The Lost Melody: Empirical Observations on Text-to-Video Generation From A Storytelling Perspective.
Andrew ShinYusuke MoriKunitake KanekoPublished in: CoRR (2024)
Keyphrases
- text generation
- text detection
- video search
- video data
- natural language descriptions
- video sequences
- multimedia documents
- video content
- video frames
- information retrieval
- multimedia
- video streams
- natural language generation
- text mining
- video database
- video analysis
- free text
- video clips
- video segments
- text retrieval
- news video
- multimedia data
- digital video
- closed captions
- database
- multimedia search
- low level
- scene text
- key concepts
- spatial and temporal
- video retrieval
- space time
- key frames
- keywords
- semantic labels
- event detection
- human activities
- document images
- text documents