Research map / Vision-language and multimodal / Human and embodied modeling
Hierarchical Photo-Scene Encoder for Album Storytelling
Bairui Wang, Lin Ma, Wei Zhang, Wenhao Jiang, Feng Zhang
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 the scene encoder to HP (ablation) | HP · VIST test | CIDEr: 7.44 -> 7.75 | Improved |
| add the reconstructor to HP (ablation) | HP · VIST test | CIDEr: 7.44 -> 7.61 | Improved |
| add both the scene encoder and reconstructor to HP (ablation) | HP · VIST test | CIDEr: 7.44 -> 8.03 | Improved |
| increase ranking-loss weight from 0.0 to 0.2 (ablation) | HPS · VIST test | CIDEr: 6.99 -> 7.75 | Improved |
| increase ranking-loss weight from 0.2 to 0.5 (ablation) | HPS · VIST test | CIDEr: 7.75 -> 7.60 | Hurt |
| increase reconstruction-loss weight from 0.0 to 0.8 (ablation) | HPSR · VIST test | CIDEr: 7.75 -> 8.03 | Improved |
Closest papers by meaning
- Let Your Photos Talk: Generating Narrative Paragraph for Photo Stream via Bidirectional Attention Recurrent Neural Networks (AAAI 2017 · similarity 0.86)
- Beyond Single Images: A Comprehensive Benchmark for Album-Level Vision-Language Understanding (CVPR 2026 · similarity 0.85)
- Can Machines Understand Composition? Dataset and Benchmark for Photographic Image Composition Embedding and Understanding (CVPR 2025 · similarity 0.83)
- The Scene Language: Representing Scenes with Programs, Words, and Embeddings (CVPR 2025 · similarity 0.82)
- SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency (NeurIPS 2025 · similarity 0.82)
- Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models (CVPR 2024 · similarity 0.82)
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.
