3190 search results - page 459 / 638 » cans 2011 |
203
click to vote
ICCV
2011
IEEE
14 years 6 months ago
2011
IEEE
We present an active learning approach to choose image annotation requests among both object category labels and the objects’ attribute labels. The goal is to solicit those labe...
195
click to vote
ICCV
2011
IEEE
14 years 6 months ago
2011
IEEE
Many applications involve multiple-modalities such as text and images that describe the problem of interest. In order to leverage the information present in all the modalities, on...
153
click to vote
ICCV
2011
IEEE
14 years 6 months ago
2011
IEEE
In this work we present a new crowd analysis algorithm powered by behavior priors that are learned on a large database of crowd videos gathered from the Internet. The algorithm wo...
349
click to vote
ICCV
2011
IEEE
14 years 6 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...
228
click to vote
ICCV
2011
IEEE
14 years 6 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...