Can I read Classroom Action Recognition Based On Graph Convolutional Neural Networks and Contrast Learning on EtoBox?

Classroom Action Recognition Based On Graph Convolutional Neural Networks and Contrast Learning by 03Nguyễn Du is a document available to read on EtoBox.

What is Classroom Action Recognition Based On Graph Convolutional Neural Networks and Contrast Learning about?

This document presents a novel action recognition model for classroom environments, utilizing Graph Convolutional Neural Networks (GCNs) and contrastive learning techniques to improve the accuracy of recognizing student actions based on skeleton data. The authors introduce the Student Classroom Skeleton (SCS) dataset, which consists of sequences of skeletons extracted from classroom videos, achieving a recognition accuracy of 95.95%. The proposed model addresses challenges associated with traditional image

Author

03Nguyễn Du

Language

EN