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 Concept Videos

Extraction: Advanced Methods00:56

Extraction: Advanced Methods

425
Metal ions can be separated from one another by complexation with organic ligands–the chelating agent– to form uncharged chelates. Here, the chelating agent must contain hydrophobic groups and behave as a weak acid, losing a proton to bind with the metal. Since most organic ligands used in this process are insoluble or undergo oxidation in the aqueous phase, the chelating agent is initially added to the organic phase and extracted into the aqueous phase. The metal-ligand complex is...
425
Masking and Demasking Agents01:19

Masking and Demasking Agents

2.4K
EDTA titrations may necessitate masking and demasking agents to temporarily protect a particular metal ion in a mixture from the EDTA reaction. These agents facilitate the sequential analysis of the metal ions by forming stable complexes with some—but not all—metal ions during certain steps.
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...
2.4K
Deconvolution01:20

Deconvolution

133
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
133
Force Classification01:22

Force Classification

1.1K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.1K
Downsampling01:20

Downsampling

131
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
131
Detection of Black Holes01:10

Detection of Black Holes

2.2K
Although black holes were theoretically postulated in the 1920s, they remained outside the domain of observational astronomy until the 1970s.
Their closest cousins are neutron stars, which are composed almost entirely of neutrons packed against each other, making them extremely dense. A neutron star has the same mass as the Sun but its diameter is only a few kilometers. Therefore, the escape velocity from their surface is close to the speed of light.
Not until the 1960s, when the first neutron...
2.2K

You might also read

Related Articles

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

Sort by
Same author

Clinical evidence of acupuncture for infertile women with diminished ovarian reserve undergoing IVF/ICSI: a systematic review and meta-analysis.

Frontiers in endocrinology·2026
Same author

Organoid modeling of lung branching morphogenesis and epithelial lineage specification.

Developmental cell·2026
Same author

Automated and quantitative segmentation of colorectal polyps via an information-guided deep learning network with boundary perception.

Quantitative imaging in medicine and surgery·2026
Same author

Catalytic lactate-regulatory nanosystems attenuate cellular senescence for atherosclerosis amelioration.

Bioactive materials·2026
Same author

Root traits and soil phosphorus gradients determine crop-specific responsiveness to arbuscular mycorrhizal fungi.

Annals of botany·2026
Same author

Pathogenic Characterization of a Novel G47R Transthyretin Mutation in Early-Onset Amyloid Cardiomyopathy.

Journal of the American Heart Association·2026

Related Experiment Video

Updated: Jun 8, 2025

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.3K

GCS-YOLOv8: A Lightweight Face Extractor to Assist Deepfake Detection.

Ruifang Zhang1,2, Bohan Deng1,2, Xiaohui Cheng3

  • 1Key Laboratory of Advanced Manufacturing and Automation Technology, Education Department of Guangxi Zhuang Autonomous Region, Guilin University of Technology, Guilin 541006, China.

Sensors (Basel, Switzerland)
|November 9, 2024
PubMed
Summary

We developed GCS-YOLOv8, a lightweight face extractor for deepfake detection. This model improves accuracy and reduces computational costs, making deepfake analysis more efficient and effective.

Keywords:
C2f-GDConvCCN-based Cross-Scale Feature Fusion with GDConvGroup Normalization and Shared Convolution Detect HeadHGStemP6YOLOv8deepfakeface extractionlightweight

More Related Videos

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

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

Published on: October 27, 2023

1.3K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K

Related Experiment Videos

Last Updated: Jun 8, 2025

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.3K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

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

Published on: October 27, 2023

1.3K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Digital Forensics

Background:

  • Deepfake videos present challenges like blurred features and false detections due to compression.
  • Existing face extraction methods often require high computational resources, hindering practical application.

Purpose of the Study:

  • To propose GCS-YOLOv8, a lightweight and efficient face extractor to aid deepfake detection.
  • To enhance accuracy in detecting faces in compressed deepfake videos while minimizing computational demands.

Main Methods:

  • Implemented HGStem module for initial downsampling to reduce false detections of small objects.
  • Introduced C2f-GDConv module and a P6 large target detection layer to optimize parameters and expand receptive fields.
  • Designed a cross-scale feature fusion module (CCFG) and improved the detection head with group normalization and shared convolution.
  • Refined the training dataset by removing low-quality labels to decrease false detection rates.

Main Results:

  • GCS-YOLOv8 achieved improved Average Precision (AP) on the WiderFace dataset: 94.2% (Easy), 92.7% (Medium), and 81.2% (Hard).
  • The model boasts significantly reduced parameters (1.68 MB, 44.2% reduction) and FLOPs (3.5 G, 56.8% reduction) compared to YOLOv8.
  • Demonstrated enhanced adaptability to scale variations and improved detection of large-scale faces in low-compression deepfakes.

Conclusions:

  • GCS-YOLOv8 offers a lightweight and effective solution for face extraction in deepfake detection.
  • The proposed methods successfully address challenges of blurred features, false detections, and high computational costs.
  • This model provides a more efficient and accurate tool for deepfake analysis.