TeViS:Translating Text Synopses to Video Storyboards

TL;DR

This paper introduces the TeViS task, which retrieves and sequences images to create video storyboards from text synopses, and proposes a novel VQ-Trans model that outperforms existing methods on a new dataset.

Contribution

The paper defines a new task, constructs a dedicated dataset, and proposes a VQ-Trans model that enhances cross-modal retrieval and sequence generation for video storyboarding.

Findings

VQ-Trans outperforms prior methods and CLIP-based baselines.

Constructed the MovieNet-TeViS dataset with 10K synopses and keyframes.

Significant gap remains between model performance and human level.

Abstract

A video storyboard is a roadmap for video creation which consists of shot-by-shot images to visualize key plots in a text synopsis. Creating video storyboards, however, remains challenging which not only requires cross-modal association between high-level texts and images but also demands long-term reasoning to make transitions smooth across shots. In this paper, we propose a new task called Text synopsis to Video Storyboard (TeViS) which aims to retrieve an ordered sequence of images as the video storyboard to visualize the text synopsis. We construct a MovieNet-TeViS dataset based on the public MovieNet dataset. It contains 10K text synopses each paired with keyframes manually selected from corresponding movies by considering both relevance and cinematic coherence. To benchmark the task, we present strong CLIP-based baselines and a novel VQ-Trans. VQ-Trans first encodes text synopsis and images into a joint embedding space and uses vector quantization (VQ) to improve the visual representation. Then, it auto-regressively generates a sequence of visual features for retrieval and ordering. Experimental results demonstrate that VQ-Trans significantly outperforms prior methods and the CLIP-based baselines. Nevertheless, there is still a large gap compared to human performance suggesting room for promising future work. The code and data are available at: \url{https://ruc-aimind.github.io/projects/TeViS/}