Sciweavers

890 search results - page 142 / 178
» Learning Generic Prior Models for Visual Computation
Sort
View
90
Voted
JIRS
2007
116views more  JIRS 2007»
14 years 9 months ago
Recognition of Human Motion From Qualitative Normalised Templates
Abstract This paper proposes a Qualitative Normalised Templates (QNTs) framework for solving the human motion classification problem. In contrast to other human motion classifica...
Chee Seng Chan, Honghai Liu, David J. Brown
HUMO
2000
Springer
15 years 1 months ago
Specialized Mappings and the Estimation of Human Body Pose from a Single Image
We present an approach for recovering articulated body pose from single monocular images using the Specialized Mappings Architecture (SMA), a non-linear supervised learning archit...
Rómer Rosales, Stan Sclaroff
ESANN
2007
14 years 11 months ago
Toward a robust 2D spatio-temporal self-organization
Abstract. Several models have been proposed for spatio-temporal selforganization, among which the TOM model by Wiemer [1] is particularly promising. In this paper, we propose to ad...
Thomas Girod, Laurent Bougrain, Frédé...
CVPR
2005
IEEE
15 years 11 months ago
Semi-Supervised Adapted HMMs for Unusual Event Detection
We address the problem of temporal unusual event detection. Unusual events are characterized by a number of features (rarity, unexpectedness, and relevance) that limit the applica...
Dong Zhang, Daniel Gatica-Perez, Samy Bengio, Iain...
ECCV
2008
Springer
15 years 11 months ago
Online Tracking and Reacquisition Using Co-trained Generative and Discriminative Trackers
Visual tracking is a challenging problem, as an object may change its appearance due to viewpoint variations, illumination changes, and occlusion. Also, an object may leave the fie...
Gérard G. Medioni, Qian Yu, Thang Ba Dinh