TransFusion: Multi-Modal Fusion for Video Tag Inference via Translation-based Knowledge Embedding.
Di JinZhongang QiYingmin LuoYing ShanPublished in: ACM Multimedia (2021)
Keyphrases
- multi modal fusion
- video data
- video sequences
- knowledge management
- knowledge representation
- knowledge acquisition
- expert systems
- multimedia
- video streams
- video content
- youtube videos
- prior knowledge
- domain knowledge
- knowledge base
- machine translation
- object recognition
- bayesian networks
- three dimensional
- multimedia data