Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection.
Yicheng XiaoZhuoyan LuoYong LiuYue MaHengwei BianYatai JiYujiu YangXiu LiPublished in: CoRR (2023)
Keyphrases
- information retrieval
- multimedia
- face detection and tracking
- video indexing
- video sequences
- query expansion
- event detection
- video content
- retrieval framework
- video dataset
- semantic video
- semantic concept detection
- real time
- image retrieval
- image database
- information retrieval systems
- language model
- face detection
- video streams
- multimedia information