Research map / Vision-language and multimodal / Visual question answering
High-Order Attention Models for Visual Question Answering
Idan Schwartz, Alexander Schwing, Tamir Hazan
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 |
|---|---|---|---|
| add ternary attention to unary and pairwise attention (ablation) | 3-modality VQA attention with ResNet · Multiple-Choice VQA test-dev, All | accuracy: 68.7 -> 69.4 | Improved |
| use 3 modalities rather than 2, adding answer attention (ablation) | VQA attention with ResNet · Multiple-Choice VQA test-dev, All | accuracy: 66.7 -> 68.7 | Improved |
| use a 2-layer MCB decision unit instead of MCT (ablation) | 3-modality VQA model · Multiple-Choice VQA validation | accuracy: 63.82% -> 64.57% | Improved |
| use multiple sized convolution filters for question embeddings (ablation) | Question embedding · VQA | performance | No clear effect |
| use tensor sketching units rather than element-wise multiplication, addition, or concatenation (ablation) | VQA decision making · VQA | performance | Improved |
Closest papers by meaning
- An Analysis of Visual Question Answering Algorithms (ICCV 2017 · similarity 0.92)
- Improved Fusion of Visual and Language Representations by Dense Symmetric Co-Attention for Visual Question Answering (CVPR 2018 · similarity 0.91)
- Multi-Level Attention Networks for Visual Question Answering (CVPR 2017 · similarity 0.91)
- Re-Attention for Visual Question Answering (AAAI 2020 · similarity 0.91)
- Hierarchical Question-Image Co-Attention for Visual Question Answering (NeurIPS 2016 · similarity 0.91)
- MRA-Net: Improving VQA Via Multi-Modal Relation Attention Network (TPAMI 2020 · similarity 0.91)
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.
