Multiple Instance Learning (MIL) provides a framework for training a discriminative classifier from data with ambiguous labels. This framework is well suited for the task of learni...
Carolina Galleguillos, Boris Babenko, Andrew Rabin...
— Imitation is a powerful mechanism for transferring knowledge from an instructor to a na¨ıve observer, one that is deeply contingent on a state of shared attention between the...
Aaron P. Shon, David B. Grimes, Chris Baker, Matth...
Recently, evolutionary computation has been successfully integrated into statistical learning methods. A Support Vector Machine (SVM) using evolution strategies for its optimizati...
Abstract. One solution to the lack of label problem is to exploit transfer learning, whereby one acquires knowledge from source-domains to improve the learning performance in the t...
Abstract. In recent years there has been growing interest in recognition models using local image features for applications ranging from long range motion matching to object class ...