Research map / Vision-language and multimodal / Human and embodied modeling
Knowledge-Enriched Attention Network With Group-Wise Semantic for Visual Storytelling
Tengpeng Li, Hanli Wang, Bin He, Chang Wen Chen
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 the group-wise semantic module (GSM) (ablation) | KAGS · VIST test | BLEU-1: 68.4 -> 70.1 | Improved |
| add the group-wise semantic module (GSM) (ablation) | KAGS · VIST test | BLEU-2: 42.0 -> 43.5 | Improved |
| add the group-wise semantic module (GSM) (ablation) | KAGS · VIST test | CIDEr: 10.7 -> 11.3 | Improved |
| add the cascade cross-modal attention (CCA) (ablation) | KAGS · VIST test | METEOR: 35.5 -> 36.2 | Improved |
| add the cascade cross-modal attention (CCA) (ablation) | KAGS · VIST test | ROUGE_L: 30.5 -> 31.4 | Improved |
| add the knowledge-enriched attention network (KAN) (ablation) | KAGS · VIST test | BLEU-1: 66.7 -> 70.1 | Improved |
| add the knowledge-enriched attention network (KAN) (ablation) | KAGS · VIST test | BLEU-2: 41.7 -> 43.5 | Improved |
| add the knowledge-enriched attention network (KAN) (ablation) | KAGS · VIST test | CIDEr: 9.5 -> 11.3 | Improved |
| add KAN and GSM together (ablation) | KAGS · VIST test | BLEU-1: 62.6 -> 70.1 | Improved |
| add KAN and GSM together (ablation) | KAGS · VIST test | CIDEr: 7.8 -> 11.3 | Improved |
| KAGS versus IRW with external scene, commonsense and event graphs | IRW · VIST test | BLEU-1: 66.7 -> 70.1 | Improved |
| KAGS versus IRW on BLEU-4 | IRW · VIST test | BLEU-4: 15.4 -> 14.7 | Hurt |
Closest papers by meaning
- Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models (CVPR 2024 · similarity 0.86)
- StoryGPT-V: Large Language Models as Consistent Story Visualizers (CVPR 2025 · similarity 0.85)
- StoryWeaver: A Unified World Model for Knowledge-Enhanced Story Character Customization (AAAI 2025 · similarity 0.85)
- LogiStory: A Logic-Aware Framework for Multi-Image Story Visualization (ICLR 2026 · similarity 0.84)
- VinaBench: Benchmark for Faithful and Consistent Visual Narratives (CVPR 2025 · similarity 0.84)
- ViStoryBench: Comprehensive Benchmark Suite for Story Visualization (CVPR 2026 · similarity 0.84)
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.
