Phenaki: Variable Length Video Generation From Open Domain Textual Description.
Ruben VillegasMohammad BabaeizadehPieter-Jan KindermansHernan MoraldoHan ZhangMohammad Taghi SaffarSantiago CastroJulius KunzeDumitru ErhanPublished in: CoRR (2022)
Keyphrases
- variable length
- open domain
- textual descriptions
- fixed length
- information extraction
- n gram
- semantic representation
- video sequences
- semantic concepts
- question answering
- metadata
- multimedia
- video data
- semantic information
- bitstream
- video content
- video analysis
- machine learning
- web images
- data mining
- multimedia data
- computer vision