659 search results - page 84 / 132 » Object Labelling from Human Action Recognition |
158
Voted
CVPR
2011
IEEE
14 years 12 months ago
2011
IEEE
Active learning and crowdsourcing are promising ways to efficiently build up training sets for object recognition, but thus far techniques are tested in artificially controlled ...
147
click to vote
AVSS
2006
IEEE
15 years 9 months ago
2006
IEEE
Extracting meaningful 3D human motion information from video sequences is of interest for applications like intelligent humancomputer interfaces, biometrics, video browsing and ind...
145
Voted
ATAL
2006
Springer
15 years 7 months ago
2006
Springer
We present a method for learning a human understandable, executable model of an agent's behavior using observations of its interaction with the environment. By executable we ...
136
click to vote
CVPR
2010
IEEE
15 years 7 months ago
2010
IEEE
To leverage large-scale weakly-tagged images for computer vision tasks (such as object detection and scene recognition), a novel cross-modal tag cleansing and junk image filtering...
177
Voted
TSMC
2010
14 years 10 months ago
2010
We study the problem of projecting high-dimensional tensor data on an unspecified Riemannian manifold onto some lower dimensional subspace1 without much distorting the pairwise geo...