LSECA: local semantic enhancement and cross aggregation for video-text retrieval.
Zhiwen WangDonglin ZhangZhikai HuPublished in: Int. J. Multim. Inf. Retr. (2024)
Keyphrases
- text retrieval
- information retrieval
- semantic concepts
- multimedia
- document collections
- video data
- text representation
- latent semantic indexing
- inverted file
- document retrieval
- query expansion
- video sequences
- cross language
- retrieval model
- image retrieval
- retrieval systems
- video content
- multimedia information retrieval
- image processing
- automatic query expansion
- retrieval quality
- textual information retrieval
- semantic similarity
- low level features
- digital libraries
- retrieval effectiveness
- key frames
- feature selection