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

Isotemporal substitution analysis of the effects of in-kindergarten structured and unstructured activity behaviors on sleep problems in preschool children.

BMC public health·2026

Same author

Bridging the Evidence Gap: A Prognostic CRP Threshold for East Asians With Coronary Heart Disease.

JACC. Asia·2026

Same author

Long-Term Prognostic Impact of Changes in Coronary Angiography-Derived Index of Microcirculatory Resistance Following PCI.

JACC. Cardiovascular interventions·2026

Same author

USP13 ameliorates myocardial infarction injury by inhibiting ferroptosis via stabilizing ALDOA.

Redox biology·2026

Same author

Associated Factors of Primary Cam Morphology in 4477 Early Adolescents: A Multiethnic, Population-Based, Cross-sectional Study (Generation R).

Orthopaedic journal of sports medicine·2025

Same author

Diabetes and ALDH2 Gene Polymorphism on Post-Ablation Atrial Fibrillation Recurrence.

JACC. Asia·2025

Same journal

Intervention Feasible Region and Driver Risk Capacity Aware Human-Machine Collaborative Safe Trajectory Planning.

IEEE transactions on neural networks and learning systems·2026

Same journal

A Unified Differential Denoising Learning Framework With a Pre-Trained Model and Fuzzy Graph Networks for Drug-Drug Interaction Prediction.

IEEE transactions on neural networks and learning systems·2026

Same journal

Self-Supervised Continuous Dynamic Graph Representation Learning via Hawkes Processes.

IEEE transactions on neural networks and learning systems·2026

Same journal

cPU: Consistent Risk Estimator for Positive-Unlabeled Learning.

IEEE transactions on neural networks and learning systems·2026

Same journal

Tuning-Free Latent Diffusion Models for Ultrahigh-Resolution Image Editing.

IEEE transactions on neural networks and learning systems·2026

Same journal

Hidden Data Recovery and Forecasting via Next-Generation Reservoir Computing With Multiscale Delay Selection.

IEEE transactions on neural networks and learning systems·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 9, 2025

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

ProtoCLIP: Prototypical Contrastive Language Image Pretraining.

Delong Chen, Zhao Wu, Fan Liu

IEEE Transactions on Neural Networks and Learning Systems

|December 4, 2023

Summary

This summary is machine-generated.

Prototypical contrastive language image pretraining (ProtoCLIP) enhances representation grouping for better efficiency and robustness. This method improves performance on downstream tasks and matches CLIP

More Related Videos

Transcranial Direct Current Stimulation tDCS of Wernicke's and Broca's Areas in Studies of Language Learning and Word Acquisition

Transcranial Direct Current Stimulation tDCS of Wernicke's and Broca's Areas in Studies of Language Learning and Word Acquisition

Published on: July 13, 2019

Portable Intermodal Preferential Looking IPL: Investigating Language Comprehension in Typically Developing Toddlers and Young Children with Autism

Portable Intermodal Preferential Looking IPL: Investigating Language Comprehension in Typically Developing Toddlers and Young Children with Autism

Published on: December 14, 2012

Related Experiment Videos

Last Updated: Jul 9, 2025

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

Transcranial Direct Current Stimulation tDCS of Wernicke's and Broca's Areas in Studies of Language Learning and Word Acquisition

Transcranial Direct Current Stimulation tDCS of Wernicke's and Broca's Areas in Studies of Language Learning and Word Acquisition

Published on: July 13, 2019

Portable Intermodal Preferential Looking IPL: Investigating Language Comprehension in Typically Developing Toddlers and Young Children with Autism

Portable Intermodal Preferential Looking IPL: Investigating Language Comprehension in Typically Developing Toddlers and Young Children with Autism

Published on: December 14, 2012

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Contrastive language-image pretraining (CLIP) excels at transferring learned representations to downstream tasks.
CLIP's InfoNCE objective aligns positive image-text pairs and separates negative ones, indirectly grouping similar representations.
An underlying representation grouping effect in CLIP is observed via within-modal anchors.

Purpose of the Study:

To introduce Prototypical Contrastive Language Image Pretraining (ProtoCLIP) for enhanced representation grouping efficiency and robustness.
To improve transfer learning capabilities in multimodal models.
To address the modality gap in representation learning.

Main Methods:

ProtoCLIP establishes prototype-level discrimination between image and text spaces for efficient knowledge transfer.
Prototypical back translation (PBT) decouples representation grouping from alignment, enabling learning under a large modality gap.
An online episodic training strategy allows scaling to unlimited data, incorporating external knowledge sources.

Main Results:

ProtoCLIP achieved +5.81% ImageNet linear probing improvement and +2.01% ImageNet zero-shot classification improvement on the Conceptual Captions dataset.
On the YFCC-15M dataset, ProtoCLIP matched CLIP's performance using only 33% of the training time.
The proposed methods demonstrate effective learning of meaningful representations despite significant modality gaps.

Conclusions:

ProtoCLIP offers a more efficient and robust approach to contrastive language-image pretraining.
The decoupling of grouping and alignment via PBT is key to handling modality gaps and incorporating external knowledge.
ProtoCLIP presents a scalable and effective alternative to existing pretraining methods, reducing training time and improving performance.