Research map / Label-efficient and robust learning / Recognition and long-tail
Structured and Sparse Annotations for Image Emotion Distribution Learning
Haitao Xiong, Hongfu Liu, Bineng Zhong, Yun Fu
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 sparse regularization Rsr based on emotional intensity (ablation) | SSDL · Emotion6 | KL divergence: 0.43 -> 0.41 | Improved |
| add sparse regularization Rsr (ablation) | SSDL · Emotion6 | Cosine: 0.79 -> 0.81 | Improved |
| combine EMD-based loss with KL loss instead of either alone (ablation) | SSDL · Emotion6 | KL divergence / Cosine / accuracy | Improved |
| vary EMD weight mu from 0.5 to 0.8 (ablation) | SSDL combined loss · Emotion6 | KL divergence / Cosine / accuracy | No clear effect |
| use SSDL structured and sparse annotations instead of JCDL | VGG-19 emotion distribution model · Emotion6 | accuracy: 0.52 -> 0.53 | Improved |
| use SSDL instead of DLDL (KL loss only) | VGG-19 emotion distribution model · Flickr LDL | KL divergence: 0.54 -> 0.46 | Improved |
| use SSDL instead of AA-kNN | emotion distribution learning · Flickr LDL | Clark: 0.57 -> 0.78 | Hurt |
Closest papers by meaning
- A Circular-Structured Representation for Visual Emotion Distribution Learning (CVPR 2021 · similarity 0.88)
- Learning Visual Sentiment Distributions via Augmented Conditional Probability Neural Network (AAAI 2017 · similarity 0.87)
- Retrieving and Classifying Affective Images via Deep Metric Learning (AAAI 2018 · similarity 0.87)
- Contemplating Visual Emotions: Understanding and Overcoming Dataset Bias (ECCV 2018 · similarity 0.87)
- Multiple Feature Refining Network for Visual Emotion Distribution Learning (AAAI 2025 · similarity 0.85)
- FindingEmo: An Image Dataset for Emotion Recognition in the Wild (NeurIPS 2024 · similarity 0.84)
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.
