Research map / Vision-language and multimodal / Visual question answering
Re-Attention for 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 |
|---|---|---|---|
| add cross attention module (ablation) | base attention VQA model · VQA v2 val | overall accuracy: 65.34 -> 66.62 | Helped |
| add answer-guided re-attention branch (ablation) | base attention VQA model · VQA v2 val | overall accuracy: 65.34 -> 66.89 | Helped |
| add re-attention branch on top of cross attention (ablation) | base+co · VQA v2 val | overall accuracy: 66.62 -> 67.15 | Helped |
| add re-attention branch (ablation) | base · VQA v2 val | Number accuracy: 44.71 -> 49.30 | Helped |
| vary re-attention weight lambda_r from 0.2 to 2.0 (ablation) | base+co+re-att · VQA v2 val | overall accuracy: 66.80-67.15 | No clear effect |
| full Re-Attention model vs VCTREE-HL | VQA · VQA v2 test-dev | overall accuracy: 68.19 -> 70.43 | Helped |
Closest papers by meaning
- Hierarchical Question-Image Co-Attention for Visual Question Answering (NeurIPS 2016 · similarity 0.93)
- Multi-Level Attention Networks for Visual Question Answering (CVPR 2017 · similarity 0.92)
- Making the v in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering (CVPR 2017 · similarity 0.92)
- REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering (NeurIPS 2022 · similarity 0.92)
- FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering (NeurIPS 2025 · similarity 0.91)
- When Open-Vocabulary Visual Question Answering Meets Causal Adapter: Benchmark and Approach (AAAI 2025 · 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.