Coarse-to-fine dual-level attention for video-text cross modal retrieval.
Ming JinHuaxiang ZhangLei ZhuJiande SunLi LiuPublished in: Knowl. Based Syst. (2022)
Keyphrases
- coarse to fine
- cross modal
- multi modal
- multiscale
- multimedia retrieval
- visual data
- multiresolution
- image retrieval
- multimedia
- multimedia databases
- text retrieval
- information retrieval
- image registration
- multimedia documents
- object detection
- visual similarity
- semantic concepts
- multimedia data
- visual recognition
- video sequences
- video data
- text mining
- text documents
- dynamic programming
- video frames
- web images
- video streams
- pairwise
- video analysis
- visual information
- multimedia information retrieval
- keywords
- visual features
- image database
- low level features
- pattern recognition
- content based retrieval
- document retrieval