Please use this identifier to cite or link to this item: http://hdl.handle.net/2445/182804
Full metadata record
DC FieldValueLanguage
dc.contributor.advisorClapés, Albert-
dc.contributor.advisorEscalera Guerrero, Sergio-
dc.contributor.authorYuste Ramos, Joaquim-
dc.date.accessioned2022-01-31T10:16:51Z-
dc.date.available2022-01-31T10:16:51Z-
dc.date.issued2021-06-20-
dc.identifier.urihttp://hdl.handle.net/2445/182804-
dc.descriptionTreballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2021, Director: Albert Clapés i Sergio Escalera Guerreroca
dc.description.abstract[en] This project focuses on video action segmentation task, which aims to temporally segment and classify fine-grained actions in untrimmed videos. The development and refinement of this process is an important yet challenging problem, which can provide great improvements in work areas such as robotics, e-Health assistive technologies, surveillance, and beyond. On the one hand, we will study the current state-of-the-art, as well as the metrics that are commonly used to evaluate an architecture on this kind of problems. On the other hand, we introduce two different attention-based modules that are capable of extracting frame-to-frame relationships, and a behaviour analysis will be performed by evaluating them over Georgia Tech Egocentric Activity (GTEA), which is an outstanding dataset. This dataset is focused on daily cooking activity videos, with fine-grained labels, and it has an egocentric point view. Eventually, we will compare the obtained results against the actual state-of-the-art scores, in order to discuss the effectiveness of each module.ca
dc.format.extent45 p.-
dc.format.mimetypeapplication/pdf-
dc.language.isoengca
dc.rightsmemòria: cc-nc-nd (c) Joaquim Yuste Ramos, 2021-
dc.rightscodi: MIT License (c) Joaquim Yuste Ramos, 2021-
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/-
dc.rights.urihttps://opensource.org/licenses/MIT*
dc.sourceTreballs Finals de Grau (TFG) - Enginyeria Informàtica-
dc.subject.classificationAprenentatge automàticca
dc.subject.classificationVisió per ordinadorca
dc.subject.classificationProgramarica
dc.subject.classificationTreballs de fi de grauca
dc.subject.classificationXarxes neuronals convolucionalsca
dc.subject.classificationReconeixement de formes (Informàtica)ca
dc.subject.classificationXarxes neuronals (Informàtica)ca
dc.subject.otherMachine learningen
dc.subject.otherComputer visionen
dc.subject.otherComputer softwareen
dc.subject.otherConvolutional neural networksen
dc.subject.otherPattern recognition systemsen
dc.subject.otherBachelor's thesesen
dc.subject.otherNeural networks (Computer science)en
dc.titleUsing deep learning for fine-grained action segmentationca
dc.typeinfo:eu-repo/semantics/bachelorThesisca
dc.rights.accessRightsinfo:eu-repo/semantics/openAccessca
Appears in Collections:Programari - Treballs de l'alumnat
Treballs Finals de Grau (TFG) - Enginyeria Informàtica

Files in This Item:
File Description SizeFormat 
codi.zipCodi font222.96 MBzipView/Open
tfg_joaquim_yuste_ramos.pdfMemòria2.02 MBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons