Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering

Yang Liu, Guanbin Li, Liang Lin

Abstract: Existing visual question answering methods often suffer from cross-modal spurious correlations and oversimplified event-level reasoning processes that fail to capture event temporality, causality, and dynamics spanning over the video. In this work, to address the task of event-level visual question answering, we propose a framework for cross-modal causal relational reasoning. In particular, a set of causal intervention operations is introduced to discover the underlying causal structures across visual and linguistic modalities. Our framework, named <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</b> ross- <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</b> odal <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</b> ausal Relat <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">I</b> onal <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</b> easoning (CMCIR), involves three modules: i) Causality-aware Visual-Linguistic Reasoning (CVLR) module for collaboratively disentangling the visual and linguistic spurious correlations via front-door and back-door causal interventions; ii) Spatial-Temporal Transformer (STT) module for capturing the fine-grained interactions between visual and linguistic semantics; iii) Visual-Linguistic Feature Fusion (VLFF) module for learning the global semantic-aware visual-linguistic representations adaptively. Extensive experiments on four event-level datasets demonstrate the superiority of our CMCIR in discovering visual-linguistic causal structures and achieving robust event-level visual question answering.