Sciweavers

1585 search results - page 83 / 317
» Using a Non-prior Training Active Feature Model
Sort
View
CVIU
2006
317views more  CVIU 2006»
15 years 6 months ago
A general method for human activity recognition in video
In this paper we develop a system for human behaviour recognition in video sequences. Human behaviour is modelled as a stochastic sequence of actions. Actions are described by a f...
Neil Robertson, Ian D. Reid
ACL
2011
14 years 9 months ago
Jointly Learning to Extract and Compress
We learn a joint model of sentence extraction and compression for multi-document summarization. Our model scores candidate summaries according to a combined linear model whose fea...
Taylor Berg-Kirkpatrick, Dan Gillick, Dan Klein
IJCV
2008
191views more  IJCV 2008»
15 years 6 months ago
Searching for Complex Human Activities with No Visual Examples
Abstract We describe a method of representing human activities that allows a collection of motions to be queried without examples, using a simple and effective query language. Our ...
Nazli Ikizler, David A. Forsyth
AUSDM
2006
Springer
144views Data Mining» more  AUSDM 2006»
15 years 10 months ago
A Characterization of Wordnet Features in Boolean Models For Text Classification
Supervised text classification is the task of automatically assigning a category label to a previously unlabeled text document. We start with a collection of pre-labeled examples ...
Trevor N. Mansuy, Robert J. Hilderman
ICPR
2000
IEEE
15 years 10 months ago
Probabilistic Saliency Approach for Elongated Structure Detection Using Deformable Models
In this paper we address the object recognition problem in a probabilistic framework to detect and describe object appearance through image features organized by means of active c...
Xavier Orriols, Ricardo Toledo, Xavier Binefa, Pet...