Research map / Vision-language and multimodal / Visual question answering
Answer-Type Prediction for Visual Question Answering
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 |
|---|---|---|---|
| Combine the Bayesian model with a discriminative classifier | VQA models · COCO-QA | accuracy: 62.27 -> 63.18 | Helped |
| Combine the Bayesian model with a discriminative classifier | VQA models · DAQUAR-FULL | accuracy: 28.39 -> 28.96 | Helped |
| Combine the Bayesian model with a discriminative classifier | VQA models · Visual7W | top-1 accuracy: 22.07 -> 22.29 | Helped |
| Remove explicit answer-type prediction (ablation) | BAYESIAN · COCO-QA | accuracy: 57.33 -> 59.02 | Hurt |
| Remove explicit answer-type prediction (ablation) | BAYESIAN · DAQUAR-FULL and DAQUAR-37 | accuracy | No clear effect |
| Use extended answer types instead of default answer types (ablation) | HYB-MLP · COCO-VQA Test-Dev | accuracy: 59.30 -> 59.57 | Helped |
| Use extended answer types instead of default answer types (ablation) | HYBRID · COCO-VQA Test-Dev | accuracy: 55.68 -> 56.00 | Helped |
| Combine the Bayesian model with a discriminative classifier | VQA models · DAQUAR-37 | accuracy: 43.79 -> 45.17 | Helped |
| Combine the Bayesian model with a discriminative classifier | VQA models · COCO-QA | WUPS 0.9: 72.36 -> 73.14 | Helped |
Closest papers by meaning
- Answer Them All! Toward Universal Visual Question Answering Models (CVPR 2019 · similarity 0.94)
- When Open-Vocabulary Visual Question Answering Meets Causal Adapter: Benchmark and Approach (AAAI 2025 · similarity 0.94)
- Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering (CVPR 2018 · similarity 0.93)
- OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge (CVPR 2019 · similarity 0.93)
- Self-Critical Reasoning for Robust Visual Question Answering (NeurIPS 2019 · similarity 0.93)
- Tips and Tricks for Visual Question Answering: Learnings From the 2017 Challenge (CVPR 2018 · similarity 0.93)
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.