Region-oriented convolutional networks for object retrieval
Visualitza/Obre
Estadístiques de LA Referencia / Recolecta
Inclou dades d'ús des de 2022
Cita com:
hdl:2117/88650
Tipus de documentTreball Final de Grau
Data2015-06-17
Condicions d'accésAccés obert
Llevat que s'hi indiqui el contrari, els
continguts d'aquesta obra estan subjectes a la llicència de Creative Commons
:
Reconeixement-NoComercial-SenseObraDerivada 3.0 Genèrica
Abstract
This thesis is framed in the computer vision eld, addressing a challenge related
to instance search. Instance search consists in searching for occurrences of a
certain visual instance on a large collection of visual content, and generating a
ranked list of results sorted according to their relevance to a user query. This
thesis builds up on existing work presented at the TRECVID Instance Search
Task in 2014, and explores the use of local deep learning features extracted from
object proposals. The performance of di erent deep learning architectures (at
both global and local scales) is evaluated, and a thorough comparison of them
is performed. Secondly, this thesis presents the guidelines to follow in order to
ne-tune a convolutional neural network for tasks such as image classi cation,
object detection and semantic segmentation. It does so with the nal purpose
of ne tuning SDS, a CNN trained for both object detection and semantic
segmentation, with the recently released Microsoft COCO dataset.
MatèriesComputer vision, Remote sensing, Databases, Visió per ordinador, Teledetecció, Bases de dades
TitulacióGRAU EN ENGINYERIA DE SISTEMES AUDIOVISUALS (Pla 2009)
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
eduard.fontdevila_110600.pdf | 8,018Mb | Visualitza/Obre |