13476 search results - page 2017 / 2696 » Learning from Streams |
256
click to vote
CIVR
2008
Springer
15 years 9 months ago
2008
Springer
In this paper, a motion-based approach for detecting highlevel semantic events in video sequences is presented. Its main characteristic is its generic nature, i.e. it can be direc...
220
click to vote
NIPS
2008
15 years 8 months ago
2008
CAPTCHAs are computer-generated tests that humans can pass but current computer systems cannot. CAPTCHAs provide a method for automatically distinguishing a human from a computer ...
211
click to vote
NIPS
2007
15 years 8 months ago
2007
Reliably recovering 3D human pose from monocular video requires models that bias the estimates towards typical human poses and motions. We construct priors for people tracking usi...
217
click to vote
AAAI
2004
15 years 8 months ago
2004
Traditionally, text classifiers are built from labeled training examples. Labeling is usually done manually by human experts (or the users), which is a labor intensive and time co...
248
click to vote
AAAI
1994
15 years 8 months ago
1994
Many AI problems can be modeled as constraint satisfaction problems (CSP), but many of them are actually dynamic: the set of constraints to consider evolves because of the environ...