Research map / Image generation / Autoregressive and latent generation
Category-Guided Visual Question Generation (Student Abstract)
Hongfei Liu, Jiali Chen, Wenhao Fang, Jiayuan Xie, Yi Cai
Read the paperCheck 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 |
|---|---|---|---|
| use category-guided generation instead of GRNN-RCNN | Visual question generation on TDIUC · TDIUC | mBLEU3: 35.83 -> 8.48 | Improved |
| use category-guided generation instead of GRNN-RCNN | Visual question generation on TDIUC · TDIUC | BLEU4: 16.37 -> 9.81 | Hurt |
| use category-guided generation instead of QT | Visual question generation on TDIUC · TDIUC | BLEU4: 8.47 -> 9.81 | Improved |
| use category-guided generation instead of QT | Visual question generation on TDIUC · TDIUC | mBLEU3: 25.38 -> 8.48 | Improved |
| remove TF-IDF object weighting (ablation) | CGVQG · TDIUC | BLEU4: 8.78 -> 9.81 | Hurt |
| remove TF-IDF object weighting (ablation) | CGVQG · TDIUC | mBLEU3: 14.32 -> 8.48 | Hurt |
Closest papers by meaning
- Ask Questions With Double Hints: Visual Question Generation With Answer-Awareness and Region-Reference (TPAMI 2024 · similarity 0.90)
- Explicitly Guided Difficulty-Controllable Visual Question Generation (AAAI 2025 · similarity 0.89)
- ConVQG: Contrastive Visual Question Generation with Multimodal Guidance (AAAI 2024 · similarity 0.89)
- Information Maximizing Visual Question Generation (CVPR 2019 · similarity 0.89)
- Customized Image Narrative Generation via Interactive Visual Question Generation and Answering (CVPR 2018 · similarity 0.89)
- Image Content Generation with Causal Reasoning (AAAI 2024 · similarity 0.85)
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.
