Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss.
Xing ChengHezheng LinXiangyu WuFan YangDong ShenPublished in: CoRR (2021)
Keyphrases
- text retrieval
- multi stream
- audio visual speech recognition
- retrieval systems
- document retrieval
- query expansion
- document collections
- information retrieval
- audio visual
- video data
- hidden markov models
- cross language
- multimedia
- video content
- video sequences
- video retrieval
- retrieval model
- key frames
- image retrieval
- video search
- visual data
- data sets