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

Human Activity Analysis using Multi-...

Zhang, Chenyang.

FindBook

Google Book

Amazon

博客來

Human Activity Analysis using Multi-modalities and Deep Learning.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Human Activity Analysis using Multi-modalities and Deep Learning./
作者:	Zhang, Chenyang.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2016,
面頁冊數:	115 p.
附註:	Source: Dissertation Abstracts International, Volume: 78-04(E), Section: B.
Contained By:	Dissertation Abstracts International78-04B(E).
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10159927
ISBN:	9781369148558

Human Activity Analysis using Multi-modalities and Deep Learning.
Zhang, Chenyang.

Human Activity Analysis using Multi-modalities and Deep Learning. - Ann Arbor : ProQuest Dissertations & Theses, 2016 - 115 p.

Source: Dissertation Abstracts International, Volume: 78-04(E), Section: B.

Thesis (Ph.D.)--The City College of New York, 2016.

With the successful development of video recording devices and sharing platforms, visual media has become a significant component of everyone's life in the world. To better organize and understand the tremendous amount of visual data, computer vision and machine learning have become the key technologies to resolve such a huge problem. Among the topics in computer vision research, human activity analysis is one of the most challenging and promising areas. Human activity analysis is dedicated to detecting, recognizing, and understanding the context and meaning of human activities in visual media. This dissertation focuses on two aspects in human activity analysis: 1) how to utilize multi-modality approach, including depth sensors and traditional RGB cameras, for human action modeling. 2) How to utilize more advanced machine learning technologies, such as deep learning and sparse coding, to address more sophisticated problems such as attribute learning and automatic video captioning.

ISBN: 9781369148558Subjects--Topical Terms:

523869
Computer science.

Human Activity Analysis using Multi-modalities and Deep Learning.
LDR:02902nmm a2200301 4500 001 2160731
005 20180727125211.5
008 190424s2016 ||||||||||||||||| ||eng d
020 $a 9781369148558
035 $a (MiAaPQ)AAI10159927
035 $a (MiAaPQ)ccny.cuny:10107
035 $a AAI10159927
040 $a MiAaPQ $c MiAaPQ
100 1 $a Zhang, Chenyang. $3 3348665
245 1 0 $a Human Activity Analysis using Multi-modalities and Deep Learning.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2016
300 $a 115 p.
500 $a Source: Dissertation Abstracts International, Volume: 78-04(E), Section: B.
500 $a Adviser: Yingli Tian.
502 $a Thesis (Ph.D.)--The City College of New York, 2016.
520 $a With the successful development of video recording devices and sharing platforms, visual media has become a significant component of everyone's life in the world. To better organize and understand the tremendous amount of visual data, computer vision and machine learning have become the key technologies to resolve such a huge problem. Among the topics in computer vision research, human activity analysis is one of the most challenging and promising areas. Human activity analysis is dedicated to detecting, recognizing, and understanding the context and meaning of human activities in visual media. This dissertation focuses on two aspects in human activity analysis: 1) how to utilize multi-modality approach, including depth sensors and traditional RGB cameras, for human action modeling. 2) How to utilize more advanced machine learning technologies, such as deep learning and sparse coding, to address more sophisticated problems such as attribute learning and automatic video captioning.
520 $a To explore the utilization of the depth cameras, we first present a depth camera-based image descriptor called histogram of 3D facets (H3DF) and its utilization in human action and hand gesture recognition and a holistic depth video representation for human actions. To unify both the inputs from depth cameras and RGB cameras, this dissertation first discusses a joint framework to model human affections from both facial expressions and body gestures with a multi-modality fusion framework. Then we present deep learning-based frameworks for human attribute learning and automatic video captioning tasks. Compared to human action detection recognition, automatic video captioning is more challenging because it includes complex language models and visual context. Extensive experiments have also been conducted on several public datasets to demonstrate that our proposed frameworks in this dissertation outperform the state-of-the-art approaches in this research area.
590 $a School code: 1606.
650 4 $a Computer science. $3 523869
690 $a 0984
710 2 $a The City College of New York. $b Electrical Engineering. $3 2095374
773 0 $t Dissertation Abstracts International $g 78-04B(E).
790 $a 1606
791 $a Ph.D.
792 $a 2016
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10159927