A Multi-interaction Model with Cross-Branch Feature Fusion for Video-Text Retrieval.
Junting LiDehao WuYuesheng ZhuZhiqiang BaiPublished in: ICONIP (6) (2021)
Keyphrases
- text retrieval
- feature fusion
- interaction model
- virtual environment
- information retrieval
- document retrieval
- multiple features
- multimedia
- document collections
- retrieval model
- image retrieval
- user interface
- query expansion
- feature extraction
- video sequences
- video data
- retrieval systems
- key frames
- machine learning
- mixed initiative
- information retrieval systems
- face recognition
- intelligent systems