Fewer Steps, Better Performance: Efficient Cross-Modal Clip Trimming for Video Moment Retrieval Using Language.
Xiang FangDaizong LiuWanlong FangPan ZhouZichuan XuWenzheng XuJunyang ChenRenfu LiPublished in: AAAI (2024)
Keyphrases
- cross modal
- multi modal
- multimedia retrieval
- visual data
- video clips
- image retrieval
- multimedia
- multimedia data
- multimedia databases
- video sequences
- information retrieval systems
- video data
- query expansion
- video content
- image database
- visual recognition
- video streams
- multimedia information retrieval
- key frames
- document retrieval
- retrieval systems
- high level