Transcript to Video: Efficient Clip Sequencing from Texts

TL;DR

This paper introduces a weakly-supervised framework that automatically creates coherent and style-appropriate video sequences from text inputs, enabling non-experts to produce well-edited videos efficiently.

Contribution

It proposes a novel Content Retrieval Module and Temporal Coherent Module for visual-language learning and shot sequencing, along with an efficient search strategy for real-time performance.

Findings

Retrieves content-relevant shots effectively.

Creates plausible and stylistically coherent video sequences.

Supports real-time video clip sequencing.

Abstract

Among numerous videos shared on the web, well-edited ones always attract more attention. However, it is difficult for inexperienced users to make well-edited videos because it requires professional expertise and immense manual labor. To meet the demands for non-experts, we present Transcript-to-Video -- a weakly-supervised framework that uses texts as input to automatically create video sequences from an extensive collection of shots. Specifically, we propose a Content Retrieval Module and a Temporal Coherent Module to learn visual-language representations and model shot sequencing styles, respectively. For fast inference, we introduce an efficient search strategy for real-time video clip sequencing. Quantitative results and user studies demonstrate empirically that the proposed learning framework can retrieve content-relevant shots while creating plausible video sequences in terms of style. Besides, the run-time performance analysis shows that our framework can support real-world applications.