Visual Storytelling
Abstract
We introduce the first dataset for sequential vision-to-language, and explore how this data may be used for the task of visual storytelling. The first release of this dataset, SIND v.1, includes 81,743 unique photos in 20,211 sequences, aligned to both descriptive (caption) and story language. We establish several strong baselines for the storytelling task, and motivate an automatic metric to benchmark progress. Modelling concrete description as well as figurative and social language, as provided in this dataset and the storytelling task, has the potential to move artificial intelligence from basic understandings of typical visual scenes towards more and more human-like understanding of grounded event structure and subjective expression.
Keywords
Cite
@article{arxiv.1604.03968,
title = {Visual Storytelling},
author = {Ting-Hao and Huang and Francis Ferraro and Nasrin Mostafazadeh and Ishan Misra and Aishwarya Agrawal and Jacob Devlin and Ross Girshick and Xiaodong He and Pushmeet Kohli and Dhruv Batra and C. Lawrence Zitnick and Devi Parikh and Lucy Vanderwende and Michel Galley and Margaret Mitchell},
journal= {arXiv preprint arXiv:1604.03968},
year = {2016}
}
Comments
to appear in NAACL 2016