Sciweavers

135 search results - page 24 / 27
» How to Improve a Handwriting Recognition System
Sort
View
CVPR
2011
IEEE
13 years 3 months ago
Large-Scale Live Active Learning: Training Object Detectors with Crawled Data and Crowds
Active learning and crowdsourcing are promising ways to efficiently build up training sets for object recognition, but thus far techniques are tested in artificially controlled ...
Sudheendra Vijayanarasimhan, Kristen Grauman
PERVASIVE
2006
Springer
13 years 6 months ago
Building Reliable Activity Models Using Hierarchical Shrinkage and Mined Ontology
Abstract. Activity inference based on object use has received considerable recent attention. Such inference requires statistical models that map activities to the objects used in p...
Emmanuel Munguia Tapia, Tanzeem Choudhury, Matthai...
ICDM
2009
IEEE
233views Data Mining» more  ICDM 2009»
14 years 1 months ago
Semi-Supervised Sequence Labeling with Self-Learned Features
—Typical information extraction (IE) systems can be seen as tasks assigning labels to words in a natural language sequence. The performance is restricted by the availability of l...
Yanjun Qi, Pavel Kuksa, Ronan Collobert, Kunihiko ...
PAA
2006
13 years 6 months ago
Audio-visual sports highlights extraction using Coupled Hidden Markov Models
We present our studies on the application of Coupled Hidden Markov Models(CHMMs) to sports highlights extraction from broadcast video using both audio and video information. First,...
Ziyou Xiong
CVPR
2010
IEEE
14 years 3 months ago
Moving Vistas: Exploiting Motion for Describing Scenes
Scene recognition in an unconstrained setting is an open and challenging problem with wide applications. In this paper, we study the role of scene dynamics for improved representa...
Nitesh Shroff, Pavan Turaga, Rama Chellappa