The main challenge in video question answering (VideoQA) is to capture and understand the complex spatial and temporal relations between objects based on given questions. Existing graph-based methods for VideoQA usually ignore keywords in questions and employ a simple graph to aggregate features without considering relative relations between objects, which may lead to inferior performance. In this paper, we propose a Keyword-aware Relative Spatio-Temporal (KRST) graph network for VideoQA. First, to make question features aware of keywords, we employ an attention mechanism to assign high weights to keywords during question encoding. The keyword-aware question features are then used to guide video graph construction. Second, because relations are relative, we integrate the relative relation modeling to better capture the spatio-temporal dynamics among object nodes. Moreover, we disentangle the spatio-temporal reasoning into an object-level spatial graph and a frame-level temporal graph, which reduces the impact of spatial and temporal relation reasoning on each other. Extensive experiments on the TGIF-QA, MSVD-QA and MSRVTT-QA datasets demonstrate the superiority of our KRST over multiple state-of-the-art methods.
@article{arxiv.2307.13250,
title = {Keyword-Aware Relative Spatio-Temporal Graph Networks for Video Question Answering},
author = {Yi Cheng and Hehe Fan and Dongyun Lin and Ying Sun and Mohan Kankanhalli and Joo-Hwee Lim},
journal= {arXiv preprint arXiv:2307.13250},
year = {2023}
}