Research map / Detection and segmentation / CNN features
Emotion-Aware Human Attention Prediction
Check 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 the sentiment mask generation branch (ablation) | EASal · EMOd | NSS: 1.78 -> 1.85 | Helped |
| Add the sentiment mask generation branch (ablation) | EASal · EMOd | KL: 5.54 -> 5.52 | Helped |
| Add the sentiment mask generation branch (ablation) | EASal · EMOd | IG: 1.59 -> 1.66 | Helped |
| Add the sentiment mask generation branch (ablation) | EASal · Affective CAT2000 | NSS: 2.09 -> 2.27 | Helped |
| Add the sentiment mask generation branch (ablation) | EASal · Affective CAT2000 | KL: 0.70 -> 0.65 | Helped |
| Add the sentiment mask generation branch (ablation) | EASal · Affective CAT2000 | IG: 29.27 -> 29.36 | Helped |
Closest papers by meaning
- Emotional Attention: A Study of Image Sentiment and Visual Attention (CVPR 2018 · similarity 0.93)
- Inferring Attention Shift Ranks of Objects for Image Saliency (CVPR 2020 · similarity 0.88)
- Learning from Observer Gaze: Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognition (CVPR 2024 · similarity 0.87)
- Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers (CVPR 2024 · similarity 0.87)
- Tensorized Attention for Understanding Multi-Object Relationships (AAAI 2025 · similarity 0.86)
- UniAR: A Unified model for predicting human Attention and Responses on visual content (NeurIPS 2024 · 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.