Research map / Vision-language and multimodal / Visual question answering
Visual Dialog
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 |
|---|---|---|---|
| Use a discriminative rather than generative decoder | VisDial models · VisDial v0.9 | MRR | Helped |
| Add image input to the question-only Late Fusion model (ablation) | LF-Q-G · VisDial v0.9 | MRR: 0.5048 -> 0.5204 | Helped |
| Add history to question-only Late Fusion model (ablation) | LF-Q-G · VisDial v0.9 | MRR: 0.5048 -> 0.5055 | No clear effect |
| Add history to image-and-question Late Fusion model (ablation) | LF-QI-G · VisDial v0.9 | MRR: 0.5204 -> 0.5199 | Hurt |
| Add image input to the question-and-history Late Fusion model (ablation) | LF-QH-G · VisDial v0.9 | MRR: 0.5055 -> 0.5199 | Helped |
| Add image input to the question-and-history HRE model (ablation) | HRE-QH-G · VisDial v0.9 | MRR: 0.5102 -> 0.5237 | Helped |
| Add attention over history (ablation) | HRE-QIH-G · VisDial v0.9 | MRR: 0.5237 -> 0.5242 | No clear effect |
| Add image input to the question-and-history Memory Network (ablation) | MN-QH-G · VisDial v0.9 | MRR: 0.5115 -> 0.5259 | Helped |
| Add image input to the question-only Late Fusion model (ablation) | LF-Q-D · VisDial v0.9 | MRR: 0.5508 -> 0.5759 | Helped |
| Add history to question-only Late Fusion model (ablation) | LF-Q-D · VisDial v0.9 | MRR: 0.5508 -> 0.5578 | Helped |
| Add history to image-and-question Late Fusion model (ablation) | LF-QI-D · VisDial v0.9 | MRR: 0.5759 -> 0.5807 | Helped |
| Add image input to the question-and-history Late Fusion model (ablation) | LF-QH-D · VisDial v0.9 | MRR: 0.5578 -> 0.5807 | Helped |
Closest papers by meaning
- Two Can Play This Game: Visual Dialog With Discriminative Question Generation and Answering (CVPR 2018 · similarity 0.94)
- V^2Dial: Unification of Video and Visual Dialog via Multimodal Experts (CVPR 2025 · similarity 0.91)
- Structure-Aware Multimodal Sequential Learning for Visual Dialog (AAAI 2024 · similarity 0.90)
- MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs (NeurIPS 2024 · similarity 0.90)
- Tackling Vision Language Tasks through Learning Inner Monologues (AAAI 2024 · similarity 0.89)
- Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models (ICML 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.