Abstract--Unlimited vocabulary annotation of multimedia documents remains elusive despite progress solving the problem in the case of a small, fixed lexicon. Taking advantage of th...
Although tagging has become increasingly popular in online image and video sharing systems, tags are known to be noisy, ambiguous, incomplete and subjective. These factors can ser...
Discriminative learning methods are widely used in natural language processing. These methods work best when their training and test data are drawn from the same distribution. For...
We present a novel approach for structure prediction that addresses the difficulty of obtaining labeled structures for training. We observe that structured output problems often h...
Ming-Wei Chang, Vivek Srikumar, Dan Goldwasser, Da...
We present a new data set encoding localized semantics for 1014 images and a methodology for using this kind of data for recognition evaluation. This methodology establishes protoc...