Transformer-based vision-language alignment for robot navigation and question answering.

Haonan Luo Ziyu Guo Zhenyu Wu Fei Teng Tianrui Li

Published in: Inf. Fusion (2024)

Keyphrases

question answering
robot navigation
natural language
autonomous robots
scene understanding
natural language processing
vision system
computer vision

information extraction
question classification
information retrieval
passage retrieval
cross language
open domain question answering
syntactic information

question answering systems
relation extraction
qa systems
qa clef
real time
semantic roles
named entities

knowledge base
answer extraction
retrieval systems
object detection
machine learning
sentence retrieval
natural language questions