Multi-View Visual Question Answering with Active Viewpoint Selection

Multi-View Visual Question Answering with Active Viewpoint Selection

This paper proposes a framework that allows the observation of a scene iteratively to answer a given question about the scene. Conventional visual question answering (VQA) methods are designed to answer given questions based on single-view images. However, in real-world applications, such as human–r...

Full description

Bibliographic Details
Main Authors: Yue Qiu, Yutaka Satoh, Ryota Suzuki, Kenji Iwata, Hirokatsu Kataoka
Format: Article
Language:English
Published: MDPI AG 2020-04-01
Series:Sensors
Subjects:
visual question answering
three-dimensional (3D) vision
reinforcement learning
deep learning
human–robot interaction
Online Access:https://www.mdpi.com/1424-8220/20/8/2281

Internet

https://www.mdpi.com/1424-8220/20/8/2281

Similar Items