Log In Sign Up

GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions

by   Chenfei Wu, et al.

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.


page 7

page 8

page 11

page 12


Phenaki: Variable Length Video Generation From Open Domain Textual Description

We present Phenaki, a model capable of realistic video synthesis, given ...

NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion

This paper presents a unified multimodal pre-trained model called NÜWA t...

Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions

We study joint video and language (VL) pre-training to enable cross-moda...

Learning Video Models from Text: Zero-Shot Anticipation for Procedural Actions

Can we teach a robot to recognize and make predictions for activities th...

BridgeFormer: Bridging Video-text Retrieval with Multiple Choice Questions

Pre-training a model to learn transferable video-text representation for...

Narration Generation for Cartoon Videos

Research on text generation from multimodal inputs has largely focused o...

TennisVid2Text: Fine-grained Descriptions for Domain Specific Videos

Automatically describing videos has ever been fascinating. In this work,...

Code Repositories


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

view repo