HAIR: Hierarchical Visual-Semantic Relational Reasoning for Video Question Answering.

Fei Liu Jing Liu Weining Wang Hanqing Lu

Published in: ICCV (2021)

Keyphrases

question answering
natural language
semantic parsing
semantic roles
question answering systems
visual data
information extraction
question classification
answering questions
information retrieval

visual information
video data
natural language processing
passage retrieval
multimedia
named entities
video search
video sequences
answer extraction
syntactic information

high level
semantic information
relational databases
cross language
video content
visual features
relation extraction
qa clef
knowledge base

semantic relationships
semantic analysis
video retrieval
knowledge representation
candidate answers
key frames
document collections
data model
answer validation