MIVCN: Multimodal interaction video captioning network based on semantic association graph.
Ying WangGuoheng HuangLin YumingHaoliang YuanChi-Man PunWing-Kuen LingLianglun ChengPublished in: Appl. Intell. (2022)
Keyphrases
- multimodal interaction
- association graph
- multimedia
- video sequences
- graph matching
- document representation
- semantic information
- multimedia data
- relational structures
- graph theoretic
- high level
- text to speech
- natural language
- maximal cliques
- brain computer interface
- bag of words
- co occurrence
- information extraction
- tree nodes
- image processing