Order-Embeddings of Images and Language

international conference on learning representations, 2015.

Cited by: 282|Bibtex|Views39|Links
EI

Abstract:

Hypernymy, textual entailment, and image captioning can be seen as special cases of a single visual-semantic hierarchy over words, sentences, and images. In this paper we advocate for explicitly modeling the partial order structure of this hierarchy. Towards this goal, we introduce a general method for learning ordered representations, ...More

Code:

Data:

Your rating :
0

 

Tags
Comments