616 search results - page 75 / 124 » Learning Hierarchical Models of Scenes, Objects, and Parts |
IJCV
2008
14 years 9 months ago
2008
We present an unsupervised approach for learning a generative layered representation of a scene from a video for motion segmentation. The learnt model is a composition of layers, ...
HRI
2006
ACM
15 years 3 months ago
2006
ACM
The essence of the signal-to-symbol problem consists of associating a symbolic description of an object (e.g., a chair) to a signal (e.g., an image) that captures the real object....
115
click to vote
CVPR
2009
IEEE
16 years 2 months ago
2009
IEEE
Color is a powerful visual cue for many computer vision
applications such as image segmentation and object recognition.
However, most of the existing color models depend on the i...
PVLDB
2008
14 years 9 months ago
2008
Trajectory classification, i.e., model construction for predicting the class labels of moving objects based on their trajectories and other features, has many important, real-worl...
139
click to vote
ICCV
2011
IEEE
13 years 9 months ago
2011
IEEE
Complex human activities occurring in videos can be defined in terms of temporal configurations of primitive actions. Prior work typically hand-picks the primitives, their total...