From Sora What We Can See: A Survey of Text-to-Video Generation.
Rui SunYumin ZhangTejal ShahJiahao SunShuoying ZhangWenqi LiHaoran DuanBo WeiRajiv RanjanPublished in: CoRR (2024)
Keyphrases
- text generation
- video search
- text detection
- video segments
- video sequences
- real time video
- natural language descriptions
- video streams
- news video
- video data
- real time
- text retrieval
- text documents
- video frames
- video collections
- keywords
- video content
- video images
- multimedia search
- closed captions
- spatial and temporal
- video clips
- multimedia data
- database
- information retrieval
- computer vision
- semantic labels
- space time
- natural language generation
- key frames
- multimedia documents
- digital video
- video shots
- video database
- temporal information
- web documents
- textual data
- co occurrence
- text mining
- video analysis