Storyboards comprising key illustrations and images help filmmakers to outline ideas, key moments, and story events when filming movies. Inspired by this, we introduce the first contextual benchmark dataset Script-to-Storyboard (Sc2St) composed of storyboards to explicitly express story structures in the movie domain, and propose the contextual retrieval task to facilitate movie story understanding. The Sc2St dataset contains fine-grained and diverse texts, annotated semantic keyframes, and coherent storylines in storyboards, unlike existing movie datasets. The contextual retrieval task takes as input a multi-sentence movie script summary with keyframe history and aims to retrieve a future keyframe described by a corresponding sentence to form the storyboard. Compared to classic text-based visual retrieval tasks, this requires capturing the context from the description (script) and keyframe history. We benchmark existing text-based visual retrieval methods on the new dataset and propose a recurrent-based framework with three variants for effective context encoding. Comprehensive experiments demonstrate that our methods compare favourably to existing methods; ablation studies validate the effectiveness of the proposed context encoding approaches.

Abstract Cross-depiction is the recognition—and synthesis—of objects whether they are photographed, painted, drawn, etc. It is a significant yet under-researched problem. Emulating the remarkable human ability to recognise and depict objects in an astonishingly wide variety of depictive forms is likely to advance both the foundations and the applications of computer vision. In this paper we motivate the cross-depiction problem, explain why it is difficult, and discuss some current approaches. Our main conclusions are (i) appearance-based recognition systems tend to be over-fitted to one depiction, (ii) models that explicitly encode spatial relations between parts are more robust, and (iii) recognition and non-photorealistic synthesis are related tasks.