Sciweavers

868 search results - page 16 / 174
» Learning Object Representations Using Sequential Patterns
Sort
View
ECCV
2006
Springer
14 years 9 months ago
Tracking Objects Across Cameras by Incrementally Learning Inter-camera Colour Calibration and Patterns of Activity
This paper presents a scalable solution to the problem of tracking objects across spatially separated, uncalibrated, non-overlapping cameras. Unlike other approaches this technique...
Andrew Gilbert, Richard Bowden
IROS
2008
IEEE
132views Robotics» more  IROS 2008»
14 years 1 months ago
Digital representation of everyday objects in a robot ecology via proxies
Abstract— Robotic middlewares increasingly allow the seamless integration of multiple heterogeneous robots into one distributed system. Unfortunately, very simple devices like ta...
Md. Jayedur Rashid, Mathias Broxvall, Alessandro S...
TSP
2008
167views more  TSP 2008»
13 years 6 months ago
Multi-Task Learning for Analyzing and Sorting Large Databases of Sequential Data
A new hierarchical nonparametric Bayesian framework is proposed for the problem of multi-task learning (MTL) with sequential data. The models for multiple tasks, each characterize...
Kai Ni, John William Paisley, Lawrence Carin, Davi...
KDD
2005
ACM
153views Data Mining» more  KDD 2005»
14 years 8 months ago
Improving discriminative sequential learning with rare--but--important associations
Discriminative sequential learning models like Conditional Random Fields (CRFs) have achieved significant success in several areas such as natural language processing, information...
Xuan Hieu Phan, Minh Le Nguyen, Tu Bao Ho, Susumu ...
ICPR
2008
IEEE
14 years 8 months ago
Detecting global motion patterns in complex videos
Learning dominant motion patterns or activities from a video is an important surveillance problem, especially in crowded environments like markets, subways etc., where tracking of...
Min Hu, Mubarak Shah, Saad Ali