Research map / Vision-language and multimodal / Visual question answering
OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge
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 ArticleNet sentence representations | MUTAN · OK-VQA test | VQA score: 26.41 -> 27.84 | Helped |
| Add ArticleNet sentence representations | BAN · OK-VQA test | VQA score: 25.17 -> 25.61 | Helped |
| Use ResNet50 instead of ResNet152 image features (ablation) | MUTAN · OK-VQA test | VQA score: 26.41 -> 24.74 | Hurt |
| Use ResNet18 instead of ResNet152 image features (ablation) | MUTAN · OK-VQA test | VQA score: 26.41 -> 23.64 | Hurt |
| Add image features rather than use question features alone (ablation) | MUTAN · OK-VQA test | VQA score: 14.93 -> 23.64 | Helped |
Closest papers by meaning
- KVQA: Knowledge-Aware Visual Question Answering (AAAI 2019 · similarity 0.95)
- TOA: Task-oriented Active VQA (NeurIPS 2023 · similarity 0.94)
- REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering (NeurIPS 2022 · similarity 0.94)
- Making the v in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering (CVPR 2017 · similarity 0.94)
- When Open-Vocabulary Visual Question Answering Meets Causal Adapter: Benchmark and Approach (AAAI 2025 · similarity 0.93)
- Separation of Powers: On Segregating Knowledge from Observation in LLM-enabled Knowledge-based Visual Question Answering (CVPR 2025 · similarity 0.92)
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.