Fine-Grained Features Alignment and Fusion for Text-Video Cross-Modal Retrieval.
Shuili ZhangHongzhang MuQuangang LiChenglong XiaoTingwen LiuPublished in: ICASSP (2024)
Keyphrases
- fine grained
- cross modal
- multiple modalities
- coarse grained
- multi modal
- multimedia retrieval
- text retrieval
- video search
- video clips
- information retrieval
- visual data
- multimedia documents
- video data
- access control
- feature vectors
- multimedia
- key frames
- multimedia data
- semantic information
- information retrieval systems
- feature set
- video sequences
- visual recognition
- image retrieval
- video streams
- feature extraction
- visual similarity
- low level
- image database
- video content
- text mining
- multimedia information retrieval
- visual concepts
- multiple features