In this paper, we study the problem of transfer learning from text to images in the context of network data in which link based bridges are available to transfer the knowledge bet...
The authors present TWIG, a visually grounded wordlearning system that uses its existing knowledge of vocabulary, grammar, and action schemas to help it learn the meanings of new ...
In this paper we aim to train deep neural networks for rapid visual recognition. The task is highly challenging, largely due to the lack of a meaningful regularizer on the functio...
: Communication processes have become increasingly important in modern working life. Organizations invest a surprisingly high amount of financial resources and employee work time i...
End-user programming provides a unique opportunity to study informal computer science education and knowledge acquisition in the real world. We seek to explore the use of communit...