Research map / Vision-language and multimodal / Visual question answering
Visual Reference Resolution using Attention Memory for Visual Dialog
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 attention memory for retrieving prior visual attentions | AMEM · MNIST Dialog | answer prediction accuracy: ≈ 16 % points | Helped |
| add history embeddings to attention estimation (ablation) | ATT · MNIST Dialog | answer prediction accuracy: about 17% | Helped |
| add attention memory instead of relying only on history-informed tentative attention | AMEM · MNIST Dialog | answer prediction accuracy | Helped |
| add history embeddings (ablation) | AMEM · MNIST Dialog | answer prediction accuracy: 1.7% | Helped |
| add sequential preference to memory addressing (ablation) | AMEM · MNIST Dialog | answer prediction accuracy: >96% | Helped |
| add sequential preference to memory addressing (ablation) | AMEM · VisDial v0.9 | MRR: 0.6196 -> 0.6227 | Helped |
| add history embeddings (ablation) | AMEM+SEQ · VisDial v0.9 | MRR: 0.6227 -> 0.6210 | No clear effect |
Closest papers by meaning
- Recursive Visual Attention in Visual Dialog (CVPR 2019 · similarity 0.91)
- Visual Dialog (CVPR 2017 · similarity 0.91)
- Modality-Balanced Models for Visual Dialogue (AAAI 2020 · similarity 0.90)
- Image-Question-Answer Synergistic Network for Visual Dialog (CVPR 2019 · similarity 0.90)
- Re-Attention for Visual Question Answering (AAAI 2020 · similarity 0.89)
- FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering (NeurIPS 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.