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

Masking and Demasking Agents01:19

Masking and Demasking Agents

3.2K
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...
3.2K
Observational Learning01:12

Observational Learning

699
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
699

You might also read

Related Articles

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

Sort by
Same author

Multifunctional 3D-printed Mg-doped bioactive glass/PLLA scaffolds with quercetin delivery for remodeling the osteoporotic microenvironment via osteogenic-angiogenic coupling and osteoclast inhibition.

International journal of biological macromolecules·2026
Same author

The Rise of Social Media Websites: How Plastic Surgeons Interact with Patients in the Digital Age, a Multicenter Study of China.

Aesthetic plastic surgery·2026
Same author

Identification of FOXK1 and SEMA7A as key genes associated with m<sup>6</sup>A-related programmed cell death in diabetic retinopathy.

Hereditas·2026
Same author

Knowledge, attitudes, and practices regarding chronic atrophic gastritis in gastroenterology outpatient patients.

BMC public health·2026
Same author

Graph Domain Adaptation via Theory-Grounded Spectral Regularization.

... International Conference on Learning Representations·2026
Same author

Successful resection of a giant well-differentiated liposarcoma using a modified snare technique.

Endoscopy·2026

Related Experiment Video

Updated: Dec 7, 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

9.7K

Privacy-Preserving Deep Action Recognition: An Adversarial Learning Framework and A New Dataset.

Zhenyu Wu, Haotao Wang, Zhaowen Wang

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |September 28, 2020
    PubMed
    Summary

    This study introduces a new adversarial training framework for privacy-preserving video action recognition. It optimizes privacy budgets against any attacker model and presents a new dataset, PA-HMDB51, for advancing visual privacy research.

    Related Experiment Videos

    Last Updated: Dec 7, 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

    9.7K

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Cybersecurity

    Background:

    • Video-based action recognition is crucial for smart camera applications.
    • Ensuring privacy in video analysis is a growing challenge.
    • Existing privacy metrics are insufficient against diverse adversarial attacks.

    Purpose of the Study:

    • To develop a privacy-preserving deep learning framework for video action recognition.
    • To optimize the trade-off between task performance and privacy budgets.
    • To enhance universal privacy protection against various attacker models.

    Main Methods:

    • Formulated a novel adversarial training framework for anonymization transforms.
    • Proposed model restarting and ensemble strategies for robust privacy protection.
    • Introduced a cross-dataset training heuristic to overcome data limitations.

    Main Results:

    • The framework explicitly optimizes privacy-utility trade-offs.
    • New optimization strategies provide stronger universal privacy guarantees.
    • Developed and released the PA-HMDB51 dataset with comprehensive privacy and action labels.

    Conclusions:

    • The proposed framework effectively balances utility and privacy in video action recognition.
    • The novel dataset and methods advance the field of visual privacy research.
    • This work facilitates the development of more secure and private AI systems.