296
click to vote
ICCV
2011
IEEE
14 years 7 months ago
2011
IEEE
The saliency of regions or objects in an image can be significantly boosted if they recur in multiple images. Leveraging this idea, cosegmentation jointly segments common regions...
172
click to vote
ICCV
2011
IEEE
14 years 7 months ago
2011
IEEE
We present a new framework in which image segmentation, figure/ground organization, and object detection all appear as the result of solving a single grouping problem. This frame...
240
click to vote
ICCV
2011
IEEE
14 years 7 months ago
2011
IEEE
Human-nameable visual “attributes” can benefit various recognition tasks. However, existing techniques restrict these properties to categorical labels (for example, a person ...
262
click to vote
ICCV
2011
IEEE
14 years 7 months ago
2011
IEEE
In this work, we propose to use attributes and parts for recognizing human actions in still images. We define action attributes as the verbs that describe the properties of human...
389
click to vote
ICCV
2011
IEEE
14 years 7 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...