Research map / Vision-language and multimodal / Human and embodied modeling
Hide-and-Tell: Learning to Bridge Photo Streams for Visual Storytelling
Read the paperCheck 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 hide-and-tell training, omitting image features during training (ablation) | INet · VIST test | CIDEr: 9.9 -> 10.0 | Helped |
| Add non-local layers to model inter-frame relations (ablation) | INet · VIST test | CIDEr: 9.4 -> 10.0 | Helped |
| Add the second RNN-NL telling block for feature refinement (ablation) | INet · VIST test | CIDEr: 9.2 -> 10.0 | Helped |
| Increase hidden image features gradually from 0 to 2 during training (ablation) | INet · VIST test | BLEU-4: 13.9 -> 14.7 | Helped |
| Use a fixed two-image dropout rather than a gradual curriculum (ablation) | INet · VIST test | CIDEr: 9.2 vs 10.0 | Hurt |
| Replace XE-ss with INet | Visual storytelling model · VIST test | METEOR: 34.8 -> 35.6 | Helped |
| Replace XE-ss with INet | Visual storytelling model · VIST test | CIDEr: 8.7 -> 10.0 | Helped |
| Compare INet with XE-ss in a preference study without hidden test images | INet · VIST user study | human preference (%): 24.7 % vs 55.2 % | Helped |
| Use one hidden image at inference instead of full input | INet · VIST user study | human preference (%): 30.9 % vs 40.5 % | Helped |
Closest papers by meaning
- Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models (CVPR 2024 · similarity 0.88)
- VinaBench: Benchmark for Faithful and Consistent Visual Narratives (CVPR 2025 · similarity 0.86)
- Storybooth: Training-Free Multi-Subject Consistency for Improved Visual Storytelling (ICLR 2025 · similarity 0.86)
- StoryGPT-V: Large Language Models as Consistent Story Visualizers (CVPR 2025 · similarity 0.86)
- ContextualStory: Consistent Visual Storytelling with Spatially-Enhanced and Storyline Context (AAAI 2025 · similarity 0.85)
- LogiStory: A Logic-Aware Framework for Multi-Image Story Visualization (ICLR 2026 · 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.