M3L: Language-based Video Editing via Multi-Modal Multi-Level Transformers

TL;DR

This paper introduces M3L, a multi-modal transformer model for language-guided video editing that preserves source content while applying semantic changes based on natural language instructions.

Contribution

The paper proposes a novel multi-level transformer architecture for language-based video editing, enabling more accurate and controlled edits guided by natural language instructions.

Findings

M3L effectively performs language-guided video editing.

New datasets for evaluating language-based video editing.

LBVE opens new research directions in vision-and-language tasks.

Abstract

Video editing tools are widely used nowadays for digital design. Although the demand for these tools is high, the prior knowledge required makes it difficult for novices to get started. Systems that could follow natural language instructions to perform automatic editing would significantly improve accessibility. This paper introduces the language-based video editing (LBVE) task, which allows the model to edit, guided by text instruction, a source video into a target video. LBVE contains two features: 1) the scenario of the source video is preserved instead of generating a completely different video; 2) the semantic is presented differently in the target video, and all changes are controlled by the given instruction. We propose a Multi-Modal Multi-Level Transformer (M$^3$L) to carry out LBVE. M$^3$L dynamically learns the correspondence between video perception and language semantic at different levels, which benefits both the video understanding and video frame synthesis. We build three new datasets for evaluation, including two diagnostic and one from natural videos with human-labeled text. Extensive experimental results show that M$^3$L is effective for video editing and that LBVE can lead to a new field toward vision-and-language research.