Sciweavers

123 search results - page 8 / 25
» Joint optimization of segmentation and appearance models
Sort
View
CVPR
2008
IEEE
14 years 9 months ago
Discriminative human action segmentation and recognition using semi-Markov model
Given an input video sequence of one person conducting a sequence of continuous actions, we consider the problem of jointly segmenting and recognizing actions. We propose a discri...
Qinfeng Shi, Li Wang, Li Cheng, Alexander J. Smola
BMVC
2010
13 years 4 months ago
StyP-Boost: A Bilinear Boosting Algorithm for Learning Style-Parameterized Classifiers
We introduce a novel bilinear boosting algorithm, which extends the multi-class boosting framework of JointBoost to optimize a bilinear objective function. This allows style param...
Jonathan Warrell, Philip H. S. Torr, Simon Prince
CVPR
2000
IEEE
14 years 9 months ago
Dynamic Layer Representation with Applications to Tracking
A dynamic layer representation is proposed in this paper for tracking moving objects. Previous work on layered representations has largely concentrated on two-/multiframe batch fo...
Hai Tao, Harpreet S. Sawhney, Rakesh Kumar
ICASSP
2011
IEEE
12 years 11 months ago
Contour-based hidden Markov model to segment 2D ultrasound images
The segmentation of ultrasound images is challenging due to the difficulty of appropriate modeling of their appearance variations including speckle as well as signal dropout. We ...
Xiaoning Qian, Byung-Jun Yoon
FGR
2008
IEEE
346views Biometrics» more  FGR 2008»
14 years 1 months ago
Markov random field models for hair and face segmentation
This paper presents an algorithm for measuring hair and face appearance in 2D images. Our approach starts by using learned mixture models of color and location information to sugg...
Kuang-chih Lee, Dragomir Anguelov, Baris Sumengen,...