Efficient Spatio-temporal feature extraction for human action recognition

Efficient Spatio-temporal feature extraction for human action recognition

This thesis is submitted in partial fulfilment of the requirements for the degree of Master of Engineering in Computer Science and Engineering, 2021.

Bibliografski detalji
Glavni autor: Ghosh, Dipon Kumar
Daljnji autori: Chakrabarty, Amitabha
Format: Disertacija
Jezik:English
Izdano: Brac University 2022
Teme:
Human action recognition (HAR)
Surveillance systems
Violence detection
Skeleton-based human action recognition
Convolutional neural network (CNN)
Graph convolutional networks (GCN)
Feature fusion
Human activity recognition
Neural network (Computer Science)
Online pristup:http://hdl.handle.net/10361/15946

Internet

http://hdl.handle.net/10361/15946

Similar Items