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

Search research articles

Related Experiment Video

Updated: Jun 4, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Pseudo Sentences Evaluation and Quality-Aware Robust Learning for Unsupervised Text-Based Person Search.

Kai Niu, Jiahui Chen, Ke Han

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society

|May 22, 2026

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

Genome-wide identification and expression patterns of uridine diphosphate (UDP)-glycosyltransferase genes in the brown planthopper, Nilaparvata lugens.

Comparative biochemistry and physiology. Part D, Genomics & proteomics·2025

Same author

Myeloid-Derived Suppressor Cell Accumulation Drives Intestinal Fibrosis through mCCL6/hCCL15 Chemokine-Mediated Fibroblast Activation.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2024

Same author

Enhanced Thermal Safety of Hydrophobic SiO<sub>2</sub> Aerogels Through Introduction of Layered Double Oxides.

Gels (Basel, Switzerland)·2024

Same author

Detection by super-resolution microscopy of viral proteins inside bloodborne extracellular vesicles.

Extracellular vesicles and circulating nucleic acids·2024

Same author

Bullying victimization and self-harm in adolescents: The roles of emotion regulation and bullying peer norms.

Child abuse & neglect·2024

Same author

Recovery, processing, and application of food protein using sustainable technology.

Food chemistry·2024

This study introduces a new framework, PSE-QRL, to improve unsupervised Text-Based Person Search (TBPS) by enhancing the quality of generated sentences. The method effectively addresses semantic misalignment, leading to better retrieval performance.

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Unsupervised Text-Based Person Search (TBPS) relies on pseudo-sentences generated by Multi-modal Large Language Models (MLLMs).
The quality of these pseudo-sentences can be poor, leading to semantic misalignment and hindering model performance.
Existing methods lack robustness in handling imperfect pseudo-sentence data.

Purpose of the Study:

To propose a unified framework, PSE-QRL, for enhancing robustness to pseudo-sentences in unsupervised TBPS.
To improve the accuracy and reliability of representation learning in TBPS by addressing pseudo-sentence quality issues.
To achieve state-of-the-art retrieval performance in unsupervised TBPS.

Main Methods:

Developed PSE-QRL, a framework dynamically coupling an evolving TBPS model with MLLMs for pseudo-sentence reliability assessment.

More Related Videos

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis

Published on: August 9, 2024

Related Experiment Videos

Last Updated: Jun 4, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis

Published on: August 9, 2024

Implemented Multi-granularity Sentence Augmentation to increase the diversity of image-sentence pairs.

Utilized Hybrid Quality Evaluation combining MLLM reasoning and TBPS distinguishing capabilities for sentence quality assessment.

Employed Quality-aware Robust Learning to select and re-weight samples based on quality scores.

Main Results:

Demonstrated the effectiveness of PSE-QRL in improving learning robustness for unsupervised TBPS.
Achieved state-of-the-art (SOTA) retrieval performance on CUHK-PEDES, ICFG-PEDES, and RSTPReid benchmarks.
Showcased significant improvements in handling semantic misalignment caused by low-quality pseudo-sentences.

Conclusions:

The proposed PSE-QRL framework effectively enhances robustness to pseudo-sentences in unsupervised TBPS.
Hybrid quality evaluation and quality-aware learning are crucial for leveraging pseudo-sentences effectively.
PSE-QRL represents a significant advancement in unsupervised TBPS, offering SOTA performance and improved reliability.