VoP: Text-Video Co-Operative Prompt Tuning for Cross-Modal Retrieval.
Siteng HuangBiao GongYulin PanJianwen JiangYiliang LvYuyuan LiDonglin WangPublished in: CVPR (2023)
Keyphrases
- cross modal
- multiple modalities
- multi modal
- multimedia retrieval
- video search
- visual data
- text retrieval
- image retrieval
- multimedia documents
- multimedia
- multimedia data
- multimedia databases
- information retrieval
- visual recognition
- visual similarity
- video data
- video content
- video sequences
- multimedia information retrieval
- semantic content
- semantic concepts
- video streams
- content based retrieval
- video clips
- video analysis
- video frames
- test collection
- text mining
- co occurrence
- search engine
- digital libraries
- video retrieval
- key frames
- language model
- image database