Human Activity Recognition - Learning with Less Labels and Privacy Preservation
Offered By: University of Central Florida via YouTube
Course Description
Overview
Explore cutting-edge approaches to Human Activity Recognition in this keynote talk from SPIE Automatic Target Recognition XXXII. Delve into innovative techniques for learning with limited labeled data and preserving privacy. Examine problem statements, results, and various approaches including privacy leakage prevention, pseudoleveling, and contrastive learning. Discover the potential of Zero Shot Learning and Local Local Contrast Loss in this field. Analyze experimental and qualitative results from cell surveys, gaining valuable insights into the future of activity recognition technology.
Syllabus
Intro
Problem Statement
Results
Problem
Approaches
Privacy leakage
Pseudoleveling
Contrasting
Local Local Contrast Loss
Zero Shot Learning
Evaluation
Cell Survey
Experimental Results
Qualitative Results
Taught by
UCF CRCV
Tags
Related Courses
Amazon SageMaker: Build an Object Detection Model Using Images Labeled with Ground Truth (German)Amazon Web Services via AWS Skill Builder Amazon SageMaker: creación de un modelo de detección de objetos utilizando imágenes etiquetadas con Ground Truth (Español de España) | Amazon SageMaker: Build an Object Detection Model Using Images Labeled with Ground Truth (Spanish from Spain)
Amazon Web Services via AWS Skill Builder Uptraining with Document AI Workbench
Google Cloud via Coursera Employing Best Practices for Improving the Usability of LookML Projects
Google via Google Cloud Skills Boost Agent Summarization (Custom)
Google via Google Cloud Skills Boost