Sciweavers

1401 search results - page 46 / 281
» Probabilistic Object Tracking Using Multiple Features
Sort
View
CVPR
2004
IEEE
14 years 9 months ago
Multiple Kernel Tracking with SSD
Kernel-based objective functions optimized using the mean shift algorithm have been demonstrated as an effective means of tracking in video sequences. The resulting algorithms com...
Gregory D. Hager, Maneesh Dewan, Charles V. Stewar...
ICPR
2002
IEEE
14 years 8 months ago
Tracking People
This paper describes a real-time computer vision system for tracking people in monocular video sequences. The system tracks people as they move through the camera's field of ...
Ng Kim Piau, Surendra Ranganath
ACL
1994
13 years 9 months ago
Word-Sense Disambiguation Using Decomposable Models
Most probabilistic classi ers used for word-sense disambiguationhave either been based on onlyone contextual feature or have used a model that is simply assumed to characterize th...
Rebecca F. Bruce, Janyce Wiebe
TASLP
2011
13 years 2 months ago
A Probabilistic Interaction Model for Multipitch Tracking With Factorial Hidden Markov Models
—We present a simple and efficient feature modeling approach for tracking the pitch of two simultaneously active speakers. We model the spectrogram features of single speakers u...
Michael Wohlmayr, Michael Stark, Franz Pernkopf
ICIP
2008
IEEE
14 years 9 months ago
Activity-based temporal segmentation for videos of interacting objects using invariant trajectory features
This paper presents a content-based approach for temporal segmentation of videos. Tracked objects are characterized by their 2D trajectories which are used in a meaningful way to ...
Alexandre Hervieu, Patrick Bouthemy, Jean-Pierre L...