Research map / Vision-language and multimodal / Visual question answering
Visual7W: Grounded Question Answering in Images
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 spatial attention to the LSTM | LSTM for Visual7W · Visual7W overall | accuracy: 52.1% -> 55.6% | Helped |
| Add spatial attention to the LSTM | LSTM for Visual7W · Visual7W How | accuracy: 0.503 -> 0.498 | Hurt |
| Use both question and image inputs instead of question input alone (ablation) | LSTM · Visual7W overall | accuracy: 0.462 -> 0.521 | Helped |
| Use both question and image inputs instead of image input alone (ablation) | LSTM · Visual7W overall | accuracy: 0.359 -> 0.521 | Helped |
| Add global image features to question features (ablation) | Logistic Regression · Visual7W overall | accuracy: 0.383 -> 0.352 | Hurt |
Closest papers by meaning
- Making the v in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering (CVPR 2017 · similarity 0.91)
- Answer-Type Prediction for Visual Question Answering (CVPR 2016 · similarity 0.90)
- Can I Trust Your Answer? Visually Grounded Video Question Answering (CVPR 2024 · similarity 0.90)
- Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models (ICLR 2024 · similarity 0.89)
- FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering (NeurIPS 2025 · similarity 0.89)
- When Open-Vocabulary Visual Question Answering Meets Causal Adapter: Benchmark and Approach (AAAI 2025 · 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.