Video-text retrieval via multi-modal masked transformer and adaptive attribute-aware graph convolutional network.
Gang LvYining SunFudong NianPublished in: Multim. Syst. (2024)
Keyphrases
- multi modal
- text retrieval
- semantic concepts
- video search
- convolutional network
- document retrieval
- convolutional neural networks
- information retrieval
- video data
- multiple modalities
- multimedia
- query expansion
- document collections
- retrieval systems
- multimedia retrieval
- video sequences
- image retrieval
- retrieval model
- video content
- video retrieval
- multimedia data
- image annotation
- high dimensional
- probabilistic model
- multiresolution
- language model