MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval.
Yuying GeYixiao GeXihui LiuAlex Jinpeng WangJianping WuYing ShanXiaohu QiePing LuoPublished in: CoRR (2022)
Keyphrases
- text retrieval
- retrieval systems
- information retrieval
- video sequences
- image retrieval
- video data
- multimedia
- inverted file
- document retrieval
- latent semantic indexing
- visual features
- document collections
- retrieval model
- visual information
- video content
- query expansion
- key frames
- visual concepts
- cross language
- video retrieval
- information retrieval systems
- semantic information
- low level
- multimedia data
- language model
- distance measure
- video search
- training set
- automatic query expansion
- textual information retrieval