Text-Visual Prompting for Efficient 2D Temporal Video Grounding.
Yimeng ZhangXin ChenJinghan JiaSijia LiuKe DingPublished in: CoRR (2023)
Keyphrases
- video search
- temporal information
- news video
- temporal analysis
- video streams
- multimedia
- temporal consistency
- space time
- temporal coherence
- visual information
- video content
- video sequences
- video data
- visual analysis
- multimedia documents
- video retrieval
- video segments
- semantic labels
- natural language descriptions
- real time
- text retrieval
- multimedia data
- spatial and temporal
- video frames
- keywords
- text mining
- text documents
- information retrieval
- temporal order
- temporal expressions
- text detection
- temporal structure
- low level
- visual cues
- temporal correlation
- temporal relations
- spatial temporal