Research map / Vision-language and multimodal / Visual question answering
Towards VQA Models That Can Read
Amanpreet Singh, Vivek Natarajan, Meet Shah, Yu Jiang, Xinlei Chen, Dhruv Batra, Devi Parikh, Marcus Rohrbach
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 OCR token features to Pythia (ablation) | Pythia on TextVQA · TextVQA val | accuracy: 13.04 -> 18.35 | Improved |
| Add OCR tokens and the copy mechanism, allowing answers only from OCR tokens (ablation) | Pythia on TextVQA · TextVQA val | accuracy: 13.04 -> 20.06 | Improved |
| Add LoRRA with the large answer vocabulary (ablation) | Pythia on TextVQA · TextVQA val | accuracy: 13.04 -> 26.23 | Improved |
| Replace the large answer vocabulary with the short answer vocabulary (ablation) | Pythia + LoRRA on TextVQA · TextVQA val | accuracy: 26.23 -> 26.56 | Improved |
| Add LoRRA to BAN (ablation) | BAN on TextVQA · TextVQA val | accuracy: 12.30 -> 18.41 | Improved |
| Add LoRRA to Pythia v0.3 | Pythia v0.3 on VQA 2.0 · VQA 2.0 test-dev | accuracy: 68.71 -> 69.21 | Improved |
Closest papers by meaning
- VQA: Visual Question Answering (IJCV 2016 · similarity 0.94)
- Grounding Answers for Visual Questions Asked by Visually Impaired People (CVPR 2022 · similarity 0.91)
- When Open-Vocabulary Visual Question Answering Meets Causal Adapter: Benchmark and Approach (AAAI 2025 · similarity 0.90)
- Right this way: Can VLMs Guide Us to See More to Answer Questions? (NeurIPS 2024 · similarity 0.89)
- VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning (CVPR 2024 · similarity 0.89)
- BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions (AAAI 2024 · similarity 0.89)
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.
