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

Stereotype Content Model

Stereotype Content Model

The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...

You might also read

Related Articles

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

Sort by

Same author

Psilocybin reduces fear memory and restores neuroplasticity in the hippocampus and medial prefrontal cortex.

Journal of psychopharmacology (Oxford, England)·2026

Same author

Impaired pupillary sensitivity in diabetic patients and correlation with visual outcome in cataract surgery.

BMC ophthalmology·2026

Same author

Globally doubled methane emissions from nutrient-enriched rivers.

National science review·2026

Same author

Knowledge Sharing Mediates the Relationship Between Nurses' Job Well-Being and InnovativeBehaviour: A Cross-Sectional Study.

Nursing open·2026

Same author

Multifunctional and Self-Healing Oxidized Bacterial Nanocellulose-Based Composite Hydrogels with pH-Switchable Cascade Enzyme Catalytic Activity for Accelerating Diabetic Wound Healing.

Advanced healthcare materials·2026

Same author

Lipid-based nanosystems for atherosclerosis treatment: Evolving approaches and novel therapeutic strategies.

Acta pharmaceutica Sinica. B·2026

Search research articles

Related Experiment Video

Updated: Sep 15, 2025

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Training strategies for semi-supervised remote sensing image captioning.

Qimin Cheng¹, Haojun Cheng², Linfeng Yuan³

¹School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, 430074, China. chengqm@hust.edu.cn.

Scientific Reports

|July 12, 2025

Summary

This summary is machine-generated.

This study introduces semi-supervised learning for remote sensing image captioning, reducing reliance on labeled data. New methods like WENTS and TSTN enhance caption quality and diversity, achieving state-of-the-art results.

Keywords:

Noisy student training Remote sensing image captioning Semi-supervised learning Weakly supervised learning

More Related Videos

Defining the Role Of Language in Infants' Object Categorization with Eye-tracking Paradigms

Defining the Role Of Language in Infants' Object Categorization with Eye-tracking Paradigms

Published on: February 8, 2019

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

Related Experiment Videos

Last Updated: Sep 15, 2025

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Defining the Role Of Language in Infants' Object Categorization with Eye-tracking Paradigms

Defining the Role Of Language in Infants' Object Categorization with Eye-tracking Paradigms

Published on: February 8, 2019

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

Area of Science:

Computer Vision
Artificial Intelligence
Remote Sensing

Background:

Remote sensing image captioning is crucial for environmental monitoring and disaster response.
Current models require large labeled datasets and are computationally expensive, limiting their use with scarce annotations.

Purpose of the Study:

To develop semi-supervised training strategies for remote sensing image captioning.
To reduce dependence on labeled data while improving caption quality and diversity.

Main Methods:

Proposed Weakly Supervised Enhanced Noisy Teacher-Student Network (WENTS) to improve generalization.
Developed Two-Stage Training Network (TSTN) for stable learning and diverse caption generation.
Employed semi-supervised learning to mitigate the need for extensive labeled data.

Main Results:

Achieved exceptional performance with low sampling rates and simple architectures, demonstrating high scalability.
Demonstrated state-of-the-art performance on benchmark datasets, including NWPU-Captions.
Improved CIDEr by 17.71% and Sm by 11.23% over previous methods on NWPU-Captions.

Conclusions:

Semi-supervised strategies effectively enhance remote sensing image captioning quality and diversity.
The proposed WENTS and TSTN methods offer scalable and efficient solutions for data-scarce scenarios.
This work advances the field by providing robust methods for generating high-quality captions from remote sensing imagery.