Sciweavers

3449 search results - page 540 / 690
» A Framework for Multiple-Instance Learning
Sort
View
CVPR
1999
IEEE
16 years 8 months ago
Time-Series Classification Using Mixed-State Dynamic Bayesian Networks
We present a novel mixed-state dynamic Bayesian network (DBN) framework for modeling and classifying timeseries data such as object trajectories. A hidden Markov model (HMM) of di...
Vladimir Pavlovic, Brendan J. Frey, Thomas S. Huan...
CVPR
2006
IEEE
16 years 8 months ago
Unsupervised Bayesian Detection of Independent Motion in Crowds
While crowds of various subjects may offer applicationspecific cues to detect individuals, we demonstrate that for the general case, motion itself contains more information than p...
Gabriel J. Brostow, Roberto Cipolla
CVPR
2007
IEEE
16 years 8 months ago
Modeling Appearances with Low-Rank SVM
Several authors have noticed that the common representation of images as vectors is sub-optimal. The process of vectorization eliminates spatial relations between some of the near...
Lior Wolf, Hueihan Jhuang, Tamir Hazan
CVPR
2007
IEEE
16 years 8 months ago
Joint Object Segmentation and Behavior Classification in Image Sequences
In this paper, we propose a general framework for fusing bottom-up segmentation with top-down object behavior classification over an image sequence. This approach is beneficial fo...
Laura Gui, Jean-Philippe Thiran, Nikos Paragios
ECCV
2006
Springer
16 years 8 months ago
Dense Photometric Stereo by Expectation Maximization
Abstract. We formulate a robust method using Expectation Maximization (EM) to address the problem of dense photometric stereo. Previous approaches using Markov Random Fields (MRF) ...
Tai-Pang Wu, Chi-Keung Tang