Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval.
Haowei LiuYaya ShiHaiyang XuChunfeng YuanQinghao YeChenliang LiMing YanJi ZhangFei HuangBing LiWeiming HuPublished in: CoRR (2024)
Keyphrases
- text retrieval
- information retrieval
- image retrieval
- document collections
- inverted file
- cross language
- document retrieval
- query expansion
- video data
- retrieval systems
- retrieval model
- video sequences
- video content
- temporal information
- space time
- information extraction
- latent semantic indexing
- video search
- probabilistic model
- automatic query expansion