Video Question Answering via Attribute-Augmented Attention Network Learning

TL;DR

This paper introduces an attribute-augmented attention network that models temporal dynamics and performs multi-step reasoning for improved video question answering, addressing limitations of static image-based methods.

Contribution

It proposes a novel attribute-augmented attention framework with joint attribute detection and multi-step reasoning for video question answering.

Findings

Effective on multiple-choice and open-ended tasks

Improves performance over existing methods

Constructed a large-scale VQA dataset

Abstract

Video Question Answering is a challenging problem in visual information retrieval, which provides the answer to the referenced video content according to the question. However, the existing visual question answering approaches mainly tackle the problem of static image question, which may be ineffectively for video question answering due to the insufficiency of modeling the temporal dynamics of video contents. In this paper, we study the problem of video question answering by modeling its temporal dynamics with frame-level attention mechanism. We propose the attribute-augmented attention network learning framework that enables the joint frame-level attribute detection and unified video representation learning for video question answering. We then incorporate the multi-step reasoning process for our proposed attention network to further improve the performance. We construct a large-scale video question answering dataset. We conduct the experiments on both multiple-choice and open-ended video question answering tasks to show the effectiveness of the proposed method.