CVCLLGOct 8, 2019

Prose for a Painting

arXiv:1910.03634v13 citations
Originality Synthesis-oriented
AI Analysis

This addresses the need for more engaging captions in art contexts, but it is incremental as it builds on existing style transfer methods.

The authors tackled the problem of generating creative Shakespearean prose descriptions for paintings, which lacks a large supervised dataset, by using an intermediate English poem description and applying language style transfer. They evaluated their results through human evaluation on a Likert scale and BLEU scores, demonstrating applicability and limitations on famous paintings.

Painting captions are often dry and simplistic which motivates us to describe a painting creatively in the style of Shakespearean prose. This is a difficult problem, since there does not exist a large supervised dataset from paintings to Shakespearean prose. Our solution is to use an intermediate English poem description of the painting and then apply language style transfer which results in Shakespearean prose describing the painting. We rate our results by human evaluation on a Likert scale, and evaluate the quality of language style transfer using BLEU score as a function of prose length. We demonstrate the applicability and limitations of our approach by generating Shakespearean prose for famous paintings. We make our models and code publicly available.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes