Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/150342
Title: DEEP VISUAL SCENE UNDERSTANDING: CLASSIFICATION, SEGMENTATION AND PREDICTION
Authors: JIN XIAOJIE
Keywords: Scene understanding,deep learning,classification,segmentation,prediction
Issue Date: 20-Jul-2018
Citation: JIN XIAOJIE (2018-07-20). DEEP VISUAL SCENE UNDERSTANDING: CLASSIFICATION, SEGMENTATION AND PREDICTION. ScholarBank@NUS Repository.
Abstract: Scene understanding including scene classification, scene parsing, prediction in the future scenes, etc., has attracted intense interests in both academia and industry. Traditional works are based on hand-crafted features followed by simple classifiers which have limited learning capabilities. In recent year, deep learning methods have achieved state-of-the-art results in various sub-areas in computer vision and machine learning. However, there is only a few work focusing on solving scene understanding problems by employing deep learning methods. This thesis introduces systematic deep learning based methods towards robust and efficient scene understanding. Specifically, this thesis focuses on three challenging and interrelated tasks in scene understanding, including (1) traditional scene understanding tasks, such as scene and object classification, image and video scene parsing, (2) higher level scene understanding tasks such as predicting rich information in future scenes and (3) deep model compression and acceleration to deploy deep models in practical computational resources constrained devices.
URI: http://scholarbank.nus.edu.sg/handle/10635/150342
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
JinXJ.pdf6.81 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

28
checked on Jul 10, 2020

Download(s)

32
checked on Jul 10, 2020

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.