Modality Shifting Attention Network for Multi-modal Video Question Answering.
Junyeong KimMinuk MaTrung X. PhamKyungsu KimChang D. YooPublished in: CoRR (2020)
Keyphrases
- multi modal
- question answering
- semantic concepts
- multiple modalities
- video search
- natural language
- information extraction
- natural language processing
- question classification
- high dimensional
- audio visual
- information retrieval
- passage retrieval
- video data
- qa clef
- natural language questions
- syntactic information
- semantic roles
- answer validation
- cross language
- video sequences
- single modality
- multimedia
- cross modal
- multi modality
- candidate answers
- video frames
- answer extraction
- video analysis
- image annotation
- video content