AI Paper Atlas

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

High-Order Attention Models for Visual Question Answering

Idan Schwartz, Alexander Schwing, Tamir Hazan

NeurIPS 2017 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 74 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 ternary attention to unary and pairwise attention (ablation)3-modality VQA attention with ResNet · Multiple-Choice VQA test-dev, Allaccuracy: 68.7 -> 69.4Improved
use 3 modalities rather than 2, adding answer attention (ablation)VQA attention with ResNet · Multiple-Choice VQA test-dev, Allaccuracy: 66.7 -> 68.7Improved
use a 2-layer MCB decision unit instead of MCT (ablation)3-modality VQA model · Multiple-Choice VQA validationaccuracy: 63.82% -> 64.57%Improved
use multiple sized convolution filters for question embeddings (ablation)Question embedding · VQAperformanceNo clear effect
use tensor sketching units rather than element-wise multiplication, addition, or concatenation (ablation)VQA decision making · VQAperformanceImproved

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