Human action recognition using machine learning

The accurate detection of human pose is useful in various areas such as surveillance, clothes parsing and game modelling. While many existing models attempt to breach the gap, they suffer from problems including learning uninformative latent variables and being memory- intensive. In this work, we...

Full description

Saved in:
Bibliographic Details
Main Author: Cao, QingTian
Other Authors: Lin Weisi
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2024
Subjects:
Online Access:https://hdl.handle.net/10356/175048
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-175048
record_format dspace
spelling sg-ntu-dr.10356-1750482024-04-19T15:41:46Z Human action recognition using machine learning Cao, QingTian Lin Weisi School of Computer Science and Engineering WSLin@ntu.edu.sg Computer and Information Science The accurate detection of human pose is useful in various areas such as surveillance, clothes parsing and game modelling. While many existing models attempt to breach the gap, they suffer from problems including learning uninformative latent variables and being memory- intensive. In this work, we propose FFPoser, a diffusion-based model that leverages the use of Fast-Fourier Transformation and a complex-valued neural network to resolve the above issues. It is able to generate fairly realistic poses and produce accurate occlusion recovery results. Additionally, it is easy to train while still be able to learn the important information of the source data. Bachelor's degree 2024-04-19T01:28:19Z 2024-04-19T01:28:19Z 2024 Final Year Project (FYP) Cao, Q. (2024). Human action recognition using machine learning. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/175048 https://hdl.handle.net/10356/175048 en SCSE23-0613 application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Computer and Information Science
spellingShingle Computer and Information Science
Cao, QingTian
Human action recognition using machine learning
description The accurate detection of human pose is useful in various areas such as surveillance, clothes parsing and game modelling. While many existing models attempt to breach the gap, they suffer from problems including learning uninformative latent variables and being memory- intensive. In this work, we propose FFPoser, a diffusion-based model that leverages the use of Fast-Fourier Transformation and a complex-valued neural network to resolve the above issues. It is able to generate fairly realistic poses and produce accurate occlusion recovery results. Additionally, it is easy to train while still be able to learn the important information of the source data.
author2 Lin Weisi
author_facet Lin Weisi
Cao, QingTian
format Final Year Project
author Cao, QingTian
author_sort Cao, QingTian
title Human action recognition using machine learning
title_short Human action recognition using machine learning
title_full Human action recognition using machine learning
title_fullStr Human action recognition using machine learning
title_full_unstemmed Human action recognition using machine learning
title_sort human action recognition using machine learning
publisher Nanyang Technological University
publishDate 2024
url https://hdl.handle.net/10356/175048
_version_ 1814047151958786048