Sora as an AGI World Model? A Complete Survey on Text-to-Video Generation.
Joseph ChoFachrina Dewi PuspitasariSheng ZhengJingyao ZhengLik-Hang LeeTae-Ho KimChoong Seon HongChaoning ZhangPublished in: CoRR (2024)
Keyphrases
- world model
- semantic interpretation
- text generation
- artificial general intelligence
- video data
- video search
- natural language descriptions
- text detection
- information retrieval
- video content
- vision system
- video streams
- video sequences
- multimedia
- video segments
- video retrieval
- real time
- intelligent systems
- text documents
- database
- free text
- text mining
- news video
- video frames
- natural language generation
- databases
- general intelligence
- textual descriptions
- action selection
- action recognition
- keywords
- information systems
- artificial intelligence
- video analysis
- structured data
- key frames