In light of recent advances in multimodal Large Language Models (LLMs), there is increasing attention to scaling them from image-text data to more informative real-world videos. Compared to static images, video poses unique challenges for effective large-scale pre-training due to the modeling of its spatiotemporal dynamics. In this paper, we address such limitations in video-language pre-training with an efficient video decomposition that represents each video as keyframes and temporal motions. These are then adapted to an LLM using well-designed tokenizers that discretize visual and temporal information as a few tokens, thus enabling unified generative pre-training of videos, images, and text. At inference, the generated tokens from the LLM are carefully recovered to the original continuous pixel space to create various video content. Our proposed framework is both capable of comprehending and generating image and video content, as demonstrated by its competitive performance across 13 multimodal benchmarks in image and video understanding and generation. Our code and models will be available at https://video-lavit.github.io.

本文介绍了一种用于视频-语言预训练的高效视频分解的方法，该方法通过设计良好的分词器将视觉和时间信息离散化为少量的标记，从而使大规模生成式预训练能够统一视频、图像和文本内容。在图像和视频的理解和生成的13个多模态基准测试中，我们提出的框架表现出竞争性的性能。

Video-LaVIT：统一的视频-语言预训练与解耦的视觉-运动词汇编