Exploring Graph Neural Networks for Video Action Segmentation

A common challenge in computer vision is the applicability of algorithms developed in a controlled dataset to real-world problems, such as unscripted or uncontrolled videos. Graph neural networks (GNNs) have emerged as a promising tool to solve this kind of problem. This master's thesis explore...

ver descrição completa

Detalhes bibliográficos
Autor: Vaccher Gomez, Jordi
Tipo de documento: dissertação
Data de publicação:2023
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositório:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglês
OAI Identifier:oai:upcommons.upc.edu:2117/399778
Acesso em linha:https://hdl.handle.net/2117/399778
Access Level:Acceso aberto
Palavra-chave:Machine learning
Neural networks (Computer science)
Deep learning (Machine learning)
Graph Neural Networks
machine learning
deep learning
action segmentation
video data
Aprenentatge automàtic
Xarxes neuronals (Informàtica)
Aprenentatge profund
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
id ES_a948f608896e6cdca64db21b9b90a21d
oai_identifier_str oai:upcommons.upc.edu:2117/399778
network_acronym_str ES
network_name_str España
repository_id_str
spelling Exploring Graph Neural Networks for Video Action SegmentationVaccher Gomez, JordiMachine learningNeural networks (Computer science)Deep learning (Machine learning)Graph Neural Networksmachine learningdeep learningaction segmentationvideo dataAprenentatge automàticXarxes neuronals (Informàtica)Aprenentatge profundÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificialA common challenge in computer vision is the applicability of algorithms developed in a controlled dataset to real-world problems, such as unscripted or uncontrolled videos. Graph neural networks (GNNs) have emerged as a promising tool to solve this kind of problem. This master's thesis explores the use of graph neural networks for the classification of actions and activities in video data. Specifically, the study focuses on the Breakfast dataset, which features two types of labels: activity labels for each video and action labels for each frame. In this work, we investigate various methods for action and activity classification and propose a novel architecture that employs a graph neural network for unsupervised embedding extraction trained to separate the intra-video action classes, improving the baseline performance. The proposed GNN-based embedding extractor architecture shows the capability of graph-based techniques to improve our comprehension of complex events and actions in video data.Universitat Politècnica de CatalunyaRuiz Hidalgo, JavierDimiccoli, Mariella20232023-05-3020242024-01-18master thesishttp://purl.org/coar/resource_type/c_bdccNAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/2117/399778reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/3997782026-05-27T15:37:01Z
dc.title.none.fl_str_mv Exploring Graph Neural Networks for Video Action Segmentation
title Exploring Graph Neural Networks for Video Action Segmentation
spellingShingle Exploring Graph Neural Networks for Video Action Segmentation
Vaccher Gomez, Jordi
Machine learning
Neural networks (Computer science)
Deep learning (Machine learning)
Graph Neural Networks
machine learning
deep learning
action segmentation
video data
Aprenentatge automàtic
Xarxes neuronals (Informàtica)
Aprenentatge profund
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
title_short Exploring Graph Neural Networks for Video Action Segmentation
title_full Exploring Graph Neural Networks for Video Action Segmentation
title_fullStr Exploring Graph Neural Networks for Video Action Segmentation
title_full_unstemmed Exploring Graph Neural Networks for Video Action Segmentation
title_sort Exploring Graph Neural Networks for Video Action Segmentation
dc.creator.none.fl_str_mv Vaccher Gomez, Jordi
author Vaccher Gomez, Jordi
author_facet Vaccher Gomez, Jordi
author_role author
dc.contributor.none.fl_str_mv Ruiz Hidalgo, Javier
Dimiccoli, Mariella
dc.subject.none.fl_str_mv Machine learning
Neural networks (Computer science)
Deep learning (Machine learning)
Graph Neural Networks
machine learning
deep learning
action segmentation
video data
Aprenentatge automàtic
Xarxes neuronals (Informàtica)
Aprenentatge profund
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
topic Machine learning
Neural networks (Computer science)
Deep learning (Machine learning)
Graph Neural Networks
machine learning
deep learning
action segmentation
video data
Aprenentatge automàtic
Xarxes neuronals (Informàtica)
Aprenentatge profund
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
description A common challenge in computer vision is the applicability of algorithms developed in a controlled dataset to real-world problems, such as unscripted or uncontrolled videos. Graph neural networks (GNNs) have emerged as a promising tool to solve this kind of problem. This master's thesis explores the use of graph neural networks for the classification of actions and activities in video data. Specifically, the study focuses on the Breakfast dataset, which features two types of labels: activity labels for each video and action labels for each frame. In this work, we investigate various methods for action and activity classification and propose a novel architecture that employs a graph neural network for unsupervised embedding extraction trained to separate the intra-video action classes, improving the baseline performance. The proposed GNN-based embedding extractor architecture shows the capability of graph-based techniques to improve our comprehension of complex events and actions in video data.
publishDate 2023
dc.date.none.fl_str_mv 2023
2023-05-30
2024
2024-01-18
dc.type.none.fl_str_mv master thesis
http://purl.org/coar/resource_type/c_bdcc
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/399778
url https://hdl.handle.net/2117/399778
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universitat Politècnica de Catalunya
publisher.none.fl_str_mv Universitat Politècnica de Catalunya
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869416007554039808
score 15.301629

Registros relacionados