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

Muscles for Facial Expressions

Muscles for Facial Expressions

The craniofacial muscles are a collection of approximately 20 thin skeletal muscles situated beneath the skin of the face and scalp. These muscles, primarily responsible for the vast array of human facial expressions, originate from the bones or fibrous structures of the skull and extend outwards to connect with the skin. While most skeletal muscles in the body are enveloped in thick fascia, facial muscles generally have a more delicate fascial covering, with the buccinator muscle being a...

You might also read

Related Articles

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

Sort by

Same author

A multimodal MRI-radiomics deep learning model for survival risk stratification after gamma knife radiosurgery in patients with brain metastases: A multicenter retrospective study.

Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology·2026

Same author

Lactate metabolism and epigenetic reprogramming drive c-KIT hyperactivation to mediate Gilteritinib resistance: Rationale for c-KIT degraders over kinase inhibitors.

Acta pharmaceutica Sinica. B·2026

Same author

High-Entropy Alloys: A Review of Emerging Sensing Materials for Next-Generation Flexible Electronics.

Materials (Basel, Switzerland)·2026

Same author

Optimizing NGN2 Dosage Enhances the Neuronal Enrichment of iPSC-derived Neuronal Cultures.

Molecular & cellular proteomics : MCP·2026

Same author

XOV-Action: Towards Generalizable Open-Vocabulary Action Recognition.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

Gold(I)-Loaded Nanomedicine for Liver Cancer: A Closed-Loop Strategy Integrating Ferritinophagy-Driven Ferroptosis and Immunotherapy.

Journal of medicinal chemistry·2026

Search research articles

Related Experiment Video

Updated: Jul 7, 2025

Holistic Facial Composite Creation and Subsequent Video Line-up Eyewitness Identification Paradigm

Holistic Facial Composite Creation and Subsequent Video Line-up Eyewitness Identification Paradigm

Published on: December 24, 2015

Talk-to-Edit: Fine-Grained 2D and 3D Facial Editing via Dialog.

Yuming Jiang, Ziqi Huang, Tianxing Wu

IEEE Transactions on Pattern Analysis and Machine Intelligence

|December 26, 2023

Summary

This summary is machine-generated.

Talk-to-Edit enables continuous, fine-grained facial attribute manipulation via natural language dialog. This interactive framework uses a novel semantic field in GAN latent space for smoother, more realistic edits, outperforming existing methods.

More Related Videos

Improving 2D and 3D Skin In Vitro Models Using Macromolecular Crowding

Improving 2D and 3D Skin In Vitro Models Using Macromolecular Crowding

Published on: August 22, 2016

Author Spotlight: Enhancing Skin Model Diversity with Cost-Effective 3D Cellular Models

Author Spotlight: Enhancing Skin Model Diversity with Cost-Effective 3D Cellular Models

Published on: October 20, 2023

Related Experiment Videos

Last Updated: Jul 7, 2025

Holistic Facial Composite Creation and Subsequent Video Line-up Eyewitness Identification Paradigm

Holistic Facial Composite Creation and Subsequent Video Line-up Eyewitness Identification Paradigm

Published on: December 24, 2015

Improving 2D and 3D Skin In Vitro Models Using Macromolecular Crowding

Improving 2D and 3D Skin In Vitro Models Using Macromolecular Crowding

Published on: August 22, 2016

Author Spotlight: Enhancing Skin Model Diversity with Cost-Effective 3D Cellular Models

Author Spotlight: Enhancing Skin Model Diversity with Cost-Effective 3D Cellular Models

Published on: October 20, 2023

Area of Science:

Computer Vision
Artificial Intelligence
Natural Language Processing

Background:

Generative models can create high-fidelity 2D and 3D facial images.
Existing facial editing methods lack continuous, fine-grained control and natural user interaction.

Purpose of the Study:

To propose an interactive facial editing framework, Talk-to-Edit, for fine-grained attribute manipulation through user-system dialog.
To enable continuous and natural facial editing experiences.

Main Methods:

Modeling a continual semantic field in the Generative Adversarial Network (GAN) latent space.
Formulating fine-grained editing as finding curving trajectories on the semantic field, guided by user language requests and image context.
Generating language feedback for meaningful dialog, considering user requests and the semantic field's state.
Demonstrating effectiveness on 2D and 3D-aware generative models, introducing 'tri-plane' flow for 3D-aware models.
Creating the CelebA-Dialog dataset for visual-language facial editing research.

Main Results:

Achieved smooth, fine-grained facial editing with preserved identity and attributes.
Demonstrated superior visual photorealism and dialog fluency compared to previous methods.
User studies showed an 80% preference for the Talk-to-Edit system.
The 'tri-plane' flow effectively models changes in both color and density spaces for 3D-aware models.

Conclusions:

Talk-to-Edit offers a novel and effective approach to interactive facial editing using dialog.
The proposed semantic field and trajectory-finding method enable unprecedented control and realism in facial attribute manipulation.
The CelebA-Dialog dataset facilitates future research in visual-language facial editing.