Duration: 39:06

101 views

1

In this talk, we present some of our recent attempts on tagging visual data with textual descriptions. Annotation process learns to predict the tags from examples. Tags could be a set of words, phrases or even sentences. Our method uses simple machine learning schemes, and it outperforms the state of the art methods which uses more complex models. Our method captures the prior and statistics of the textual data, and uses it in a nearest neighbour setting with learned distance measures. Parts of this work appear in AAAI 2012 and ECCV 2012.