Trust Your Partner's Friends: Hierarchical Cross-Modal Contrastive Pre-Training for Video-Text Retrieval.
Yuhan XiangKaijian LiuShixiang TangLei BaiFeng ZhuRui ZhaoXianming LinPublished in: ICASSP (2023)
Keyphrases
- text retrieval
- cross modal
- multimedia retrieval
- image retrieval
- multi modal
- visual data
- video data
- multimedia data
- multimedia
- information retrieval
- document retrieval
- query expansion
- video content
- retrieval model
- document collections
- multimedia information retrieval
- retrieval systems
- video frames
- multimedia databases
- video sequences
- semantic concepts
- training set
- video analysis
- high dimensional
- video retrieval
- visual content
- visual recognition
- image sequences
- image database