Sciweavers

119 search results - page 13 / 24
» Object, Scene and Actions: Combining Multiple Features for H...
Sort
View
ICCV
2009
IEEE
13 years 6 months ago
Fast realistic multi-action recognition using mined dense spatio-temporal features
Within the field of action recognition, features and descriptors are often engineered to be sparse and invariant to transformation. While sparsity makes the problem tractable, it ...
Andrew Gilbert, John Illingworth, Richard Bowden
CVPR
2011
IEEE
13 years 4 months ago
Cross-View Action Recognition via View Knowledge Transfer
In this paper, we present a novel approach to recognizing human actions from different views by view knowledge transfer. An action is originally modelled as a bag of visual-words ...
Jingen Liu
DAGM
2006
Springer
14 years 7 days ago
Handling Camera Movement Constraints in Reinforcement Learning Based Active Object Recognition
In real world scenes, objects to be classified are usually not visible from every direction, since they are almost always positioned on some kind of opaque plane. When moving a cam...
Christian Derichs, Heinrich Niemann
IJCAI
2007
13 years 10 months ago
Common Sense Based Joint Training of Human Activity Recognizers
Given sensors to detect object use, commonsense priors of object usage in activities can reduce the need for labeled data in learning activity models. It is often useful, however,...
Shiaokai Wang, William Pentney, Ana-Maria Popescu,...
ECCV
2008
Springer
14 years 10 months ago
Cross-View Action Recognition from Temporal Self-similarities
This paper concerns recognition of human actions under view changes. We explore self-similarities of action sequences over time and observe the striking stability of such measures ...
Imran N. Junejo, Emilie Dexter, Ivan Laptev, Patri...