Target-Aware Spatio-Temporal Reasoning via Answering Questions in Dynamic Audio-Visual Scenarios.

Yuanyuan Jiang Jianqin Yin

Published in: EMNLP (Findings) (2023)

Keyphrases

temporal reasoning
audio visual
answering questions
multi modal
temporal information
visual information
qualitative and quantitative
event calculus
spatio temporal
spatial reasoning
reasoning tasks
visual data
question answering
space time
computer vision
passage retrieval
question answering systems
databases