AI Paper Atlas

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

CVPR 2023 · Vision-language and multimodal › Visual question answering · approach: Multimodal question answering datasets · 47 citations (OpenAlex)

Read the paper

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 changedWhereMeasuredEffect
Add MCR to B2A with GloVe featuresB2A · Causal-VidQAAcc: 43.26 -> 48.01Improved
Add MCR to B2A with BERT featuresB2A · Causal-VidQAAcc: 49.11 -> 51.06Improved
Add MCR to HGAHGA · NExT-QAAll accuracy: 50.01 -> 52.35Improved
Add the visual causal module (ablation)B2A · Causal-VidQAAcc: 49.11 -> 50.41Improved
Add the textual causal module (ablation)B2A · Causal-VidQAAcc: 49.11 -> 49.57Improved
Use both visual and textual causal modules (ablation)B2A · Causal-VidQAAcc: 49.11 -> 50.96Improved
Set the intervention schedule to k1/k2=3 (ablation)MCR · Causal-VidQAAcc: 46.65; 50.58; 49.58; 48.23; 46.37Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy