Research map / Vision-language and multimodal / Visual question answering
The VQA-Machine: Learning How to Use Existing Vision Algorithms to Answer New Questions
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 ground-truth attribute facts to object facts (ablation) | VQA-Machine · Visual Genome QA test | accuracy (%): 34.77 -> 37.50 | Helped |
| Add ground-truth relationship facts to object facts (ablation) | VQA-Machine · Visual Genome QA test | accuracy (%): 34.77 -> 35.15 | Helped |
| Use ground-truth object, attribute, and relationship facts together (ablation) | VQA-Machine · Visual Genome QA test | accuracy (%): 34.77 -> 38.06 | Helped |
| Add VGG image features to the ground-truth fact inputs (ablation) | VQA-Machine · Visual Genome QA test | accuracy (%): 38.06 -> 39.30 | Helped |
| Add predicted scene-category facts (ablation) | VQA-Machine with predicted facts · Visual Genome QA test | accuracy (%): 34.01 -> 35.20 | Helped |
| Add VGG image features to predicted object, attribute, and relationship facts (ablation) | VQA-Machine · Visual Genome QA test | accuracy (%): 34.01 -> 36.44 | Helped |
| Add VGG image features and predicted scene facts to predicted object, attribute, and relationship facts (ablation) | VQA-Machine · Visual Genome QA test | accuracy (%): 35.20 -> 36.99 | Helped |
| Use predicted rather than ground-truth object, attribute, and relationship facts (ablation) | VQA-Machine · Visual Genome QA test | accuracy (%): 38.06 -> 34.01 | Hurt |
Closest papers by meaning
- Tips and Tricks for Visual Question Answering: Learnings From the 2017 Challenge (CVPR 2018 · similarity 0.94)
- Making the v in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering (CVPR 2017 · similarity 0.92)
- OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge (CVPR 2019 · similarity 0.92)
- Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering (CVPR 2018 · similarity 0.92)
- When Open-Vocabulary Visual Question Answering Meets Causal Adapter: Benchmark and Approach (AAAI 2025 · similarity 0.91)
- VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning (CVPR 2024 · similarity 0.90)
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.