Research map / Label-efficient and robust learning / Recognition and long-tail
Affective Image Content Analysis: Two Decades Review and New Perspectives
Sicheng Zhao, Xingxu Yao, Jufeng Yang, Guoli Jia, Guiguang Ding, Tat‐Seng Chua, Björn Wolfgang Schuller, Kurt Keutzer
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 global features to local features (ablation) | WSCNet · FI2 | accuracy: 0.894 -> 0.896 | Improved |
| add global features to local features (ablation) | PDANet · FI2 | accuracy: 0.807 -> 0.878 | Improved |
| add global features to local features (ablation) | PDANet · Comics | accuracy: 0.263 -> 0.588 | Improved |
| use global instead of local features (ablation) | PDANet · FI8 | accuracy: 0.606 -> 0.696 | Improved |
| add local features to global features (ablation) | PDANet · FI8 | accuracy: 0.696 -> 0.694 | No clear effect |
| add local features to global features (ablation) | WSCNet · Instagram | accuracy: 0.816 -> 0.804 | Hurt |
| add local features to global features (ablation) | WSCNet · Twitter II | accuracy: 0.824 -> 0.815 | Hurt |
| use deep MVSO features instead of hand-crafted PAEF | SVM/kNN/NB average · FI2 | accuracy: 0.717 -> 0.778 | Improved |
| use pre-trained VGGNet-16 features instead of PAEF | SVM/kNN/NB average · FI8 | accuracy: 0.309 -> 0.561 | Improved |
| use high-level SentiBank instead of mid-level PAEF | SVM/kNN/NB average · FI8 | accuracy: 0.309 -> 0.413 | Improved |
| use SVM instead of kNN classifier | feature classifiers · FI2 | accuracy: 0.721 -> 0.793 | Improved |
| use SVM instead of Naive Bayes classifier | feature classifiers · FI8 | accuracy: 0.349 -> 0.490 | Improved |
Closest papers by meaning
- Retrieving and Classifying Affective Images via Deep Metric Learning (AAAI 2018 · similarity 0.90)
- AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models (ICML 2025 · similarity 0.86)
- Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approach (ICLR 2026 · similarity 0.86)
- AI-generated Image Quality Assessment in Visual Communication (AAAI 2025 · similarity 0.86)
- MART: Masked Affective RepresenTation Learning via Masked Temporal Distribution Distillation (CVPR 2024 · similarity 0.86)
- Uncertain Multimodal Intention and Emotion Understanding in the Wild (CVPR 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.
