AI Paper Atlas

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

Dual Attention Network for Product Compatibility and Function Satisfiability Analysis

Hu Xu, Sihong Xie, Lei Shu, Philip S. Yu

AAAI 2018 · Vision-language and multimodal › Visual question answering · approach: Open-domain multimodal QA · 12 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
use DAN with question and answer attention over a QA story instead of QA CoAttentionProduct Compatibility Analysis · Product Compatibility AnalysisPCA F1: 62.9 -> 64.8Improved
use DAN with question and answer attention over QA CoAttentionProduct Compatibility Analysis · Product Compatibility AnalysisCER F1: 79.8 -> 80.9Improved
add answer attention (ablation)DAN · Product Compatibility AnalysisPolarity accuracy: 81.5 -> 82.5Improved
add answer attention (ablation)DAN · Product Compatibility AnalysisPCA F1: 63.9 -> 64.8Improved
add answer attention (ablation)DAN · Product Compatibility AnalysisCER F1: 80.2 -> 80.9Improved
use DAN with question and answer attention over QA CoAttentionProduct Function Satisfiability Analysis · Product Function Satisfiability AnalysisFSA F1: 61.7 -> 63.9Improved
use DAN with question and answer attention over QA CoAttentionProduct Function Satisfiability Analysis · Product Function Satisfiability AnalysisFNR F1: 77.4 -> 78.2Improved
add answer attention (ablation)DAN · Product Function Satisfiability AnalysisPolarity accuracy: 83.0 -> 84.3Improved
add answer attention (ablation)DAN · Product Function Satisfiability AnalysisFSA F1: 62.5 -> 63.9Improved
add answer attention (ablation)DAN · Product Function Satisfiability AnalysisFNR F1: 78.0 -> 78.2Improved

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