Cross-Domain Modality Fusion for Dense Video Captioning.
Nayyer AafaqAjmal MianWei LiuNaveed AkhtarMubarak ShahPublished in: IEEE Trans. Artif. Intell. (2022)
Keyphrases
- cross domain
- multi domain
- domain adaptation
- transfer learning
- multi modal
- sentiment classification
- video sequences
- video frames
- knowledge transfer
- multimedia
- text categorization
- video data
- key frames
- target domain
- video content
- biologically inspired
- video retrieval
- e government
- software engineering
- pairwise
- natural language
- web image annotation