CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers.
Wenyi HongMing DingWendi ZhengXinghan LiuJie TangPublished in: ICLR (2023)
Keyphrases
- video collections
- text generation
- natural language descriptions
- video search
- video data
- video content
- video sequences
- text detection
- video streams
- video clips
- news video
- text retrieval
- video database
- multimedia
- information retrieval
- text mining
- real time
- free text
- multimedia documents
- event recognition
- video segments
- online video
- small scale
- video analysis
- video retrieval
- real world
- audio content
- digital video
- database
- information extraction
- generation process
- event detection
- multimedia data
- keywords
- natural language processing
- multiple modalities
- semantic markup
- metadata
- text information
- video images
- key frames
- video shots
- news stories