Relation Triplet Construction for Cross-modal Text-to-Video Retrieval.
Xue SongJingjing ChenYu-Gang JiangPublished in: ACM Multimedia (2023)
Keyphrases
- video retrieval
- cross modal
- video search
- concept based video retrieval
- multi modal
- visual content
- multimedia retrieval
- visual similarity
- retrieval systems
- content based retrieval
- semantic gap
- text retrieval
- visual data
- video content
- video data
- key frames
- image retrieval
- information retrieval
- video clips
- text mining
- multimedia
- text documents
- semantic content
- keywords
- video streams
- natural language processing
- relevance feedback
- probabilistic model