Research map / Large language models / Retrieval and knowledge
Knowledge-Enriched Visual Storytelling
Chao-Chun Hsu, Zi-Yuan Chen, Chi-Yang Hsu, Chih-Chia Li, Tzu-Yuan Lin, Ting-Hao Huang, Lun-Wei Ku
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 |
|---|---|---|---|
| add knowledge-graph enrichment using OpenIE (ablation) | KG-Story · Human Evaluation (with images) | Avg. Rank (1 to 5): 3.152 -> 2.975 | Improved |
| add knowledge-graph enrichment using Visual Genome (ablation) | KG-Story · Human Evaluation (with images) | Avg. Rank (1 to 5): 3.152 -> 2.975 | Improved |
| add knowledge-graph enrichment using OpenIE (ablation) | KG-Story · Human Evaluation (without images) | Avg. Rank (1 to 5): 3.285 -> 3.049 | Improved |
| add knowledge-graph enrichment using Visual Genome (ablation) | KG-Story · Human Evaluation (without images) | Avg. Rank (1 to 5): 3.285 -> 2.990 | Improved |
| add knowledge-graph enrichment (ablation) | KG-Story · VIST | BLEU1: .376 -> .446 (OpenIE); .376 -> .451 (Visual Genome) | Improved |
| add knowledge-graph enrichment (ablation) | KG-Story · VIST | ROUGE: .237 -> .241 | Mixed |
| add knowledge-graph enrichment (ablation) | KG-Story · VIST | CIDEr: .055 -> .094 (OpenIE); .055 -> .096 (Visual Genome) | Improved |
| use Visual Genome instead of OpenIE for knowledge enrichment | KG-Story · Human Evaluation (with images) | Avg. Rank (1 to 5): 2.975* -> 2.975* | No clear effect |
| use Visual Genome instead of OpenIE for knowledge enrichment | KG-Story · VIST | BLEU1: .446 -> .451 | Improved |
Closest papers by meaning
- Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models (CVPR 2024 · similarity 0.88)
- StoryWeaver: A Unified World Model for Knowledge-Enhanced Story Character Customization (AAAI 2025 · similarity 0.88)
- StoryGPT-V: Large Language Models as Consistent Story Visualizers (CVPR 2025 · similarity 0.86)
- Is Your World Simulator a Good Story Presenter? A Consecutive Events-Based Benchmark for Future Long Video Generation (CVPR 2025 · similarity 0.86)
- One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt (ICLR 2025 · similarity 0.85)
- VinaBench: Benchmark for Faithful and Consistent Visual Narratives (CVPR 2025 · 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.
