EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding.
Yanmin WuXinhua ChengRenrui ZhangZesen ChengJian ZhangPublished in: CVPR (2023)
Keyphrases
- input output
- information retrieval
- visual features
- web images
- text mining
- video search
- word level
- text retrieval
- semantic content
- database
- image alignment
- visual information
- document analysis
- news video
- sequence alignment
- visual perception
- latent semantic analysis
- fairy tales
- visual cues
- key concepts
- image search
- text documents
- web documents
- low level
- image retrieval
- pairwise
- keywords
- high level