Research map / Detection and segmentation / Open-set and few-shot detection
Emotional Attention: A Study of Image Sentiment and Visual Attention
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 CASNet rather than SalGAN | Saliency prediction model · EMOd | NSS: 1.74 -> 1.75 | Helped |
| Use CASNet rather than SALICON | Saliency prediction model · EMOd | IG: 1.45 -> 1.58 | Helped |
| Use CASNet rather than SalGAN | Saliency prediction model · NUSEF | NSS: 1.72 -> 1.75 | Helped |
| Use CASNet rather than SALICON | Saliency prediction model · NUSEF | IG: 1.24 -> 1.35 | Helped |
| Use CASNet rather than SalGAN | Saliency prediction model · CAT2000 | NSS: 1.45 -> 1.50 | Helped |
| Use CASNet rather than SALICON | Saliency prediction model · CAT2000 | IG: 0.27 -> 0.46 | Helped |
| Add the channel weighting subnetwork (ablation) | CASNet · EMOd | NSS: 1.61 -> 1.75 | Helped |
| Add the channel weighting subnetwork (ablation) | CASNet · EMOd | IG: 1.48 -> 1.58 | Helped |
| Add the channel weighting subnetwork (ablation) | CASNet · NUSEF | NSS: 1.67 -> 1.75 | Helped |
| Add the channel weighting subnetwork (ablation) | CASNet · NUSEF | IG: 1.29 -> 1.35 | Helped |
| Add the channel weighting subnetwork (ablation) | CASNet · CAT2000 | NSS: 1.36 -> 1.50 | Helped |
| Add the channel weighting subnetwork (ablation) | CASNet · CAT2000 | IG: 0.30 -> 0.46 | Helped |
Closest papers by meaning
- Emotion-Aware Human Attention Prediction (CVPR 2019 · similarity 0.93)
- Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approach (ICLR 2026 · similarity 0.88)
- EmoEdit: Evoking Emotions through Image Manipulation (CVPR 2025 · similarity 0.87)
- UniAR: A Unified model for predicting human Attention and Responses on visual content (NeurIPS 2024 · similarity 0.87)
- EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment (ICML 2026 · similarity 0.86)
- Multiple Feature Refining Network for Visual Emotion Distribution Learning (AAAI 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.