Research map / Vision-language and multimodal / Visual question answering
KVQA: Knowledge-Aware Visual Question Answering
Read the paperCheck 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 |
|---|---|---|---|
| use memory network instead of BLSTM over KG facts | KVQA baseline · KVQA open world, +wikiCap ORG | accuracy: 20.6 -> 36.8 | Helped |
| move from closed world to open world entity set | MemNet · KVQA +wikiCap ORG | accuracy: 50.2 -> 36.8 | Hurt |
| paraphrase test questions | MemNet · KVQA closed world -wikiCap | accuracy: 49.5 -> 32.0 | Hurt |
| add Wikipedia captions as input | MemNet · KVQA closed world ORG | accuracy: 49.5 -> 50.2 | No clear effect |
Closest papers by meaning
- OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge (CVPR 2019 · similarity 0.95)
- REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering (NeurIPS 2022 · similarity 0.93)
- VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning (CVPR 2024 · similarity 0.93)
- Separation of Powers: On Segregating Knowledge from Observation in LLM-enabled Knowledge-based Visual Question Answering (CVPR 2025 · similarity 0.92)
- When Open-Vocabulary Visual Question Answering Meets Causal Adapter: Benchmark and Approach (AAAI 2025 · similarity 0.92)
- CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark (NeurIPS 2024 · 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.