Please use this identifier to cite or link to this item:
Title: Using deep learning for fine-grained action segmentation
Author: Yuste Ramos, Joaquim
Director/Tutor: Clapés, Albert
Escalera Guerrero, Sergio
Keywords: Aprenentatge automàtic
Visió per ordinador
Treballs de fi de grau
Xarxes neuronals convolucionals
Reconeixement de formes (Informàtica)
Xarxes neuronals (Informàtica)
Machine learning
Computer vision
Computer software
Convolutional neural networks
Pattern recognition systems
Bachelor's theses
Neural networks (Computer science)
Issue Date: 20-Jun-2021
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.
Note: Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2021, Director: Albert Clapés i Sergio Escalera Guerrero
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