AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

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

Yang Liu, Guanbin Li, Liang Lin

TPAMI 2023 · Vision-language and multimodal › Visual question answering · approach: Multimodal question answering datasets · 377 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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 the hierarchical semantic-role parser (HSRP) (ablation)CMCIR · SUTD-TrafficQAaccuracy: 37.65 -> 38.58Improved
add linguistic back-door causal intervention (ablation)CMCIR · SUTD-TrafficQAaccuracy: 37.71 -> 38.58Improved
add visual front-door causal intervention (ablation)CMCIR · SUTD-TrafficQAaccuracy: 37.68 -> 38.58Improved
add the causality-aware visual-linguistic reasoning module (CVLR) (ablation)CMCIR · SUTD-TrafficQAaccuracy: 37.42 -> 38.58Improved
add semantic graph embedding (ablation)CMCIR · SUTD-TrafficQAaccuracy: 37.93 -> 38.58Improved
add adaptive linguistic feature fusion (ablation)CMCIR · SUTD-TrafficQAaccuracy: 37.84 -> 38.58Improved
add CVLR (ablation)CMCIR · MSVD-QAaccuracy: 42.0 -> 43.7Improved
add CVLR (ablation)CMCIR · MSRVTT-QAaccuracy: 38.0 -> 38.9Improved
add HSRP (ablation)CMCIR · TGIF-QA (Action)accuracy: 75.4 -> 78.1Improved
use 8 MMA heads instead of 1CMCIR · SUTD-TrafficQAaccuracy: 37.83 -> 38.58Improved
use 1 GCN layer instead of 2CMCIR · SUTD-TrafficQAaccuracy: 37.84 -> 38.58Improved
use more MTB layers (3 vs 8)CMCIR · SUTD-TrafficQAaccuracy: 38.58 -> 37.58Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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