3837 search results - page 313 / 768 » Learning Approximate Consistencies |
188
click to vote
ICPR
2010
IEEE
15 years 5 months ago
2010
IEEE
Detecting abnormal behaviors in crowd scenes is quite important for public security and has been paid more and more attentions. Most previous methods use offline trained model to p...
217
click to vote
ECIR
2009
Springer
15 years 5 months ago
2009
Springer
Abstract. Active learning refers to the task of devising a ranking function that, given a classifier trained from relatively few training examples, ranks a set of additional unlabe...
260
click to vote
SIGIR
2011
ACM
14 years 10 months ago
2011
ACM
We study how to best use crowdsourced relevance judgments learning to rank [1, 7]. We integrate two lines of prior work: unreliable crowd-based binary annotation for binary classi...
245
click to vote
AAAI
2012
13 years 9 months ago
2012
Transfer learning proves to be effective for leveraging labeled data in the source domain to build an accurate classifier in the target domain. The basic assumption behind transf...
259
click to vote
CVPR
2009
IEEE
17 years 2 months ago
2009
IEEE
We present a novel method for modeling dynamic visual
phenomena, which consists of two key aspects. First, the in-
tegral motion of constituent elements in a dynamic scene is
ca...