Research map / Vision-language and multimodal / Visual question answering
Ask Me Anything: Free-Form Visual Question Answering Based on Knowledge From External Sources
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 image captions to the attribute representation (ablation) | Att-LSTM · Toronto COCO-QA | accuracy (%): 61.38 -> 69.02 | Helped |
| Add external knowledge to the attribute-and-caption representation (ablation) | Att+Cap-LSTM · Toronto COCO-QA | accuracy (%): 69.02 -> 69.73 | Helped |
| Add captions and external knowledge to the attribute representation (ablation) | Att-LSTM · VQA validation | overall accuracy: 51.60 -> 55.96 | Helped |
| Add image captions to the attribute representation (ablation) | Att-LSTM · VQA validation | overall accuracy: 51.60 -> 55.04 | Helped |
| Add external knowledge to the attribute representation (ablation) | Att-LSTM · VQA validation | overall accuracy: 51.60 -> 53.79 | Helped |
| Add external knowledge to the attribute-and-caption representation (ablation) | Att+Cap-LSTM · VQA validation | overall accuracy: 55.04 -> 55.96 | Helped |
| Add external knowledge to attribute-only inputs (ablation) | Att-LSTM · VQA validation, Why questions | accuracy (%): 7.77% -> 11.88% | Helped |
| Use the top-10 rather than top-5 attributes for knowledge-base queries (ablation) | Att+Cap+Know-LSTM · VQA | performance | No clear effect |
Closest papers by meaning
- An Empirical Evaluation of Visual Question Answering for Novel Objects (CVPR 2017 · similarity 0.92)
- Visual Question Answering with Question Representation Update (QRU) (NeurIPS 2016 · similarity 0.92)
- Multi-Level Attention Networks for Visual Question Answering (CVPR 2017 · similarity 0.91)
- Graph-Structured Representations for Visual Question Answering (CVPR 2017 · similarity 0.91)
- VQA With No Questions-Answers Training (CVPR 2020 · similarity 0.91)
- Separation of Powers: On Segregating Knowledge from Observation in LLM-enabled Knowledge-based Visual Question Answering (CVPR 2025 · 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.