CRET: Cross-Modal Retrieval Transformer for Efficient Text-Video Retrieval.
Kaixiang JiJiajia LiuWeixiang HongLiheng ZhongJian WangJingdong ChenWei ChuPublished in: SIGIR (2022)
Keyphrases
- video retrieval
- cross modal
- video collections
- video search
- concept based video retrieval
- multi modal
- content based retrieval
- retrieval systems
- multimedia retrieval
- text retrieval
- visual content
- semantic gap
- information retrieval
- visual similarity
- multimedia databases
- video content
- multimedia documents
- image database
- video data
- key frames
- video clips
- multimedia
- semantic content
- visual data
- news video
- relevance feedback
- image retrieval
- multimedia data
- text documents
- text mining