Sciweavers

8676 search results - page 257 / 1736
» A Feature Model for an IDE4OCL
Sort
View
ECCV
2010
Springer
15 years 12 months ago
Tracklet Descriptors  for Action Modeling and Video Analysis
We present spatio-temporal feature descriptors that can be inferred from video and used as building blocks in action recognition systems. They capture the evolution of ``elementar...
Michalis Raptis , Stefano Soatto
FSKD
2006
Springer
190views Fuzzy Logic» more  FSKD 2006»
15 years 10 months ago
A Maximum Entropy Model Based Answer Extraction for Chinese Question Answering
We regard answer extraction of Question Answering (QA) system as a classification problem, classifying answer candidate sentences into positive or negative. To confirm the feasibil...
Ang Sun, Minghu Jiang, Yanjun Ma
MVA
1996
109views Computer Vision» more  MVA 1996»
15 years 7 months ago
Model Based Tracking on 3D Objects
In this paper, a new tracking algorithm, based on local minimum energy, is proposed for matching between a projected model and corresponding image features in real-time. The algor...
Zheng Li, Han Wang
TCSV
2010
15 years 1 months ago
Image and Video Segmentation by Combining Unsupervised Generalized Gaussian Mixture Modeling and Feature Selection
In this letter, we propose a clustering model that efficiently mitigates image and video under/over-segmentation by combining generalized Gaussian mixture modeling and feature sele...
Mohand Saïd Allili, Djemel Ziou, Nizar Bougui...
JMLR
2010
104views more  JMLR 2010»
15 years 1 months ago
Increasing Feature Selection Accuracy for L1 Regularized Linear Models
L1 (also referred to as the 1-norm or Lasso) penalty based formulations have been shown to be effective in problem domains when noisy features are present. However, the L1 penalty...
Abhishek Jaiantilal, Gregory Z. Grudic