TASTA: Text-Assisted Spatial and Temporal Attention Network for Video Question Answering.
Tian WangBoyao HouJiakun LiPeng ShiBaochang ZhangHichem SnoussiPublished in: Adv. Intell. Syst. (2023)
Keyphrases
- spatial and temporal
- question answering
- syntactic information
- information retrieval
- video frames
- space time
- spatio temporal
- question classification
- textual entailment recognition
- spatial temporal
- natural language processing
- temporal domain
- text summarization
- passage retrieval
- information extraction
- named entities
- qa clef
- spatial and temporal information
- video data
- dynamic textures
- natural language questions
- relation extraction
- free text
- cross language
- text documents
- text mining
- text retrieval
- natural language
- video sequences
- semantic roles
- semantic information
- keywords
- question answer pairs
- question answering systems
- answer extraction
- computer vision