Semantics-Enriched Cross-Modal Alignment for Complex-Query Video Moment Retrieval.
Xingyu ShenXiang ZhangXun YangYibing ZhanLong LanJianfeng DongHongzhou WuPublished in: ACM Multimedia (2023)
Keyphrases
- cross modal
- complex queries
- multi modal
- multimedia retrieval
- visual data
- cost model
- multimedia
- image retrieval
- multimedia data
- multimedia databases
- visual similarity
- video data
- semantic concepts
- video sequences
- video streams
- visual recognition
- image database
- video frames
- video content
- low level
- multimedia information retrieval
- video analysis
- user queries
- semantic information
- keywords
- document retrieval
- multimedia documents
- high level
- information retrieval