Language:
繁體中文
English
日文
說明(常見問題)
南開科技大學
圖書館首頁
編目中圖書申請
登入
回首頁
切換:
標籤
|
MARC模式
|
ISBD
Facing uncertainty: Three-dimension...
~
Marks, Tim Kalman.
Facing uncertainty: Three-dimensional face tracking and learning with generative models.
紀錄類型:
書目-電子資源 : 單行本
正題名/作者:
Facing uncertainty: Three-dimensional face tracking and learning with generative models./
作者:
Marks, Tim Kalman.
面頁冊數:
161 p.
附註:
Source: Dissertation Abstracts International, Volume: 66-11, Section: B, page: 6073.
Contained By:
Dissertation Abstracts International66-11B.
標題:
Computer Science. -
電子資源:
http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3196545
ISBN:
9780542406447
Facing uncertainty: Three-dimensional face tracking and learning with generative models.
Marks, Tim Kalman.
Facing uncertainty: Three-dimensional face tracking and learning with generative models.
- 161 p.
Source: Dissertation Abstracts International, Volume: 66-11, Section: B, page: 6073.
Thesis (Ph.D.)--University of California, San Diego, 2006.
We present a generative graphical model and stochastic filtering algorithm for simultaneous tracking of 3D rigid and nonrigid motion, object texture, and background texture from single-camera video. The inference procedure takes advantage of the conditionally Gaussian nature of the model using Rao-Blackwellized particle filtering, which involves Monte Carlo sampling of the nonlinear component of the process and exact filtering of the linear Gaussian component. The smoothness of image sequences in time and space is exploited using Gauss-Newton optimization and Laplace's method to generate proposal distributions for importance sampling.
ISBN: 9780542406447Subjects--Topical Terms:
1000005419
Computer Science.
Facing uncertainty: Three-dimensional face tracking and learning with generative models.
LDR
:03555nmm 2200337 4500
001
1000004756
005
20061114130255.5
008
061114s2006 eng d
020
$a
9780542406447
035
$a
(UnM)AAI3196545
035
$a
AAI3196545
040
$a
UnM
$c
UnM{me_controlnum}
100
1
$a
Marks, Tim Kalman.
$3
1000005840
245
1 0
$a
Facing uncertainty: Three-dimensional face tracking and learning with generative models.
300
$a
161 p.
500
$a
Source: Dissertation Abstracts International, Volume: 66-11, Section: B, page: 6073.
500
$a
Chairs: James Hollan; Javier Movellan.
502
$a
Thesis (Ph.D.)--University of California, San Diego, 2006.
520
$a
We present a generative graphical model and stochastic filtering algorithm for simultaneous tracking of 3D rigid and nonrigid motion, object texture, and background texture from single-camera video. The inference procedure takes advantage of the conditionally Gaussian nature of the model using Rao-Blackwellized particle filtering, which involves Monte Carlo sampling of the nonlinear component of the process and exact filtering of the linear Gaussian component. The smoothness of image sequences in time and space is exploited using Gauss-Newton optimization and Laplace's method to generate proposal distributions for importance sampling.
520
$a
Our system encompasses an entire continuum from optic flow to template-based tracking, elucidating the conditions under which each method is optimal, and introducing a related family of new tracking algorithms. We demonstrate an application of the system to 3D nonrigid face tracking. We also introduce a new method for collecting ground truth information about the position of facial features while filming an unmarked subject, and introduce a data set created using this technique.
520
$a
We develop a neurally plausible method for learning the models used for 3D face tracking, a method related to learning factorial codes. Factorial representations play a fundamental role in cognitive psychology, computational neuroscience, and machine learning. Independent component analysis pursues a form of factorization proposed by Barlow [1994] as a model for coding in sensory cortex. Morton proposed a different form of factorization that fits a wide variety of perceptual data [Massaro, 1987b]. Recently, Hinton [2002] proposed a new class of models that exhibit yet another form of factorization. Hinton also proposed an objective function, contrastive divergence, that is particularly effective for training models of this class.
520
$a
We analyze factorial codes within the context of diffusion networks, a stochastic version of continuous time, continuous state recurrent neural networks. We demonstrate that a particular class of linear diffusion networks models precisely the same class of observable distributions as factor analysis. This suggests novel nonlinear generalizations of factor analysis and independent component analysis that could be implemented using interactive noisy circuitry. We train diffusion networks on a database of 3D faces by minimizing contrastive divergence, and explain how diffusion networks can learn 3D deformable models from 2D data.
590
$a
School code: 0033.
650
4
$a
Computer Science.
$3
1000005419
650
4
$a
Artificial Intelligence.
$3
165300
650
4
$a
Psychology, Cognitive.
$3
1000005612
690
$a
0984
690
$a
0800
690
$a
0633
710
2 0
$a
University of California, San Diego.
$3
1000005841
773
0
$t
Dissertation Abstracts International
$g
66-11B.
790
1 0
$a
Hollan, James,
$e
advisor
790
1 0
$a
Movellan, Javier,
$e
advisor
790
$a
0033
791
$a
Ph.D.
792
$a
2006
856
4 0
$u
http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3196545
$z
0 筆讀者評論
館藏地:
全部
線上資料庫
出版年:
卷號:
館藏
1 筆 • 頁數 1 •
1
條碼號
典藏地名稱
館藏流通類別
資料類型
索書號
使用類型
借閱狀態
預約人數
備註欄
附件
OE0000731
線上資料庫
線上資源
線上電子書
OE
一般(Normal)
在架
0
1 筆 • 頁數 1 •
1
多媒體
評論
新增評論
分享你的心得
建立或儲存個人書籤
書目轉出
取書館別
處理中
...
變更密碼
登入