Is an Image Worth More than a Thousand Words? On the Fine-Grain Semantic Differences between Visual and Linguistic Representations

Guillem Collell and Marie-Francine Moens

COLING 2016 | pdf |

Takeaways:

Some concepts are better captured from image than from a linguistic description: color, form and surface and motion. Whereas linguistic features outperform in encyclopedic features. Both perform equivalently on taxonomic features (classes and categories)