期刊论文

Chen Qiu

英文

Information Processing & Management

0306-4573

2023

60

2

103207

10.1016/j.ipm.2022.103207

This work was supported by the National Natural Science Foundation of China under Grants 61972173 , the Joint Funds of the National Natural Science Foundation of China under Grants U1836118 , and the Fundamental Research Funds for the Central Universities (No. CCNU22QN015 ). We thank Emanuele Bugliarello for the constructive feedback regarding the VOLTA framework implementation. We are grateful to the anonymous reviewers and the associate editor for their insightful comments.

本校为其他机构

Visual Question Answering (VQA) requires reasoning about the visually-grounded relations in the image and question context. A crucial aspect of solving complex questions is reliable multi-hop reasoning, i.e., dynamically learning the interplay between visual entities in each step. In this paper, we investigate the potential of the reasoning graph network on multi-hop reasoning questions, especially over 3 “hops.” We call this model QMRGT: A Question-Guided Multi-hop Reasoning Graph Network. It constructs a cross-modal interaction module (CIM)...