Sciweavers

275 search results - page 5 / 55
» Learning equivalent action choices from demonstration
Sort
View
SCIA
2005
Springer
211views Image Analysis» more  SCIA 2005»
15 years 3 months ago
Perception-Action Based Object Detection from Local Descriptor Combination and Reinforcement Learning
This work proposes to learn visual encodings of attention patterns that enables sequential attention for object detection in real world environments. The system embeds a saccadic d...
Lucas Paletta, Gerald Fritz, Christin Seifert

Publication
200views
13 years 5 months ago
Learning Tags from Unsegmented Videos of Multiple Human Actions
Providing methods to support semantic interaction with growing volumes of video data is an increasingly important challenge for data mining. To this end, there has been some succes...
Timothy Hospedales, Shaogang Gong, Tao Xiang
LICS
2010
IEEE
14 years 8 months ago
Weak Equivalences in Psi-Calculi
Psi-calculi extend the pi-calculus with nominal datatypes to represent data, communication channels, and logics for facts and conditions. This general framework admits highly expr...
Magnus Johansson, Jesper Bengtson, Joachim Parrow,...
CVPR
2010
IEEE
15 years 3 months ago
Recognizing Human Actions from Still Images with Latent Poses
We consider the problem of recognizing human actions from still images. We propose a novel approach that treats the pose of the person in the image as latent variables that will h...
Weilong Yang, Yang Wang, Greg Mori
WSDM
2012
ACM
214views Data Mining» more  WSDM 2012»
13 years 5 months ago
Selecting actions for resource-bounded information extraction using reinforcement learning
Given a database with missing or uncertain content, our goal is to correct and fill the database by extracting specific information from a large corpus such as the Web, and to d...
Pallika H. Kanani, Andrew K. McCallum