Research map / Vision-language and multimodal / Human and embodied modeling
Story Visualization by Online Text Augmentation with Context Memory
Daechul Ahn, Daneul Kim, Gwangmo Song, Seung Hwan Kim, Honglak Lee, Dongyeop Kang, Jonghyun Choi
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 partial-level memory connection (last layer only) (ablation) | Single Directional Transformer · Pororo-SV (64x64) | FID: 63.88 -> 59.05 | Improved |
| add attentively weighted memory (AWM) (ablation) | PMA · Pororo-SV (64x64) | FID: 59.05 -> 56.98 | Improved |
| add bi-directional training (ablation) | PMA + AWM · Pororo-SV (64x64) | Char. F1 / Frm. Acc.: FID 56.98 -> 54.69; Char. F1 50.15 -> 51.27; Frm. Acc. 22.01 -> 22.15 | Mixed |
| add online text augmentation (ablation) | PMA + AWM + Bi. · Pororo-SV (64x64) | FID: 54.69 -> 52.13 | Improved |
| use online instead of offline pseudo-text augmentation (ablation) | CMOTA · Pororo-SV (64x64) | FID: 54.51 -> 52.13 | Improved |
| use partial-level memory connection instead of all-level (ablation) | CMOTA · Pororo-SV (64x64) | FID: 61.23 -> 59.05 | Improved |
| increase resolution from 64x64 to 128x128 | CMOTA · Flintstones-SV | FID: FID 36.71 -> 54.81; Char. F1 79.74 -> 86.44 | Mixed |
| use CMOTA instead of VP-CSV (character-centric module) | CMOTA · Pororo-SV (64x64) | Char. F1: 56.84 -> 53.25 | Hurt |
| use CMOTA (96.6M) instead of 1.3B StoryDALL-E fine-tune | CMOTA · Pororo-SV | FID: 25.90 -> 55.26 | Hurt |
| add context memory (ablation) | CMOTA · human study, temporal consistency | preference (%): 34.5% -> 61.2% | Improved |
Closest papers by meaning
- StoryGPT-V: Large Language Models as Consistent Story Visualizers (CVPR 2025 · similarity 0.89)
- LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts (ICLR 2024 · similarity 0.87)
- Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models (AAAI 2025 · similarity 0.87)
- Magnifying What Matters: Attention-Guided Adaptive Rendering for Visual Text Comprehension (NeurIPS 2026 · similarity 0.87)
- One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt (ICLR 2025 · similarity 0.87)
- Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models (CVPR 2024 · similarity 0.87)
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.
