Learning Object Attributes with Category-Free Grounded Language from Deep Featurization
Luke E. Richards,Kasra Darvish,Cynthia Matuszek,Luke E. Richards,Kasra Darvish,Cynthia Matuszek
While grounded language learning, or learning the meaning of language with respect to the physical world in which a robot operates, is a major area in human-robot interaction studies, most research occurs in closed worlds or domain-constrained settings. We present a system in which language is grounded in visual percepts without using categorical constraints by combining CNN-based visual featuriza...
