About this document
Visual Compositionality in Language by stergios chatzikyriakidis is a document available to read on EtoBox.
This document reports on preliminary experiments exploring visual semantic compositionality by modeling the composition of attributes and objects in the visual modality, similar to modeling the composition of adjectives and nouns in language. The experiments show similarities between the concept topologies in visual and linguistic spaces, supporting the hypothesis that semantic compositionality is a general cognitive process irrespective of modality. Vector representations of attributes, objects, and their
- Author
- stergios chatzikyriakidis
- Language
- EN