Automatically Detecting Bystanders in Photos to Reduce Privacy Risks
Offered By: IEEE via YouTube
Course Description
Overview
Learn about an innovative approach to protect bystander privacy in photographs taken in public spaces. Explore a 16-minute IEEE conference talk that delves into the challenges posed by unintentional capture of individuals in photos and the potential privacy risks associated with online sharing and advanced computer vision technologies. Discover how researchers are developing methods to automatically identify bystanders in images using visual information, without requiring proactive measures from individuals. Examine the study's methodology, including an online user survey to understand human classification of subjects and bystanders, and the development of classifier models based on intuitive concepts. Gain insights into the model's performance, achieving high detection accuracy across different datasets, and its potential implications for enhancing privacy protection in the digital age.
Syllabus
Automatically Detecting Bystanders in Photos to Reduce Privacy Risks
Taught by
IEEE Symposium on Security and Privacy
Tags
Related Courses
Introduction to Artificial IntelligenceStanford University via Udacity Natural Language Processing
Columbia University via Coursera Probabilistic Graphical Models 1: Representation
Stanford University via Coursera Computer Vision: The Fundamentals
University of California, Berkeley via Coursera Learning from Data (Introductory Machine Learning course)
California Institute of Technology via Independent