What Matters: Attentive and Relational Feature Aggregation Network for Video-Text Retrieval.
Xiaoshuai HaoYucan ZhouDayan WuWanqian ZhangBo LiWeiping WangDan MengPublished in: ICME (2021)
Keyphrases
- text retrieval
- image retrieval
- latent semantic indexing
- document collections
- inverted file
- cross language
- query expansion
- retrieval model
- information retrieval
- multimedia
- retrieval systems
- document retrieval
- automatic query expansion
- video sequences
- video data
- video content
- video streams
- feature vectors
- relational databases
- databases
- action recognition
- database
- information retrieval systems
- machine learning