Sciweavers

360 search results - page 25 / 72
» Combining Learned Discrete and Continuous Action Models
Sort
View
ICML
2010
IEEE
15 years 5 months ago
3D Convolutional Neural Networks for Human Action Recognition
We consider the fully automated recognition of actions in uncontrolled environment. Most existing work relies on domain knowledge to construct complex handcrafted features from in...
Shuiwang Ji, Wei Xu, Ming Yang, Kai Yu
ICPR
2008
IEEE
15 years 10 months ago
Optimal feature weighting for the discrete HMM
We propose a modified discrete HMM that includes a feature weighting discrimination component. We assume that the feature space is partitioned into subspaces and that the relevan...
Oualid Missaoui, Hichem Frigui
SIGGRAPH
2010
ACM
15 years 8 months ago
Discrete scale axis representations for 3D geometry
This paper addresses the fundamental problem of computing stable medial representations of 3D shapes. We propose a spatially adaptive classification of geometric features that yi...
Balint Miklos, Joachim Giesen, Mark Pauly
CVIU
2006
317views more  CVIU 2006»
15 years 4 months ago
A general method for human activity recognition in video
In this paper we develop a system for human behaviour recognition in video sequences. Human behaviour is modelled as a stochastic sequence of actions. Actions are described by a f...
Neil Robertson, Ian D. Reid
ECCV
2004
Springer
16 years 6 months ago
A Statistical Model for General Contextual Object Recognition
We consider object recognition as the process of attaching meaningful labels to specific regions of an image, and propose a model that learns spatial relationships between objects....
Peter Carbonetto, Nando de Freitas, Kobus Barnard