TAVGBench: Benchmarking Text to Audible-Video Generation.
Yuxin MaoXuyang ShenJing ZhangZhen QinJinxing ZhouMochu XiangYiran ZhongYuchao DaiPublished in: CoRR (2024)
Keyphrases
- natural language descriptions
- text generation
- text detection
- video data
- video sequences
- video search
- video frames
- video content
- multimedia
- text retrieval
- video segments
- real time
- video analysis
- closed captions
- multimedia documents
- video clips
- information retrieval
- keywords
- video streams
- multimedia search
- spatio temporal
- video images
- text documents
- space time
- digital video
- video collections
- news video
- natural language generation
- text mining
- visual features
- generation process
- video database
- textual descriptions
- text information
- semantic labels
- web documents
- natural language
- free text
- key concepts
- audio content
- temporal information