VideoTetris: Towards Compositional Text-to-Video Generation.
Ye TianLing YangHaotian YangYuan GaoYufan DengJingmin ChenXintao WangZhaochen YuXin TaoPengfei WanDi ZhangBin CuiPublished in: CoRR (2024)
Keyphrases
- text generation
- video data
- text detection
- natural language descriptions
- video search
- multimedia
- information retrieval
- video sequences
- video frames
- video content
- video segments
- multimedia search
- video streams
- video retrieval
- news video
- real time
- multimedia documents
- free text
- video clips
- text retrieval
- video database
- key concepts
- video shots
- video collections
- natural language generation
- database
- text information
- video dataset
- real time video
- online video
- audio content
- semantic labels
- closed captions
- textual descriptions
- text summarization
- textual data
- space time
- co occurrence
- natural language
- computer vision