LLaViLo: Boosting Video Moment Retrieval via Adapter-Based Multimodal Modeling.
Kaijing MaXianghao ZangZerun FengHan FangChao BanYuhan WeiZhongjiang HeYongxiang LiHao SunPublished in: ICCV (Workshops) (2023)
Keyphrases
- multimedia
- video data
- content based video
- video sequences
- video indexing
- real time
- information retrieval
- video search
- multimedia information
- video streams
- content based indexing
- video content
- news video
- story segmentation
- document retrieval
- image database
- semantic video
- content based video retrieval
- video dataset
- audio visual content
- multimedia documents
- video analysis
- retrieval model
- video frames
- information retrieval systems
- image retrieval
- audio visual
- visual data
- multimedia databases
- video clips
- broadcast news
- lifelog
- video collections
- video retrieval
- key frames
- multimedia search