Multi-Feature Graph Attention Network for Cross-Modal Video-Text Retrieval.
Xiaoshuai HaoYucan ZhouDayan WuWanqian ZhangBo LiWeiping WangPublished in: ICMR (2021)
Keyphrases
- text retrieval
- cross modal
- multimedia retrieval
- multi feature
- image retrieval
- multi modal
- multimedia
- document retrieval
- information retrieval
- multimedia information retrieval
- document collections
- multimedia data
- query expansion
- multi class
- visual data
- video data
- video sequences
- video content
- retrieval model
- retrieval systems
- image classification
- multimedia databases
- language model
- video frames
- space time
- video retrieval
- multiple features
- feature space
- digital libraries
- learning algorithm