Text-Visual Prompting for Efficient 2D Temporal Video Grounding.
Yimeng ZhangXin ChenJinghan JiaSijia LiuKe DingPublished in: CVPR (2023)
Keyphrases
- video search
- temporal analysis
- temporal information
- spatial and temporal
- news video
- space time
- natural language descriptions
- text detection
- temporal coherence
- temporal data
- multimedia
- text retrieval
- video sequences
- spatio temporal
- temporal consistency
- video data
- temporal domain
- visual data
- image classification
- visual analysis
- content based video retrieval
- temporal correlation
- temporal expressions
- video content
- semantic content
- visual cues
- visual information
- semantic information
- action recognition
- visual features
- image quality
- keywords
- high level