Research map / Vision-language and multimodal / Human and embodied modeling
SentiCap: Generating Image Descriptions with Sentiments
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 |
|---|---|---|---|
| switching RNN with word-level sentiment (SentiCap) vs RNN-Transfer | caption generator · SentiCap NEG | CIDEr: 55.9 -> 61.8 | Helped |
| SentiCap vs RNN-Transfer | caption generator · SentiCap POS | CIDEr: 54.1 -> 54.4 | No clear effect |
| SentiCap vs ANP insertion baselines | caption generator · SentiCap POS | human-judged sentiment: 84.8% -> 88.4% | Helped |
| adding sentiment via SentiCap | CNN+RNN · SentiCap NEG | descriptiveness: 2.81 -> 2.40 | Hurt |
| SentiCap vs CNN+RNN | caption generator · combined | novel caption %: 38.2% -> 95.7% | Helped |
Closest papers by meaning
- A Hierarchical Approach for Generating Descriptive Image Paragraphs (CVPR 2017 · similarity 0.87)
- CoEmoGen: Towards Semantically-Coherent and Scalable Emotional Image Content Generation (ICLR 2026 · similarity 0.87)
- Noise-Aware Image Captioning with Progressively Exploring Mismatched Words (AAAI 2024 · similarity 0.86)
- StyleNet: Generating Attractive Visual Captions With Styles (CVPR 2017 · similarity 0.86)
- EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Models (CVPR 2024 · similarity 0.85)
- EmoEdit: Evoking Emotions through Image Manipulation (CVPR 2025 · 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.