Not (yet) the whole story: Evaluating Visual Storytelling Requires More than Measuring Coherence, Grounding, and Repetition

TL;DR

This paper proposes a human-likeness based evaluation method for visual storytelling, revealing that current models, even with high scores, may not produce truly good stories, highlighting the complexity of story quality.

Contribution

It introduces a novel human-likeness measurement approach for evaluating visual stories and demonstrates its effectiveness in revealing limitations of existing models.

Findings

LLaVA achieves the best score but only slightly better than smaller models.

Upgrading visual and language components improves model performance.

Human evaluation suggests story quality depends on more than coherence, grounding, and repetition.

Abstract

Visual storytelling consists in generating a natural language story given a temporally ordered sequence of images. This task is not only challenging for models, but also very difficult to evaluate with automatic metrics since there is no consensus about what makes a story 'good'. In this paper, we introduce a novel method that measures story quality in terms of human likeness regarding three key aspects highlighted in previous work: visual grounding, coherence, and repetitiveness. We then use this method to evaluate the stories generated by several models, showing that the foundation model LLaVA obtains the best result, but only slightly so compared to TAPM, a 50-times smaller visual storytelling model. Upgrading the visual and language components of TAPM results in a model that yields competitive performance with a relatively low number of parameters. Finally, we carry out a human evaluation study, whose results suggest that a 'good' story may require more than a human-like level of visual grounding, coherence, and repetition.