Sciweavers

174 search results - page 20 / 35
» A new objective function for sequence labeling
Sort
View
NIPS
2007
14 years 11 months ago
Fast and Scalable Training of Semi-Supervised CRFs with Application to Activity Recognition
We present a new and efficient semi-supervised training method for parameter estimation and feature selection in conditional random fields (CRFs). In real-world applications suc...
Maryam Mahdaviani, Tanzeem Choudhury
TJS
2002
160views more  TJS 2002»
14 years 9 months ago
Adaptive Optimizing Compilers for the 21st Century
Historically, compilers have operated by applying a fixed set of optimizations in a predetermined order. We call such an ordered list of optimizations a compilation sequence. This...
Keith D. Cooper, Devika Subramanian, Linda Torczon
AVSS
2009
IEEE
15 years 1 months ago
Regressed Importance Sampling on Manifolds for Efficient Object Tracking
In this paper, a new integrated particle filter is proposed for video object tracking. After particles are generated by importance sampling, each particle is regressed on the tran...
Fatih Porikli, Pan Pan
CVPR
2006
IEEE
15 years 11 months ago
An Adaptive Appearance Model Approach for Model-based Articulated Object Tracking
The detection and tracking of three-dimensional human body models has progressed rapidly but successful approaches typically rely on accurate foreground silhouettes obtained using...
Alexandru O. Balan, Michael J. Black
ICCV
2007
IEEE
15 years 4 months ago
Co-Tracking Using Semi-Supervised Support Vector Machines
This paper treats tracking as a foreground/background classification problem and proposes an online semisupervised learning framework. Initialized with a small number of labeled ...
Feng Tang, Shane Brennan, Qi Zhao, Hai Tao