Sciweavers

505 search results - page 99 / 101
» Building text features for object image classification
Sort
View
ICCV
2009
IEEE
14 years 7 months ago
Selection and context for action recognition
Recognizing human action in non-instrumented video is a challenging task not only because of the variability produced by general scene factors like illumination, background, occlu...
Dong Han, Liefeng Bo, Cristian Sminchisescu
SIAMIS
2010
102views more  SIAMIS 2010»
14 years 4 months ago
Cross Correlation and Deconvolution of Noise Signals in Randomly Layered Media
It is known that cross correlation of waves generated by noise sources, propagating in an unknown medium, and recorded by a sensor array, can provide information about the medium. ...
Josselin Garnier, Knut Sølna
ACCV
2010
Springer
14 years 4 months ago
A Unified Approach to Segmentation and Categorization of Dynamic Textures
Dynamic textures (DT) are videos of non-rigid dynamical objects, such as fire and waves, which constantly change their shape and appearance over time. Most of the prior work on DT ...
Avinash Ravichandran, Paolo Favaro, René Vi...
BMCBI
2011
14 years 1 months ago
To aggregate or not to aggregate high-dimensional classifiers
Background: High-throughput functional genomics technologies generate large amount of data with hundreds or thousands of measurements per sample. The number of sample is usually m...
Cheng-Jian Xu, Huub C. J. Hoefsloot, Age K. Smilde
VLSISP
2010
106views more  VLSISP 2010»
14 years 8 months ago
A Multi-Pronged Approach to Improving Semantic Extraction of News Video
In this paper we describe a multi-strategy approach to improving semantic extraction from news video. Experiments show the value of careful parameter tuning, exploiting multiple fe...
Alexander G. Hauptmann, Ming-yu Chen, Michael G. C...