Video Graph Transformer for Video Question Answering

TL;DR

The paper introduces a Video Graph Transformer (VGT) that enhances Video Question Answering by explicitly modeling visual object relations and disentangling video and text processing, achieving superior performance without extensive pretraining.

Contribution

It presents a novel dynamic graph transformer module and disentangled video-text transformers, improving reasoning and accuracy in VideoQA tasks beyond prior models.

Findings

VGT outperforms prior arts in pretraining-free scenarios.

Self-supervised pretraining further boosts VGT performance.

VGT demonstrates data efficiency and superior relation reasoning in videos.

Abstract

This paper proposes a Video Graph Transformer (VGT) model for Video Quetion Answering (VideoQA). VGT's uniqueness are two-fold: 1) it designs a dynamic graph transformer module which encodes video by explicitly capturing the visual objects, their relations, and dynamics for complex spatio-temporal reasoning; and 2) it exploits disentangled video and text Transformers for relevance comparison between the video and text to perform QA, instead of entangled cross-modal Transformer for answer classification. Vision-text communication is done by additional cross-modal interaction modules. With more reasonable video encoding and QA solution, we show that VGT can achieve much better performances on VideoQA tasks that challenge dynamic relation reasoning than prior arts in the pretraining-free scenario. Its performances even surpass those models that are pretrained with millions of external data. We further show that VGT can also benefit a lot from self-supervised cross-modal pretraining, yet with orders of magnitude smaller data. These results clearly demonstrate the effectiveness and superiority of VGT, and reveal its potential for more data-efficient pretraining. With comprehensive analyses and some heuristic observations, we hope that VGT can promote VQA research beyond coarse recognition/description towards fine-grained relation reasoning in realistic videos. Our code is available at https://github.com/sail-sg/VGT.