Sciweavers

8099 search results - page 1175 / 1620
» Higher-Order Task Models
Sort
View
205
Voted
IJCV
2006
161views more  IJCV 2006»
15 years 6 months ago
Discriminative Random Fields
In this research we address the problem of classification and labeling of regions given a single static natural image. Natural images exhibit strong spatial dependencies, and mode...
Sanjiv Kumar, Martial Hebert
235
Voted
JMLR
2008
230views more  JMLR 2008»
15 years 6 months ago
Exponentiated Gradient Algorithms for Conditional Random Fields and Max-Margin Markov Networks
Log-linear and maximum-margin models are two commonly-used methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of...
Michael Collins, Amir Globerson, Terry Koo, Xavier...
MMS
2006
15 years 6 months ago
View-invariant motion trajectory-based activity classification and recognition
Motion trajectories provide rich spatio-temporal information about an object's activity. The trajectory information can be obtained using a tracking algorithm on data streams ...
Faisal I. Bashir, Ashfaq A. Khokhar, Dan Schonfeld
196
Voted
TIP
2008
169views more  TIP 2008»
15 years 6 months ago
Weakly Supervised Learning of a Classifier for Unusual Event Detection
In this paper, we present an automatic classification framework combining appearance based features and Hidden Markov Models (HMM) to detect unusual events in image sequences. One...
Mark Jager, Christian Knoll, Fred A. Hamprecht
DEDS
2002
119views more  DEDS 2002»
15 years 6 months ago
Diagnosing Discrete-Event Systems: Extending the "Diagnoser Approach" to Deal with Telecommunication Networks
Abstract. Detection and isolation of failures in large and complex systems such as telecommunication networks are crucial and challenging tasks. The problem considered here is that...
Laurence Rozé, Marie-Odile Cordier
« Prev « First page 1175 / 1620 Last » Next »