東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Robust Data Representations for Visu...

Li, Sheng.

FindBook

Google Book

Amazon

博客來

Robust Data Representations for Visual Learning.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Robust Data Representations for Visual Learning./
作者:	Li, Sheng.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2017,
面頁冊數:	158 p.
附註:	Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.
Contained By:	Dissertation Abstracts International78-10B(E).
標題:	Computer engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10275665
ISBN:	9781369806588

Robust Data Representations for Visual Learning.
Li, Sheng.

Robust Data Representations for Visual Learning. - Ann Arbor : ProQuest Dissertations & Theses, 2017 - 158 p.

Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.

Thesis (Ph.D.)--Northeastern University, 2017.

Extracting informative representations from data is a critical task in visual learning applications, which mitigates the gap between low-level observed data and high-level semantic knowledge. Many traditional visual learning algorithms pose strong assumptions on the underlying distribution of data. In practice, however, the data might be corrupted, contaminated with severe noise, or captured by different types of sensors, which violates these assumptions. As a result, it is of great importance to learn robust data representations that could effectively and efficiently handle the noisy visual data.

ISBN: 9781369806588Subjects--Topical Terms:

621879
Computer engineering.

Robust Data Representations for Visual Learning.
LDR:03962nmm a2200349 4500 001 2161307
005 20180823122925.5
008 190424s2017 ||||||||||||||||| ||eng d
020 $a 9781369806588
035 $a (MiAaPQ)AAI10275665
035 $a (MiAaPQ)coe.neu:10848
035 $a AAI10275665
040 $a MiAaPQ $c MiAaPQ
100 1 $a Li, Sheng. $3 1035681
245 1 0 $a Robust Data Representations for Visual Learning.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2017
300 $a 158 p.
500 $a Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.
500 $a Adviser: Yun Fu.
502 $a Thesis (Ph.D.)--Northeastern University, 2017.
520 $a Extracting informative representations from data is a critical task in visual learning applications, which mitigates the gap between low-level observed data and high-level semantic knowledge. Many traditional visual learning algorithms pose strong assumptions on the underlying distribution of data. In practice, however, the data might be corrupted, contaminated with severe noise, or captured by different types of sensors, which violates these assumptions. As a result, it is of great importance to learn robust data representations that could effectively and efficiently handle the noisy visual data.
520 $a Recent advances on low-rank and sparse modeling have shown promising performance on recovering clean data from noisy observations, which motivate us to develop new models for robust visual learning. This dissertation focuses on extracting mid-level feature representations from visual data such as images and videos. The research goals of this dissertation are twofold: (1) learning robust data representations from visual data, by exploiting the low-dimensional subspace structures; (2) evaluating the performance of the learned data representations on various analytics tasks of images and videos.
520 $a Three types of data representations are studied in this dissertation, including graph, subspace, and dictionary. First, two novel graph construction schemes are proposed, by integrating the low-rank modeling with graph sparsification strategies. Each sample is represented in the low-rank coding space. And it is revealed that the similarity measurement in the low-rank coding space is more robust than that in the original sample space. The proposed graphs could greatly enhance the performance of graph based clustering and semi-supervised classification. Second, low-dimensional discriminative subspaces are learned in single-view and multi-view scenarios, respectively. The single-view robust subspace discovery model is motivated from low-rank modeling and Fisher criterion, and it is able to accurately classify the noisy images. The multi-view subspace learning model is designed for extracting compact features from multimodal time series data, which leverages a shared latent space and fuses information from multiple data views. Third, dictionary serves as expressive bases for characterizing visual data. A non-negative dictionary with Laplacian regularization is learned to extract robust features from human motion videos, which leads to promising motion segmentation results. In addition, a robust dictionary learning method is designed to transfer knowledge from source domain to a target domain with limited training samples.
520 $a In summary, this dissertation aims to address the challenges in processing noisy visual data captured in real world. The proposed robust data representations have shown promising performance in a wide range of visual learning tasks, such as image clustering, face recognition, human motion segmentation, and multimodal classification.
590 $a School code: 0160.
650 4 $a Computer engineering. $3 621879
650 4 $a Computer science. $3 523869
650 4 $a Educational technology. $3 517670
690 $a 0464
690 $a 0984
690 $a 0710
710 2 $a Northeastern University. $b Electrical and Computer Engineering. $3 1018491
773 0 $t Dissertation Abstracts International $g 78-10B(E).
790 $a 0160
791 $a Ph.D.
792 $a 2017
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10275665