Tagging before Alignment: Integrating Multi-Modal Tags for Video-Text Retrieval.
Yizhen ChenJie WangLijian LinZhongang QiJin MaYing ShanPublished in: AAAI (2023)
Keyphrases
- multi modal
- text retrieval
- semantic concepts
- video search
- social tagging
- part of speech
- tag recommendation
- metadata
- document retrieval
- information retrieval
- document collections
- image retrieval
- video data
- retrieval systems
- multimedia retrieval
- multi modality
- multimedia
- image annotation
- multiple modalities
- audio visual
- retrieval model
- video frames
- query expansion
- video sequences
- keywords
- high dimensional
- video content
- video analysis
- video shots
- multimedia information retrieval
- key frames
- video retrieval
- image search
- digital libraries
- similarity measure