Abstract--Acquisition of new sensorimotor knowledge by imitation is a promising paradigm for robot learning. To be effective, action learning should not be limited to direct replic...
This paper presents a methodology to derive a Supply Chain Management Ontology based on the RosettaNet specification framework. A prototype to mechanically derive a core ontology ...
Multiple Instance Learning (MIL) has been widely exploited in many computer vision tasks, such as image retrieval, object tracking and so on. To handle ambiguity of instance label...
Dynamic visual category learning calls for efficient adaptation as new training images become available or new categories are defined, existing training images or categories becom...