Research map / Label-efficient and robust learning / Recognition and long-tail
A Circular-Structured Representation for Visual Emotion Distribution Learning
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 |
|---|---|---|---|
| Use the circular-structured representation and PC loss rather than the strongest listed baseline | Visual emotion distribution learning · Flickr_LDL | KL: 0.44(2) -> 0.41(1) | Helped |
| Use the circular-structured representation and PC loss rather than the strongest listed baseline | Visual emotion distribution learning · Twitter_LDL | Accuracy: 0.77(2) -> 0.78(1) | Helped |
| Add polar loss to KL loss (ablation) | Visual emotion distribution learning · Flickr_LDL | Accuracy: 0.669 -> 0.695 | Helped |
| Add type loss to KL loss (ablation) | Visual emotion distribution learning · Flickr_LDL | Accuracy: 0.669 -> 0.700 | Helped |
| Add polar and type losses to KL loss (ablation) | Visual emotion distribution learning · Flickr_LDL | Accuracy: 0.669 -> 0.718 | Helped |
| Add emotion-intensity weighting to polar and type constraints (ablation) | Progressive Circular loss · Flickr_LDL | Accuracy: 0.718 -> 0.721 | Helped |
| Add polar loss to KL loss (ablation) | Visual emotion distribution learning · Twitter_LDL | Accuracy: 0.744 -> 0.764 | Helped |
| Add type loss to KL loss (ablation) | Visual emotion distribution learning · Twitter_LDL | Accuracy: 0.744 -> 0.770 | Helped |
| Add polar and type losses to KL loss (ablation) | Visual emotion distribution learning · Twitter_LDL | Accuracy: 0.744 -> 0.779 | Helped |
| Add emotion-intensity weighting to polar and type constraints (ablation) | Progressive Circular loss · Twitter_LDL | Accuracy: 0.779 -> 0.781 | Helped |
| Combine PC loss with KL loss instead of using KL loss alone (ablation) | Visual emotion distribution learning · Twitter_LDL | Accuracy: 0.744 -> 0.781 | Helped |
Closest papers by meaning
- Bridge Then Begin Anew: Generating Target-Relevant Intermediate Model for Source-Free Visual Emotion Adaptation (AAAI 2025 · similarity 0.87)
- Multiple Feature Refining Network for Visual Emotion Distribution Learning (AAAI 2025 · similarity 0.87)
- Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approach (ICLR 2026 · similarity 0.86)
- Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognition (CVPR 2025 · similarity 0.86)
- To Err Like Human: Affective Bias-Inspired Measures for Visual Emotion Recognition Evaluation (NeurIPS 2024 · similarity 0.85)
- Enriching Multimodal Sentiment Analysis Through Textual Emotional Descriptions of Visual-Audio Content (AAAI 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.