Multilevel Hierarchical Network with Multiscale Sampling for Video Question Answering

TL;DR

This paper introduces a Multilevel Hierarchical Network with multiscale sampling for VideoQA, effectively integrating multiscale visual appearance and motion information to improve question answering accuracy.

Contribution

It proposes a novel MHN architecture with RMI and PVR modules that leverage multiscale sampling to enhance visual understanding in VideoQA tasks.

Findings

Achieved superior performance on three VideoQA datasets.

Validated the effectiveness of multiscale sampling and hierarchical processing.

Outperformed previous state-of-the-art methods.

Abstract

Video question answering (VideoQA) is challenging given its multimodal combination of visual understanding and natural language processing. While most existing approaches ignore the visual appearance-motion information at different temporal scales, it is unknown how to incorporate the multilevel processing capacity of a deep learning model with such multiscale information. Targeting these issues, this paper proposes a novel Multilevel Hierarchical Network (MHN) with multiscale sampling for VideoQA. MHN comprises two modules, namely Recurrent Multimodal Interaction (RMI) and Parallel Visual Reasoning (PVR). With a multiscale sampling, RMI iterates the interaction of appearance-motion information at each scale and the question embeddings to build the multilevel question-guided visual representations. Thereon, with a shared transformer encoder, PVR infers the visual cues at each level in parallel to fit with answering different question types that may rely on the visual information at relevant levels. Through extensive experiments on three VideoQA datasets, we demonstrate improved performances than previous state-of-the-arts and justify the effectiveness of each part of our method.