Sciweavers

236 search results - page 24 / 48
» Confidence-based policy learning from demonstration using Ga...
Sort
View
NIPS
1996
13 years 10 months ago
Continuous Sigmoidal Belief Networks Trained using Slice Sampling
Real-valued random hidden variables can be useful for modelling latent structure that explains correlations among observed variables. I propose a simple unit that adds zero-mean G...
Brendan J. Frey
ICML
2010
IEEE
13 years 9 months ago
Gaussian Processes Multiple Instance Learning
This paper proposes a multiple instance learning (MIL) algorithm for Gaussian processes (GP). The GP-MIL model inherits two crucial benefits from GP: (i) a principle manner of lea...
Minyoung Kim, Fernando De la Torre
ECCV
2008
Springer
14 years 10 months ago
Estimating 3D Face Model and Facial Deformation from a Single Image Based on Expression Manifold Optimization
Facial expression modeling is central to facial expression recognition and expression synthesis for facial animation. Previous works reported that modeling the facial expression wi...
Shu-Fan Wang, Shang-Hong Lai
ICMCS
2006
IEEE
174views Multimedia» more  ICMCS 2006»
14 years 2 months ago
Web Image Mining Based on Modeling Concept-Sensitive Salient Regions
In this paper, we propose a probabilistic model for web image mining, which is based on concept-sensitive salient regions without human intervene. Our goal is to achieve a middle-...
Jing Liu, Qingshan Liu, Jinqiao Wang, Hanqing Lu, ...
ICIP
2007
IEEE
14 years 10 months ago
Monocular Tracking 3D People By Gaussian Process Spatio-Temporal Variable Model
Tracking 3D people from monocular video is often poorly constrained. To mitigate this problem, prior knowledge should be exploited. In this paper, the Gaussian process spatio-temp...
Junbiao Pang, Laiyun Qing, Qingming Huang, Shuqian...