Abstract. We tackle the problem of multi-class relational sequence learning using relevant patterns discovered from a set of labelled sequences. To deal with this problem, firstly...
Nicola Di Mauro, Teresa Maria Altomare Basile, Ste...
Abstract. We propose a novel unsupervised transfer learning framework that utilises unlabelled auxiliary data to quantify and select the most relevant transferrable knowledge for r...
Virtually all methods of learning dynamic systems from data start from the same basic assumption: the learning algorithm will be given a sequence of data generated from the dynami...
Relevant Component Analysis (RCA) has been proposed for learning distance metrics with contextual constraints for image retrieval. However, RCA has two important disadvantages. On...
Steven C. H. Hoi, Wei Liu, Michael R. Lyu, Wei-Yin...
Abstract. This contribution proposes a compositional approach to visual object categorization of scenes. Compositions are learned from the Caltech 101 database1 intermediate abstra...