Research map / Image generation / GANs
Show, Reward and Tell: Automatic Generation of Narrative Paragraph From Photo Stream by Adversarial Training
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 |
|---|---|---|---|
| add both discriminators as rewards (ablation) | hierarchical story generator · SIND | METEOR: 11.03 -> 12.32 | Helped |
| add both discriminators as rewards (ablation) | hierarchical story generator · SIND | CIDEr: 9.79 -> 11.35 | Helped |
| add both discriminators as rewards (ablation) | hierarchical story generator · Disney | METEOR: 7.82 -> 9.90 | Helped |
| add both discriminators as rewards (ablation) | hierarchical story generator · NYC | METEOR: 7.39 -> 8.39 | Helped |
| add multi-modal discriminator to language-style discriminator (ablation) | hierarchical story generator · SIND | METEOR: 11.15 -> 12.32 | Helped |
| add language-style discriminator to multi-modal discriminator (ablation) | hierarchical story generator · SIND | METEOR: 12.19 -> 12.32 | Helped |
| use only language-style discriminator vs none (ablation) | hierarchical story generator · SIND | CIDEr: 9.79 -> 10.69 | Helped |
| use hierarchical generator instead of flat story model (Story-Flat) | story generator · SIND | METEOR: 10.25 -> 11.03 | Helped |
| set tradeoff lambda around 0.7 between discriminator rewards (ablation) | reward function · SIND | normalized metrics | Helped |
Closest papers by meaning
- Let Your Photos Talk: Generating Narrative Paragraph for Photo Stream via Bidirectional Attention Recurrent Neural Networks (AAAI 2017 · similarity 0.92)
- Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models (CVPR 2024 · similarity 0.88)
- One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt (ICLR 2025 · similarity 0.87)
- Rich Human Feedback for Text-to-Image Generation (CVPR 2024 · similarity 0.86)
- Learning to Sample Effective and Diverse Prompts for Text-to-Image Generation (CVPR 2025 · similarity 0.86)
- Subject-driven Text-to-Image Generation via Preference-based Reinforcement Learning (NeurIPS 2024 · similarity 0.86)
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.