Sciweavers

2934 search results - page 566 / 587
» Hypothesis Spaces for Learning
Sort
View
TMM
2010
270views Management» more  TMM 2010»
13 years 2 months ago
Sequence Multi-Labeling: A Unified Video Annotation Scheme With Spatial and Temporal Context
Abstract--Automatic video annotation is a challenging yet important problem for content-based video indexing and retrieval. In most existing works, annotation is formulated as a mu...
Yuanning Li, YongHong Tian, Ling-Yu Duan, Jingjing...
ICCV
2011
IEEE
12 years 7 months ago
Struck: Structured Output Tracking with Kernels
Adaptive tracking-by-detection methods are widely used in computer vision for tracking arbitrary objects. Current approaches treat the tracking problem as a classification task a...
Sam Hare, Amir Saffari, Philip H.S. Torr
KDD
2012
ACM
178views Data Mining» more  KDD 2012»
11 years 9 months ago
Mining emerging patterns by streaming feature selection
Building an accurate emerging pattern classifier with a highdimensional dataset is a challenging issue. The problem becomes even more difficult if the whole feature space is unava...
Kui Yu, Wei Ding 0003, Dan A. Simovici, Xindong Wu
CVPR
2005
IEEE
14 years 9 months ago
Bi-Layer Segmentation of Binocular Stereo Video
This paper describes two algorithms capable of real-time segmentation of foreground from background layers in stereo video sequences. Automatic separation of layers from colour/co...
Vladimir Kolmogorov, Antonio Criminisi, Andrew Bla...
CVPR
2007
IEEE
14 years 9 months ago
Combining Static Classifiers and Class Syntax Models for Logical Entity Recognition in Scanned Historical Documents
Class syntax can be used to 1) model temporal or locational evolvement of class labels of feature observation sequences, 2) correct classification errors of static classifiers if ...
Song Mao, Praveer Mansukhani, George R. Thoma