Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Visual Sentiment Distributions via Augmented Conditional Probability Neural Network
Jufeng Yang, Ming Sun, Xiaoxiao Sun
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 |
|---|---|---|---|
| encode labels as binary vectors instead of integers (BCPNN) (ablation) | CPNN · Abstract (SentiBank) | Chebyshev distance: 0.2933 -> 0.2686 | Improved |
| encode labels as binary vectors instead of integers (BCPNN) (ablation) | CPNN · Emotion6 (SentiBank) | Chebyshev distance: 0.3495 -> 0.3542 | Hurt |
| add noise-augmented label distributions (ACPNN) (ablation) | BCPNN · Abstract (SentiBank) | Chebyshev distance: 0.2686 -> 0.2442 | Improved |
| ACPNN vs best LDL baseline AA-kNN | label distribution learning · Abstract (VGG features) | Average Rank: 1.67 -> 1.33 | Improved |
Closest papers by meaning
- Probing Sentiment-Oriented Pre-Training Inspired by Human Sentiment Perception Mechanism (CVPR 2023 · similarity 0.88)
- Structured and Sparse Annotations for Image Emotion Distribution Learning (AAAI 2019 · similarity 0.87)
- A Circular-Structured Representation for Visual Emotion Distribution Learning (CVPR 2021 · similarity 0.87)
- Retrieving and Classifying Affective Images via Deep Metric Learning (AAAI 2018 · similarity 0.86)
- Multiple Feature Refining Network for Visual Emotion Distribution Learning (AAAI 2025 · similarity 0.85)
- Seek Common Ground While Reserving Differences: Semi-Supervised Image-Text Sentiment Recognition (CVPR 2025 · 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.
