Neural-Symbolic VideoQA: Learning Compositional Spatio-Temporal Reasoning for Real-world Video Question Answering

TL;DR

This paper introduces NS-VideoQA, a neural-symbolic framework that enhances compositional spatio-temporal reasoning in real-world VideoQA by transforming videos into symbolic representations and applying top-down reasoning, leading to improved accuracy.

Contribution

It presents a novel neural-symbolic approach with a Scene Parser Network and a Symbolic Reasoning Machine for better reasoning in VideoQA tasks, enabling step-by-step analysis.

Findings

Improves reasoning accuracy on AGQA Decomp benchmark

Enables step-by-step error analysis

Enhances logical inference capabilities

Abstract

Compositional spatio-temporal reasoning poses a significant challenge in the field of video question answering (VideoQA). Existing approaches struggle to establish effective symbolic reasoning structures, which are crucial for answering compositional spatio-temporal questions. To address this challenge, we propose a neural-symbolic framework called Neural-Symbolic VideoQA (NS-VideoQA), specifically designed for real-world VideoQA tasks. The uniqueness and superiority of NS-VideoQA are two-fold: 1) It proposes a Scene Parser Network (SPN) to transform static-dynamic video scenes into Symbolic Representation (SR), structuralizing persons, objects, relations, and action chronologies. 2) A Symbolic Reasoning Machine (SRM) is designed for top-down question decompositions and bottom-up compositional reasonings. Specifically, a polymorphic program executor is constructed for internally consistent reasoning from SR to the final answer. As a result, Our NS-VideoQA not only improves the compositional spatio-temporal reasoning in real-world VideoQA task, but also enables step-by-step error analysis by tracing the intermediate results. Experimental evaluations on the AGQA Decomp benchmark demonstrate the effectiveness of the proposed NS-VideoQA framework. Empirical studies further confirm that NS-VideoQA exhibits internal consistency in answering compositional questions and significantly improves the capability of spatio-temporal and logical inference for VideoQA tasks.