Temporally Multi-Modal Semantic Reasoning with Spatial Language Constraints for Video Question Answering.
Mingyang LiuRuomei WangFan ZhouGe LinPublished in: Symmetry (2022)
Keyphrases
- multi modal
- question answering
- semantic concepts
- natural language
- video search
- semantic parsing
- information extraction
- natural language processing
- semantic roles
- knowledge representation
- question classification
- question answering systems
- cross language
- qa clef
- passage retrieval
- answering questions
- information retrieval
- multiple modalities
- natural language questions
- temporal information
- conceptual graphs
- video shots
- video sequences
- video frames
- audio visual
- answer extraction
- knowledge base
- qa systems
- multimedia
- artificial intelligence
- machine learning
- feature space