GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions

04/30/2021 ∙ by Chenfei Wu, et al. ∙ 14

Generating videos from text is a challenging task due to its high computational requirements for training and infinite possible answers for evaluation. Existing works typically experiment on simple or small datasets, where the generalization ability is quite limited. In this work, we propose GODIVA, an open-domain text-to-video pretrained model that can generate videos from text in an auto-regressive manner using a three-dimensional sparse attention mechanism. We pretrain our model on Howto100M, a large-scale text-video dataset that contains more than 136 million text-video pairs. Experiments show that GODIVA not only can be fine-tuned on downstream video generation tasks, but also has a good zero-shot capability on unseen texts. We also propose a new metric called Relative Matching (RM) to automatically evaluate the video generation quality. Several challenges are listed and discussed as future work.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 7

page 8

page 11

page 12

Code Repositories

DALLE_clip_score

Simple script to compute CLIP-based scores given a DALL-e trained model.


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.