CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers.

Wenyi Hong Ming Ding Wendi Zheng Xinghan Liu Jie Tang

Published in: CoRR (2022)

Keyphrases

video collections
text generation
natural language descriptions
video retrieval
multimedia
video search
text detection
video content
video segments

video clips
video data
news video
digital video
video database
video sequences
real world
real time
text retrieval

video frames
text mining
multimedia documents
video analysis
small scale
database
video streams
free text
spatial and temporal

semantic labels
text documents
semantic concepts
space time
text data
textual descriptions
text information
natural language
audio content