Research map / Vision-language and multimodal / Human and embodied modeling
Affective Image Filter: Reflecting Emotions from Text to Images
Shuchen Weng, Peixuan Zhang, Zheng Chang, Xinlong Wang, Si Li, Boxin Shi
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 VAD dictionary affective embeddings to the text encoder (ablation) | AIF · AIF dataset test set | Style Difference (SD): 5.8416 -> 5.4147 | Improved |
| add VAD dictionary affective embeddings to the text encoder (ablation) | AIF · AIF dataset test set | Accuracy (%): 29.76 -> 29.96 | No clear effect |
| add sentiment extractor with sentiment metric loss and anchor-based sentiment loss (ablation) | AIF · AIF dataset test set | Sentiment Gap (per mille): 1.4799 -> 1.3881 | Improved |
| add emotional distribution estimator and emotional distribution loss (ablation) | AIF · AIF dataset test set | Accuracy (%): 26.48 -> 29.96 | Improved |
| add emotional distribution estimator and emotional distribution loss (ablation) | AIF · AIF dataset test set | SSIM (%): 53.75 -> 56.15 | Improved |
| add GAN loss with multi-level conditional-unconditional discriminator (ablation) | AIF · AIF dataset test set | Accuracy (%): 29.15 -> 29.96 | Improved |
| add GAN loss (ablation) | AIF · AIF dataset test set | SSIM (%): 56.07 -> 56.15 | No clear effect |
| use AIF instead of best prior method for emotion reflection | AIF vs CLVA/CLIPstyler/DiffusionCLIP/ManiGAN · AIF dataset test set | Accuracy (%): 27.77 -> 29.96 | Improved |
| use AIF instead of prior methods in human preference | AIF · User study (AMT) | preference score: 13.24 -> 54.68 | Improved |
Closest papers by meaning
- EmoEdit: Evoking Emotions through Image Manipulation (CVPR 2025 · similarity 0.88)
- EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Models (CVPR 2024 · similarity 0.87)
- Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approach (ICLR 2026 · similarity 0.87)
- A Unified and Interpretable Emotion Representation and Expression Generation (CVPR 2024 · similarity 0.86)
- EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment (ICML 2026 · similarity 0.86)
- AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models (ICML 2025 · 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.
