Research map / Vision-language and multimodal / Visual question answering
Discovering the Real Association: Multimodal Causal Reasoning in Video Question Answering
Chuanqi Zang, Hanqing Wang, Mingtao Pei, Wei Liang
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add MCR to B2A with GloVe features | B2A · Causal-VidQA | Acc: 43.26 -> 48.01 | Improved |
| Add MCR to B2A with BERT features | B2A · Causal-VidQA | Acc: 49.11 -> 51.06 | Improved |
| Add MCR to HGA | HGA · NExT-QA | All accuracy: 50.01 -> 52.35 | Improved |
| Add the visual causal module (ablation) | B2A · Causal-VidQA | Acc: 49.11 -> 50.41 | Improved |
| Add the textual causal module (ablation) | B2A · Causal-VidQA | Acc: 49.11 -> 49.57 | Improved |
| Use both visual and textual causal modules (ablation) | B2A · Causal-VidQA | Acc: 49.11 -> 50.96 | Improved |
| Set the intervention schedule to k1/k2=3 (ablation) | MCR · Causal-VidQA | Acc: 46.65; 50.58; 49.58; 48.23; 46.37 | Improved |
Closest papers by meaning
- Invariant Grounding for Video Question Answering (CVPR 2022 · similarity 0.91)
- Hierarchical Conditional Relation Networks for Multimodal Video Question Answering (IJCV 2021 · similarity 0.90)
- Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering (TPAMI 2023 · similarity 0.90)
- Cross-modal Causal Relation Alignment for Video Question Grounding (CVPR 2025 · similarity 0.89)
- VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection (CVPR 2025 · similarity 0.89)
- When Open-Vocabulary Visual Question Answering Meets Causal Adapter: Benchmark and Approach (AAAI 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
