Sciweavers

31 search results - page 2 / 7
» Latent Pose Estimator for Continuous Action Recognition
Sort
View
ACCV
2010
Springer
13 years 10 days ago
Continuous Surface-Point Distributions for 3D Object Pose Estimation and Recognition
We present a 3D, probabilistic object-surface model, along with mechanisms for probabilistically integrating unregistered 2.5D views into the model, and for segmenting model instan...
Renaud Detry, Justus H. Piater
CVPR
2012
IEEE
11 years 7 months ago
Multi-view latent variable discriminative models for action recognition
Many human action recognition tasks involve data that can be factorized into multiple views such as body postures and hand shapes. These views often interact with each other over ...
Yale Song, Louis-Philippe Morency, Randall Davis
CVPR
2008
IEEE
13 years 11 months ago
Pose primitive based human action recognition in videos or still images
This paper presents a method for recognizing human actions based on pose primitives. In learning mode, the parameters representing poses and activities are estimated from videos. ...
Christian Thurau, Václav Hlavác
CVPR
2011
IEEE
13 years 1 months ago
Action Recognition from a Distributed Representation of Pose and Appearance
We present a distributed representation of pose and appearance of people called the “poselet activation vector”. First we show that this representation can be used to estimate...
Subhransu Maji, Lubomir Bourdev, Jitendra Malik
CVPR
2007
IEEE
13 years 11 months ago
Single View Human Action Recognition using Key Pose Matching and Viterbi Path Searching
3D human pose recovery is considered as a fundamental step in view-invariant human action recognition. However, inferring 3D poses from a single view usually is slow due to the la...
Fengjun Lv, Ramakant Nevatia