Please use this identifier to cite or link to this item:
Title: Learning with Contexts
Keywords: spatial context, web context, machine learning, age estimation, random forest, optimization
Issue Date: 17-Sep-2010
Source: NI BINGBING (2010-09-17). Learning with Contexts. ScholarBank@NUS Repository.
Abstract: Context information has played increasingly a very important role in visual learning tasks. In computer vision research community, various information sources could be referred to as context, which include (but not limited to) semantic context, spatial context, shape context, category context and web context, etc, and they have been successfully applied on visual learning tasks such as face recognition, object and scene classification, activity analysis as well as image based human age estimation. Each of these context types contributes significantly in its own application domain and we mainly focus the studies on image local spatial context as well as web context for the purpose of enhancing visual learning performances in this dissertation. The entire thesis is therefore arranged into two parts. In the first part, we investigate the spatial context, i.e., image local feature spatial context. The conventional methods for image local spatial context modeling are mostly limited by considering only the 2nd-order spatial contexts between image local feature neighbors. Given the fact that the 3rd-order as well as higherorder spatial contexts can convey much richer information and more discriminative capability, a theoretical way for modeling higher-order spatial contexts is therefore demanded. To address this problem, we first propose a contextualizing histogram framework, which is capable of encoding the 3rd-order spatial and spatial-temporal contexts by convoluting a set of ternary structure local homogeneity distributions with the histogram-bin index images/videos. Then, motivated by the recent success of random forest in leaning discriminative visual codebook, we present a Spatialized Random Forest (SRF) approach, which is further capable of encoding unlimited high-order local spatial contexts. Extensive experimental results on various visual learning tasks including face recognition, object and scene classification, activity analysis well demonstrate the discriminating power achieved by encoding 3rd-order and even high-order image local spatial contexts. We then study the web context in the second part. Given the observation that millions of images (videos) which contain human faces as well as weak age label information are online available, we investigate the possibility of incorporating this type of web context for building a universal and robust human age estimator, which is applicable to all gender, age and ethnic groups as well as various image qualities. Towards this end, an automatic image and video crawling, face detection, noise removal and robust age estimator training pipeline is proposed. This automatically derived human age estimator is extensively evaluated on three popular benchmark human aging databases, and without taking any images from these benchmark databases as training samples, comparable age estimation accuracies with the stateof- the-art results are achieved, which demonstrates that web context could serve as a very important resource for tackling practical real-world applications such as universal age estimation.
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
NiBB.pdf10.45 MBAdobe PDF



Page view(s)

checked on Dec 11, 2017


checked on Dec 11, 2017

Google ScholarTM


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