Sciweavers

986 search results - page 122 / 198
» Zero-data Learning of New Tasks
Sort
View
TOG
2012
193views Communications» more  TOG 2012»
13 years 11 days ago
Continuous character control with low-dimensional embeddings
Interactive, task-guided character controllers must be agile and responsive to user input, while retaining the flexibility to be readily authored and modified by the designer. C...
Sergey Levine, Jack M. Wang, Alexis Haraux, Zoran ...
CVPR
2012
IEEE
13 years 10 days ago
Scalable k-NN graph construction for visual descriptors
The k-NN graph has played a central role in increasingly popular data-driven techniques for various learning and vision tasks; yet, finding an efficient and effective way to con...
Jing Wang, Jingdong Wang, Gang Zeng, Zhuowen Tu, R...
CVPR
2009
IEEE
16 years 5 months ago
Learning Optimized MAP Estimates in Continuously-Valued MRF Models
We present a new approach for the discriminative training of continuous-valued Markov Random Field (MRF) model parameters. In our approach we train the MRF model by optimizing t...
Kegan G. G. Samuel, Marshall F. Tappen
ECCV
2006
Springer
15 years 11 months ago
A Learning Based Approach for 3D Segmentation and Colon Detagging
Abstract. Foreground and background segmentation is a typical problem in computer vision and medical imaging. In this paper, we propose a new learning based approach for 3D segment...
Zhuowen Tu, Xiang Zhou, Dorin Comaniciu, Luca Bogo...
ETRA
2010
ACM
176views Biometrics» more  ETRA 2010»
15 years 4 months ago
Learning relevant eye movement feature spaces across users
In this paper we predict the relevance of images based on a lowdimensional feature space found using several users’ eye movements. Each user is given an image-based search task,...
Zakria Hussain, Kitsuchart Pasupa, John Shawe-Tayl...