AI Paper Atlas

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

VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering

Yanan Wang, Michihiro Yasunaga, Hongyu Ren, Shinya Wada, Jure Leskovec

ICCV 2023 · Vision-language and multimodal › Visual question answering · approach: Universal VQA models · 88 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 VQA-GNN on top of RESERVE-LRESERVE-L · VCR testQ->AR accuracy: 72.0 -> 74.3Improved
replace SGEITL+VLBERT with VQA-GNNSGEITL+VLBERT · VCR testQ->AR accuracy: 59.6 -> 62.8Improved
use two modality-specialized GNNs instead of a single GNN (ablation)VQA-GNN · VCR val (Q->A)accuracy: 73.0 -> 75.1Improved
use two modality-specialized GNNs instead of single GNN with cross-modal edges (ablation)VQA-GNN · VCR val (Q->A)accuracy: 70.6 -> 75.1Improved
remove direct cross-modal edges in a single GNN (ablation)single GNN · VCR val (Q->A)accuracy: 70.6 -> 73.0Improved
add QA-concept node p (ablation)scene-graph + concept-graph · VCR val (Q->A)accuracy: 75.1 -> 77.1Improved
add scene graph to node z and p (ablation)Node z · VCR val (Q->A)accuracy: 53.8 -> 73.7Improved
add concept graph to node z (ablation)Node z · VCR val (Q->A)accuracy: 53.8 -> 69.0Improved
use bidirectional fusion instead of unidirectional fusion (ablation)VQA-GNN · GQA valaccuracy: 86.3 -> 90.3Improved
use bidirectional fusion instead of average pooling (ablation)VQA-GNN · GQA valaccuracy: 62.3 -> 90.3Improved
interconnect visual and textual scene graphs (ablation)VQA-GNN · GQA valaccuracy: 87.9 -> 90.3Improved
replace GCN with VQA-GNN (textual SG)GCN · GQA valaccuracy: 85.7 -> 87.9Improved

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