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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use DAN with question and answer attention over a QA story instead of QA CoAttention | Product Compatibility Analysis · Product Compatibility Analysis | PCA F1: 62.9 -> 64.8 | Improved |
| use DAN with question and answer attention over QA CoAttention | Product Compatibility Analysis · Product Compatibility Analysis | CER F1: 79.8 -> 80.9 | Improved |
| add answer attention (ablation) | DAN · Product Compatibility Analysis | Polarity accuracy: 81.5 -> 82.5 | Improved |
| add answer attention (ablation) | DAN · Product Compatibility Analysis | PCA F1: 63.9 -> 64.8 | Improved |
| add answer attention (ablation) | DAN · Product Compatibility Analysis | CER F1: 80.2 -> 80.9 | Improved |
| use DAN with question and answer attention over QA CoAttention | Product Function Satisfiability Analysis · Product Function Satisfiability Analysis | FSA F1: 61.7 -> 63.9 | Improved |
| use DAN with question and answer attention over QA CoAttention | Product Function Satisfiability Analysis · Product Function Satisfiability Analysis | FNR F1: 77.4 -> 78.2 | Improved |
| add answer attention (ablation) | DAN · Product Function Satisfiability Analysis | Polarity accuracy: 83.0 -> 84.3 | Improved |
| add answer attention (ablation) | DAN · Product Function Satisfiability Analysis | FSA F1: 62.5 -> 63.9 | Improved |
| add answer attention (ablation) | DAN · Product Function Satisfiability Analysis | FNR F1: 78.0 -> 78.2 | Improved |
Closest papers by meaning
- Answer Identification from Product Reviews for User Questions by Multi-Task Attentive Networks (AAAI 2019 · similarity 0.85)
- Compatibility Family Learning for Item Recommendation and Generation (AAAI 2018 · similarity 0.84)
- Context-Aware Visual Compatibility Prediction (CVPR 2019 · similarity 0.82)
- TransNFCM: Translation-Based Neural Fashion Compatibility Modeling (AAAI 2019 · similarity 0.82)
- Optimize Incompatible Parameters Through Compatibility-aware Knowledge Integration (AAAI 2025 · similarity 0.80)
- Spectral-Based Graph Neural Networks for Complementary Item Recommendation (AAAI 2024 · similarity 0.80)
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.
