• Pre-process and training code
• Code release to generate own Causal Chains
• Causal Chains Release
• 24 Dec 2025 We release our paper on arxiv.

Existing Causal-Why Video Question Answering (VideoQA) models often struggle with higher-order reasoning, relying on opaque, monolithic pipelines that entangle video understanding, causal inference, and answer generation. These black-box approaches offer limited interpretability and tend to depend on shallow heuristics. We propose a novel, modular paradigm that explicitly decouples causal reasoning from answer generation, introducing natural language causal chains as interpretable intermediate representations. Inspired by human cognitive models, these structured cause-effect sequences bridge low-level video content with high-level causal reasoning, enabling transparent and logically coherent inference. Our two-stage architecture comprises a Causal Chain Extractor (CCE) that generates causal chains from video-question pairs, and a Causal Chain-Driven Answerer (CCDA) that derives answers grounded in these chains. To address the lack of annotated reasoning traces, we introduce a scalable method for generating accurate causal chains from existing datasets. We construct human verified causal chains for 46K samples. We also propose CauCo, a new evaluation metric for causality-oriented captioning. Experiments on three large-scale benchmarks demonstrate that our approach not only outperforms state-of-the-art models, but also yields substantial gains in explainability, user trust, and generalization -- positioning the CCE as a reusable causal reasoning engine across diverse domains.

We appreciate your citations if you find our paper related and useful to your research!

@inproceedings{parmar2026causal,
  title={Causal Chain-Guided Reasoning for Modular and Explainable Causal-Why Video Question Answering},
  author={Parmar, Paritosh and Peh, Eric and Fernando, Basura},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={5860--5870},
  year={2026}
}