-Step Small Object Detector for Autonomous Aerial Vehicles.

    IEEE transactions on cybernetics·2026
    Same journal

    Online Data-Driven-Based Optimal Output Tracking Control Without Initial Stabilizing Policy.

    IEEE transactions on cybernetics·2026
    Same journal

    Digital Redesign-Based Interval State Estimation for Continuous Systems With Aperiodic Discrete Measurements.

    IEEE transactions on cybernetics·2026
    Same journal

    Output Prediction-Based Event-Triggered Interval Estimation for Continuous-Time Switched Systems.

    IEEE transactions on cybernetics·2026
    Same journal

    Differentially Private Distributed Algorithms for Aggregative Games Over Directed Graphs With Linear Convergence.

    IEEE transactions on cybernetics·2026
    Same journal

    Communication Delay-Based Under-Actuated MASVs Distributed Formation Tracking Control With Unknown Ocean Disturbances and Input Quantization.

    IEEE transactions on cybernetics·2026
    See all related articles

    We introduce composed object re-identification (CORI), a new task combining identity preservation and text-guided appearance changes. Our weakly supervised framework enables this novel retrieval setting, outperforming existing methods.

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Existing object re-identification (re-ID) methods preserve identity but lack appearance modification.
    • Composed image retrieval (CIR) allows attribute changes but not identity consistency.
    • A gap exists in retrieval tasks requiring both identity preservation and specified appearance modifications.

    Purpose of the Study:

    • Introduce composed object re-identification (CORI), a novel task addressing the limitations of re-ID and CIR.
    • Develop a weakly supervised framework for CORI using large language models (LLMs) and visual question answering (VQA).
    • Establish benchmark datasets and a baseline model for CORI evaluation.

    Main Methods:

    • Proposed a weakly supervised framework leveraging LLMs and VQA for automatic description generation.

    Related Experiment Videos

    Last Updated: Apr 19, 2026

    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

    1.2K
  • Developed a baseline model with shared-weight image encoders, a text encoder, and a compositor module.
  • Utilized contrastive, ID, and triplet losses for joint multimodal composition and identity-aware matching.

    • Main Results:

    • The proposed CORI method significantly outperforms adapted baselines from CIR and re-ID.
    • Achieved improvements in Rank@1 accuracy on benchmark datasets: RAP (2.1%), Celeb-reID-light (0.8%), VeRi-776 (9.9%), and VRIC (9.5%).

    Conclusions:

    • The novel CORI task is feasible and effectively addressed by the proposed weakly supervised framework.
    • The developed method demonstrates superior performance in simultaneously preserving identity and modifying appearance based on text guidance.
    • The established CORI datasets and baseline model pave the way for future research in this area.