Sciweavers

119 search results - page 17 / 24
» A novel method for learning policies from constrained motion
Sort
View
ICRA
2005
IEEE
142views Robotics» more  ICRA 2005»
14 years 1 months ago
A Real-Time Haptic/Graphic Demonstration of how Error Augmentation can Enhance Learning
– We developed a real-time controller for a 2 degree-of-freedom robotic system using xPC Target. This system was used to investigate how different methods of performance error fe...
Yejun Wei, James L. Patton, Preeti Bajaj, Robert S...
CVPR
2011
IEEE
13 years 4 months ago
Auto Directed Video Stabilization with Robust L1 Optimal Camera Paths
We present a novel algorithm for automatically applying constrainable, L1-optimal camera paths to generate stabilized videos by removing undesired motions. Our goal is to compute ...
Matthias Grundmann, Vivek Kwatra, Irfan Essa
ICDM
2006
IEEE
137views Data Mining» more  ICDM 2006»
14 years 1 months ago
Mining Complex Time-Series Data by Learning Markovian Models
In this paper, we propose a novel and general approach for time-series data mining. As an alternative to traditional ways of designing specific algorithm to mine certain kind of ...
Yi Wang, Lizhu Zhou, Jianhua Feng, Jianyong Wang, ...
ICCV
2005
IEEE
14 years 1 months ago
On the Spatial Statistics of Optical Flow
We develop a method for learning the spatial statistics of optical flow fields from a novel training database. Training flow fields are constructed using range images of natur...
Stefan Roth, Michael J. Black
MM
2005
ACM
250views Multimedia» more  MM 2005»
14 years 1 months ago
An object-based video coding framework for video sequences obtained from static cameras
This paper presents a novel object-based video coding framework for videos obtained from a static camera. As opposed to most existing methods, the proposed method does not require...
Asaad Hakeem, Khurram Shafique, Mubarak Shah